JP2008210323A - Layout evaluation apparatus, electronic device, layout evaluation method, and control program - Google Patents

Abstract

A layout evaluation apparatus, an electronic apparatus, a layout evaluation method, and a control program capable of obtaining an index capable of quantitatively evaluating the layout of an entire framed image.
A layout image with a frame in which a group of images are laid out in a layout frame is a “field” existing around the group of images and the image representing the layout frame, and the strength of the “field” Depends on the distance from the image, and the visual induction field calculation unit 13 for calculating a visual induction field having a larger value as it is closer to the image, and the complexity of the closed curved surface of the line connecting the equipotential values in this visual induction field The layout evaluation unit 14 calculates a degree, calculates a scale parameter of the sigmoid function when the correspondence between the complexity and the equipotential value is approximated by a sigmoid function, and evaluates the layout based on the scale parameter. I was prepared to.
[Selection] Figure 9

Description

The present invention relates to a layout evaluation apparatus, an electronic apparatus, a layout evaluation method, and a control program for evaluating an image obtained by laying out a group of images to be laid out in a layout frame.

Conventionally, layouts such as typesetting have been used for graphic and character layouts (for example, JIS standard X4).
However, there are cases where it is difficult to lay out figures and characters in the most readable manner with this rule alone. For this reason, the actual situation is that the creation of the layout and the judgment of the quality of the layout depend on the sense of the designer, and other than the designer cannot quantitatively judge the quality of the layout.
Against this background, in recent years, a technique has been proposed for obtaining an index for quantifying the quality of a layout by using the concept of “visual guidance field” (see, for example, Patent Document 1).

In the technique of Patent Document 1, there is no layout frame indicating the size of the printing paper around the figure or character (see FIG. 15A), that is, the state where the figure or character is arranged on an infinite plane. Calculate the visual induction field for an image that has a layout evaluation target and does not have this layout frame, obtain an equipotential line from the visual induction field, calculate the complexity of each equipotential line, The average value of the complexity (hereinafter referred to as complexity Cav) is used as an index for evaluating the quality of the layout.
JP 2003-30673 A

However, in general, graphics and characters are distributed as printed matter, so FIG.
As shown in FIG. 2, it is a common experience that the margin Y between the layout frame W and the document portion X greatly affects the readability of the document. The margin setting is a setting that the document creator pays attention to even when word processor software is used.

However, when an attempt is made to evaluate a framed image including the layout frame W by the technique of the above-mentioned Patent Document 1, as shown in FIG. 16, the complexity Cav calculated by changing the margin Y of each image, the line spacing, etc. As a result, the readability of each image does not correspond to the result of the sensibility evaluation, which makes it difficult to evaluate the layout.
For example, as shown in FIG. 16, when the complexity Cav is the same value (complexity C0), the evaluation of “difficult to read” and the evaluation of “very easy to read” (corresponding to the range Area) And this complexity Cav alone is a “very easy to read” evaluation,
It is difficult to accurately determine whether the layout is highly evaluated.

The present invention has been made in view of the above-described circumstances, and provides a layout evaluation apparatus, an electronic device, a layout evaluation method, and a control program capable of obtaining an index capable of quantitatively evaluating the layout of a framed image. There is.

In order to solve the above-described problem, the present invention provides a layout evaluation apparatus for evaluating a layout of a framed layout image in which a group of images are laid out in a layout frame, and the grouped layout image is compared with the grouped layout image. The “field” that exists around the image and the image representing the layout frame, and the strength of the “field” depends on the distance from the image, and the visual induction field that has a larger value as it is closer to the image is calculated. Approximating the correspondence between the complexity and the equipotential value with a sigmoid function, and the complexity calculating means for calculating the complexity of the closed surface of the line connecting the equipotential values in the visual induction field And an evaluation index calculating means for calculating a scale parameter of the sigmoid function in the case of being performed, and an evaluation means for evaluating the layout based on the scale parameter. To.
According to the present invention, for a layout image with a frame, a group of images laid out on the image and a “field” existing around the image indicating the layout frame, where the strength of the “field” is the image Depending on the distance from the image, the visual guidance field that has a larger value closer to the image is calculated,
Calculate the complexity of the closed surface of the line connecting the equipotential values in this visual induction field, and calculate the scale parameter of the sigmoid function when the correspondence between this complexity and the equipotential value is approximated by a sigmoid function. Since the layout is evaluated based on the scale parameter, the layout of the framed image can be quantitatively evaluated.

で定義することが好ましい。 In the above configuration, the sigmoid function has a complexity of C, a potential value of p, a scale parameter of T, a range of a, an offset value of b, and a parameter of p0.

Is preferably defined as

In addition, in the above configuration, it is preferable that when the scale parameter is not within a predetermined range, layout changing means for changing the framed layout image to be evaluated to a framed layout image of a different layout is provided. According to this configuration, when the scale parameter is not within the predetermined range, the layout quality can be re-evaluated with the layout image with the frame changed.

In the above configuration, the group of images includes either a character or a graphic, and storage means for storing a template that defines at least one of the layout frame, a margin between the layout frame and a line. Preferably, the guidance field calculation means calculates the visual guidance field for the framed layout image by laying out the group of images in the layout frame based on the template. According to this configuration, the user does not need to set a layout frame in advance.

Further, in the above-mentioned configuration, it has an average complexity calculation means for calculating the average value of the complexity, and a complexity evaluation means for evaluating a layout based on the average value of the complexity, the complexity evaluation means Preferably, the visual induction field is calculated for the framed layout image evaluated as being high. According to this configuration, the layout is evaluated based on the average value of the complexity, and the visual induction field is calculated for the framed layout image evaluated to be high. It is possible to reduce the processing amount and the processing time. In addition, the present invention can be widely applied to electronic devices including the layout evaluation device.

The present invention is also a layout evaluation method for evaluating a layout of a framed layout image in which a group of images are laid out in a layout frame, wherein the grouped image and the layout frame are compared with the framed layout image. Exists around the image that represents
Field, wherein the strength of the field depends on the distance from the image, and a visual field that calculates a visual induction field having a larger value as the image is closer to the image, and the like in the visual induction field, etc. A complexity calculation step for calculating the complexity of the closed surface of the line connecting the potential values, and an evaluation index for calculating the scale parameter of the sigmoid function when the correspondence between the complexity and the equipotential value is approximated by a sigmoid function It comprises a calculation step and an evaluation step for evaluating a layout based on the scale parameter.
According to the present invention, for a layout image with a frame, a group of images laid out on the image and a “field” existing around the image indicating the layout frame, where the strength of the “field” is the image Depending on the distance from the image, the visual guidance field that has a larger value closer to the image is calculated,
Calculate the complexity of the closed surface of the line connecting the equipotential values in this visual induction field, and calculate the scale parameter of the sigmoid function when the correspondence between this complexity and the equipotential value is approximated by a sigmoid function. Since the layout is evaluated based on the scale parameter, the layout of the framed image can be quantitatively evaluated.

In addition to being applied to the layout evaluation apparatus, electronic apparatus, and layout evaluation method described above, the present invention makes it possible to download a control program for carrying out the present invention via an electric communication line, or to download such a program. The present invention can also be implemented in such a manner that it is stored in a computer-readable recording medium such as a magnetic recording medium, an optical recording medium, or a semiconductor recording medium and distributed.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
<First Embodiment>
Since the layout evaluation apparatus 10 according to the present embodiment evaluates a layout using the concept of “visual guidance field”, the visual guidance field will be described first.
The visual induction field is a psychological concept that explains the visual perception phenomenon such as pattern recognition, assuming a field like an electrostatic field around the figure. “Psychology of shape” by Yoshimasa Yokose (Nagoya University) Publication (
1986)) (hereinafter referred to as a reference paper).
In this reference paper, the distribution of visual guidance fields (hereinafter simply referred to as induction fields) is related to how we see and feel our objects, such as the similarity of letters and the interpretation of optical illusions. Yes. In this reference paper, since the target is a figure composed of straight lines and arcs, an induction field for an arbitrary digital image is not required. Here, a method for calculating an induction field in a black and white binary digital image (hereinafter referred to as a binary image) will be described first.

Since the induction field can be basically interpreted as a Coulomb potential, the pixels constituting the outline of the pattern are assumed to be point charges, and the distribution of the induction field in the digital image is calculated from the accumulation of the Coulomb potential generated by them.

FIG. 1 is a diagram showing a pixel arrangement of a digital image. As shown in FIG. 1, it is assumed that an induction field is formed at an arbitrary point P by a curve f (s) composed of n point sequences. This curve f
(S) corresponds to a line segment of a line figure or an outline of an image figure. Then, each point p1, p2,..., Pi,..., Pn constituting the curve f (s) is assumed to be a point charge having a positive charge 1, and the curve f (s) is scanned from the point P. N points p1, p2,..., Pi,.
..., Where pn is found and the distance to each point on the curve f (s) found by scanning is ri, the strength Mp of the induction field at the point P is defined as follows.

この式（２）を用いることにより、任意のディジタル画像の誘導場を求めることができ
る。また、曲線が複数ある場合、点Ｐにおける誘導場の強さは個々の曲線が点Ｐにつくる
誘導場の和になる。なお、式（２）は点Ｐから発した光が直接当たる部分のみ和をとると
いう制約条件がつく。例えば、点Ｐに対して、曲線ｆ１（ｓ），ｆ２（ｓ），ｆ３（ｓ）
が図２に示すように存在しているとすると、点Ｐから見えない部分、つまり、この場合、
曲線ｆ１（ｓ）に遮蔽されて点Ｐから見えない範囲Ｚに存在する部分の和はとらない。こ
の図２の例では、曲線ｆ３（ｓ）のすべてと曲線ｆ２（ｓ）の一部の和はとらないことに
なる。これを、ここでは遮蔽条件という。

By using this equation (2), the induction field of an arbitrary digital image can be obtained. When there are a plurality of curves, the strength of the induction field at the point P is the sum of the induction fields created by the individual curves at the point P. It should be noted that Equation (2) has a constraint that only the portion directly irradiated with light emitted from the point P is summed. For example, for the point P, the curves f1 (s), f2 (s), f3 (s)
Is present as shown in FIG. 2, the part that cannot be seen from the point P, that is, in this case,
The sum of the portions present in the range Z that is shielded by the curve f1 (s) and cannot be seen from the point P is not taken. In the example of FIG. 2, the sum of all of the curve f3 (s) and a part of the curve f2 (s) is not taken. This is referred to herein as a shielding condition.

FIG. 3A shows an example of the induction field calculated by the above-described equation (1) assuming that all the pixels are point charges of charge 1 for the letter “A”. A thin line distributed in contour lines on the map around the letter “A” in FIG. 3A is an equipotential line drawn by connecting the equipotential values in the induction field. The strength (potential value) becomes weak and eventually approaches 0 (zero).
The characteristics in the shape and strength of the distribution of the induction field in FIG. 3A, particularly the characteristics near the apex of “A” are sharper than others, are related to the vicinity of the corner of the figure such as a rectangle or a triangle according to the aforementioned reference paper. It agrees with the result of psychological experiment on the distribution of the induction field.

FIG. 3B shows an induction field in which all the pixels are assumed to be a point charge of charge 1 without the above-described shielding condition (the sum of the portions existing in the range Z invisible from an arbitrary point P is not taken). For example,
The distribution of the induction field is rounded as a whole, which is different from the result of the psychological experiment by the reference paper mentioned above. Thus, the shielding condition is important in characterizing the induction field.

In this way, a visual guidance field for a certain character can be obtained. Examples of techniques using such visual guidance fields include, for example, “Michihiro Nagaishi:“ Easy-to-read Japanese proportional display using visual guidance fields ”, Journal of the Institute of Image Media and Technology, Vol. 52, No.
. 12, pp. 1865-1872 (1998) (hereinafter referred to as the first paper), Masazumi Miyoshi, Yoshifumi Shimoshiro, Hiroaki Koga, Ken Ideguchi: “Design of character layout based on sensibility using the visual induction field theory”, Electronics IEICE Transactions, 82-A, 9, 1465-1473 (1999)
”” (Hereinafter referred to as the second paper). Incidentally, the author of the first paper mentioned above is the inventor of the present invention.

By using such a visual guidance field, it is possible to evaluate the sensibility of images that have relied on human intuition and manual work. In this embodiment, an image (hereinafter referred to as a framed layout image) in which a group of images made up of characters and figures (including photographs, pictures, and tables) to be laid out are laid out in a predetermined layout frame W. This is a quantitative evaluation of whether the layout is easy to read. Hereinafter, a method for evaluating a framed layout image will be described in detail.

For example, as shown in FIG. 4, the framed layout image to be evaluated is an image in which a text portion X composed of a plurality of character strings is arranged in a layout frame W corresponding to a paper frame. In FIG. 4, the sentence portion X is indicated by a thick line, but it may be a character image or a thick line image proportional to the character size. Y indicates a margin.
First, in this embodiment, a visual induction field is obtained from a group of images (text portion X) laid out and an image of the layout frame W, and the degree of unevenness of the closed surface of the equipotential line is shown from this induction field. Find the complexity. This complexity can be obtained by the following equation (3) when the complexity of a closed curve having an equipotential value i is represented by Ci.

ここで、Ｌｉは、等ポテンシャル値ｉの等ポテンシャル面の周囲長であり、Ｓｉは面積
である。なお、周囲長Ｌｉは、等ポテンシャル面の輪郭を構成するドット数と考えること
ができ、面積Ｓｉは、等ポテンシャル面に存在するドット数と考えることができる。

Here, Li is the perimeter of the equipotential surface having the equipotential value i, and Si is the area. The peripheral length Li can be considered as the number of dots constituting the contour of the equipotential surface, and the area Si can be considered as the number of dots existing on the equipotential surface.

According to this equation (3), the longer the circumference length Li and the smaller the area Si, the larger the value of the complexity Ci, that is, the greater the equipotential line unevenness, the greater the value of the complexity Ci.
Then, the relationship between the complexity Ci and the equipotential value i (hereinafter, a potential value not limited to the equipotential value i is expressed as p) is indicated by a curve, thereby “visual guidance field distribution of the layout image” ( The difference in the induction field distribution information) can be expressed easily and visually.

The curve representing the “visual guidance field distribution of the layout image” is a monotonically increasing function, which can be approximated by a sigmoid function in most cases.
The sigmoid function is a function well known for weighting each node in a neural network or the like, and is expressed by the following equation (4) when the complexity C and the potential value p are used.

ここで、値ａはレンジであり、値ｂはオフセット値であり、値Ｔ及び値ｐ０はパラメー
タである。また、これらパラメータのうち、値Ｔは、「シグモイド関数の尺度母数」と称
される値であり、ニューラルネットワークではその逆数をユニットの「温度」と呼ぶこと
もある値である。

Here, the value a is a range, the value b is an offset value, and the value T and the value p0 are parameters. Of these parameters, the value T is a value called “scale parameter of the sigmoid function”, and in the neural network, the reciprocal is a value sometimes called the “temperature” of the unit.

FIG. 5 shows an example of a sigmoid function. The sigmoid function is particularly characterized by the rising portion indicated by the symbol α in the figure, and this sigmoid function indicates the correspondence relationship between the complexity C of the “visual guidance field distribution of the layout image” and the potential value p. It is suitable for expressing the tendency of a curve.
Therefore, by obtaining a sigmoid function representing the correspondence between the complexity C and the potential value p, it is possible to easily obtain information obtained by quantifying the “distribution information” of the visual guidance field of the layout image. It is.

Here, FIG. 6 shows the result of evaluating the readability (or readability) of a plurality of framed layout images 100 having different layouts by a psychological experiment. This figure shows the evaluation result of each framed layout image 100 in which the line spacing and the margin are changed under the same number of character strings. In this figure, each framed layout image 100 is represented by “i = 0” to “i” to “i = n” (n
Is a natural number), “i” indicates the optimum layout between the line spacing and the margin, and “i = 0”.
The line spacing is narrower and the margin is wider as it goes to the "" side, while the line spacing is wider and the margin is narrower as it goes to the "i = n" side. In addition, the number attached | subjected to each layout image has shown the average value at the time of five-step evaluation by several persons.

FIG. 7 shows the respective induction fields calculated for these framed layout images 100 to obtain the complexity C and the potential value p of the distribution of the induction field, and the corresponding relationship is represented by a curve.
As shown in FIG. 7, when the curves corresponding to “i = 0”, “i−1”, “i”, and “i = n” in FIG. 6 are compared, the shape of each curve differs depending on the layout. However, an easy-to-read item does not have a similar curved shape, and even an easy-to-read item has a different distribution area. For this reason, it has been difficult to evaluate readability (or readability) with a curved shape or distribution region.

Next, each curve was approximated with a sigmoid function, and the correlation between the parameters of the sigmoid function and the “readability” of each layout was examined. As shown in FIG. 8, the scale parameter T of the sigmoid function, It was found that there was a strong negative correlation with “readability”.
Therefore, in this embodiment, the scale parameter T of the sigmoid function is used as an evaluation index for layout, and a layout having the smallest scale parameter T as much as possible is determined as the most appropriate layout. Next, the configuration and operation of the layout evaluation apparatus 10 will be described.

FIG. 9 is a block diagram showing a functional configuration of the layout evaluation apparatus 10. The layout evaluation apparatus 10 electronically inputs a group of images to be laid out, arranges them in a frequently used layout, searches for an optimal layout based on the layout, and displays the result. I do.
More specifically, the layout evaluation apparatus 10 includes a layout target image input unit (image input unit) 11 for inputting a group of image data to be laid out, and a storage unit (storage unit) for storing a template for defining a layout. 12, a visual induction field calculation unit (guidance field calculation means) 13 for calculating a visual induction field, and a layout evaluation unit (evaluation means) for evaluating a layout based on the calculation result of the visual induction field calculation unit 13 14 and a display unit (notification means) 15 capable of displaying the processing status and evaluation results of the layout evaluation unit 14.

The layout target image input unit 11 inputs a group of image data composed of characters and figures (including photographs, pictures, and tables) to be laid out, and this image data is a multi-color image or an image with gradation. The threshold value of the binarization process is set so that the line segment is not interrupted, and the binarization process is performed with this threshold value to convert it into a binary image. Further, the layout target image input unit 11 may input data in a text format or a file format used in word processing software, and convert them into a binary image.

As a template stored in the storage unit (storage unit) 12, a template that is commonly used is applied. For example, information defining the layout frame W (paper size, portrait / landscape, etc.), layout frame W, Margins, line spacing, etc. are specified.
The visual induction field calculation unit 13 calculates the induction field of the framed layout image laid out on the template, and a group of images (for example, document portion X (FIG. 4)) to be laid out after layout, And, by calculating the induction field for the image showing the layout frame W of this image, and acquiring the equipotential line distribution information from this induction field, the layout image (layout image with frame) including the layout frame W is obtained. Get the distribution information of the induction field.

The layout evaluation unit 14 includes a layout change unit (layout change unit) 20 that rearranges the layout of the framed layout image laid out in the template (for example, changes the line spacing and margins) and the scale parameter calculation unit 30. is doing. The scale parameter calculation unit 30 calculates the complexity C for each potential value p from the distribution information of the induction field obtained by the visual guidance field calculation unit 13, and the correspondence between the complexity C and the potential value p. A sigmoid function approximating the relationship is calculated to obtain a “scale parameter T” of the sigmoid function. That is, the scale parameter calculation unit 30 functions as a complexity calculation unit that calculates the complexity C, and also functions as an evaluation index calculation unit that calculates a sigmoid function to obtain a scale parameter. In this way, the scale parameter calculation unit 3
The “scale parameter T” serving as a layout evaluation index is calculated from the framed layout image by the 0 and visual guidance field calculation unit 13.

The layout evaluation unit 14 evaluates the quality of the layout based on the “scale parameter T” calculated by the scale parameter calculation unit 30 and determines which layout is optimal. In addition, each part of the layout evaluation apparatus 10 mentioned above can be comprised by the arithmetic processing part which performs the said process. Specifically, each arithmetic processing may be configured by one or a plurality of semiconductor integrated circuits that perform hardware processing, or a CPU or R that performs software processing.
You may comprise by general purpose computers, such as OM and RAM. Arithmetic processing with a relatively large amount of calculation such as visual guidance field calculation processing is performed by hardware processing, and arithmetic processing with a relatively small amount of calculation such as good or bad layout is performed by software processing. Also good.
In addition, the display unit 15 functions as a notification unit that notifies the user of various types of information. For example, a liquid crystal display device or an organic EL display device is applied, and the display device built in the layout evaluation device 10 or this The display device is externally connected to the layout evaluation device 10.

Next, the operation of the layout evaluation apparatus 10 will be described. FIG. 10 is a flowchart showing the main operation.
When a group of images to be laid out is input to the layout target image input unit 11, the layout target image input unit 11 converts and outputs the binary image, and the layout evaluation unit 14 is stored in the storage unit 12. The binary image is provisionally arranged on the template to create a layout image (a layout image with a frame) including the layout frame W (step S1).
Next, the layout evaluation unit 14 calculates the induction field of the framed layout image by the visual induction field calculation unit 13 to obtain a potential line (step S2), and the scale parameter calculation unit 30 obtains the potential obtained. The complexity C is calculated for each potential value p of the line, a sigmoid function approximating the correspondence between the complexity C and the potential value p is calculated, and the “scale parameter T” of this sigmoid function is obtained ( Step S3).

Here, the specific processing (corresponding to the scale parameter acquisition processing) of steps S2 and S3 will be described with reference to the flowchart shown in FIG. First, the visual induction field calculation unit 13 calculates the induction field of the framed layout image (step S11), and the scale parameter calculation unit 30 calculates the complexity C for each equipotential surface of the calculated induction field. Perform the process.
Here, in the calculation definition formula of the induction field defined in the above formula (2), when the minimum pixel distance is 1, the field strength is in the range of 0 (zero) to 1. As the range of the potential value p for calculating the complexity C increases, the approximation accuracy of the later sigmoid function increases. From the viewpoint of shortening the calculation time,
It is preferable to keep the minimum range useful for layout evaluation.
Therefore, in the present embodiment, when calculating the complexity C, the potential value p is an appropriate range in a section of 0 (zero) or more and less than 1, for example, the minimum value p1 of the potential value p is set to 0.03.
And the amount of calculation is reduced by setting the resolution value Δp to 0.01 steps.

Specifically, the scale parameter calculation unit 30 first sets the potential value p to the minimum value p1 (
In step S12), an equipotential surface having this potential value p (= p1) is extracted (step S13), and the perimeter length Li and area Si of the closed surface having the equipotential value i (= p1) are obtained. The complexity Ci is calculated (step S14).
Subsequently, if the potential value p is less than the maximum value “1” (step S5: YES), the scale parameter calculation unit 30 adds the resolution value Δp to the potential value p (step S16).
By repeating the equipotential surface extraction process in step S3 and the calculation process of complexity C in step S14, the complexity in units of resolution Δp in the range of the potential value p from the minimum value p1 to the maximum value “1”. C is calculated. Note that the maximum value may be changed to a value equal to or less than the value “1” without being limited to the case where the complexity c is calculated up to the range of the maximum value “1”.

When the potential value p reaches the maximum value “1” (step S15: NO), the scale parameter calculation unit 30 obtains the plurality of complexity C obtained and the potential value p corresponding to each complexity C.
From these, the parameters (range a, offset value b, parameter p0, scale parameter T) for determining the sigmoid function shown in the equation (4) are determined using the least square method, and the sigmoid function is obtained (step S17). In the process of step S17, the error variance, that is, the approximate error is obtained by calculating the sum of squares of the error (residual) from the theoretical value.

In this case, if the approximation error is large, that is, the correlation of the function is very low and it is difficult to approximate with the sigmoid function, the layout is not readable.
Alternatively, it is considered that the image is deteriorated and cannot be used, or there is no content of the image data.
In such a case, it is preferable to notify the user of a warning by displaying on the display unit 15 that the layout is difficult.

When the scale parameter T is obtained in this way, as shown in FIG.
Determines whether the scale parameter T is within the preset optimum range (minimum value) (step S4).
). Here, as shown in FIG. 8, since the scale parameter T of the sigmoid function and “readability” have a strong negative correlation, this optimum range corresponds to “very easy to read”. The minimum range is set (for example, 0 <scale parameter T <0.05 in advance). For this reason, if the scale parameter T is within the preset minimum range, it can be determined that the layout is highly evaluated (“very easy to read”).

If it is determined in step S4 that the scale parameter T is not within the preset optimum range, it can be determined that the layout is difficult to read. That is, the layout is changed slightly from the initial state, such as margins and line spacing (step S6), and the process returns to step S2 and the same processing is performed.

By repeatedly performing such rearrangement processing, the above processing is repeated until the scale parameter T within the optimum range is obtained, that is, until the optimum layout is obtained.
Note that how to change the layout can be changed at random, but it is preferable to set in advance. In the case of setting in advance, for example, for the margin and line spacing, the template A change rule may be applied in which the margin and line spacing are changed as reference values, and the reference value is changed to a value that is gradually separated from the reference value. You may apply the prediction change rule which sets the content to change. In this prediction change rule, for example, when the margin is increased and the “scale parameter T” is decreased (when the layout has a higher evaluation than the previous one), the margin is further increased. On the other hand, if the layout is changed and the margin is increased and the “scale parameter T” is increased (when the layout becomes a lower evaluation than the previous one), the next method is to change the layout to a setting with a reduced margin. Conceivable.

When the scale parameter T within the optimum range is obtained, the layout evaluation unit 14 determines whether or not there is a defect in the layout (step S6). If there is a defect, the process proceeds to step S5. Similar processing is performed. In the defect determination in step S6, for example, it is determined whether or not a group of images to be laid out are not laid out and whether these images are within the layout frame W.
Subsequently, if it is determined in step S6 that there is no defect, the layout evaluation apparatus 10 can determine that the layout is a highly evaluated layout and that there is no defect, so that the layout image is displayed on the display unit 15. (Step S7), the user is notified of the optimum layout. The above is the operation of the layout evaluation apparatus 10.

As described above, according to the present embodiment, the induction field of the framed layout image is calculated,
Since the “scale parameter T” when the correspondence between the complexity of the equipotential value of the induction field and the potential value is approximated by a sigmoid function is calculated as a layout evaluation index, the margin Y between the layout frame W and the layout frame W is also calculated. Whether the layout is good or bad can be determined.
In this case, as shown in FIG. 8, since this “scale parameter T” is proportional to the layout evaluation, the quality of the layout is quantitatively determined by using this “scale parameter T” as a layout evaluation index. It is possible to evaluate.

Further, in the present embodiment, a layout image with a frame is created based on a template that defines a layout including the layout frame W and the layout is evaluated, so that the user does not need to set the layout frame W in advance. . In addition, when the layout to be evaluated is not good, the layout is changed and the layout is reevaluated, so that the optimum layout can be easily specified.

Second Embodiment
12, 13 and 14 show a second embodiment. As shown in FIG. 12, the layout evaluation apparatus 10 according to the second embodiment includes a complexity evaluation unit (complexity evaluation means) 40,
Based on the average value of complexity (complexity Cav) in the visual guidance field calculated from a group of layout target images (frameless layout image), the quality of the layout is determined, and the layout is determined to be highly evaluated. In this case, whether the layout of the framed layout image is good or bad is determined by the same processing as in the first embodiment with reference to the highly evaluated layout.
A technique for determining whether the layout is good or bad from the complexity Cav is disclosed in Japanese Patent Laid-Open No. 2003-306.
The technology of No. 73 is used. The inventor of the technique described in this publication is the inventor of the present invention. Hereinafter, about the same composition as the above-mentioned 1st embodiment, the same numerals are attached and the overlapping explanation is omitted.

13 and 14 are flowcharts showing the operation of the layout evaluation apparatus 10.
When a group of layout target images is input to the layout target image input unit 11, the layout target image input unit 11 converts the image into a binary image and outputs it, and the layout evaluation unit 14 determines the image in advance. Temporarily arrange on the template (step S21).

Next, the layout evaluation unit 14 calculates the induction field of the image by the visual induction field calculation unit 13 to obtain a potential line (step S22), and the scale parameter calculation unit 30 calculates the potential value p of the potential line. The complexity C is calculated every time, and the complexity Cav that is the average of the complexity C is obtained (step S23). That is, the visual guidance field calculator 13 also functions as an average complexity calculator that calculates the average complexity Cav.
Then, the layout evaluation unit 14 determines whether or not the complexity Cav is within the optimal range (minimum value) by the complexity evaluation unit 40 (step S24), and within the optimal range (minimum value). If it is determined that there is no layout, the layout is rearranged, that is, the layout is slightly changed from the initial state (step S25), and the process returns to step S22 to perform the same processing.

When the complexity Cav within the optimum range is obtained by repeating such a rearrangement process several times, the layout evaluation unit 14 determines whether or not there is a defect in the layout (as described above, overlapping) (Step S26), if there is a defect, the process proceeds to step S25 and the same process is performed. If there is no defect, the process proceeds to step S31.
That is, according to the processes in steps S21 to S26, the layout without a layout frame, that is, the layout without considering the margin between the layout frame W is judged to be good and bad, and the layout is re-layed until a highly evaluated frameless layout is obtained. A frameless layout evaluation process is performed in which evaluation is repeated.

Next, when a frameless layout that is highly evaluated and has no defects is obtained, the layout evaluation unit 14 temporarily arranges a group of images to be laid out on the template stored in the storage unit 12 with the layout. The layout image including the layout frame W (
A framed layout image) is created (step S31).
Subsequently, the layout evaluation unit 14 obtains a potential line by calculating the induction field of the image by the visual induction field calculation unit 13 (step S32), and the scale parameter calculation unit 30 calculates the potential value p of the potential line. The complexity C is calculated every time, a sigmoid function approximating the correspondence between the complexity C and the potential value p is calculated, and the “scale parameter T” of the simid function is obtained (step S33).

Then, the layout evaluation unit 14 determines that the scale parameter T is within the preset optimum range (minimum value).
(Step S34), and if it is determined that it is not within the optimum range (minimum value), rearrangement, that is, a layout that is slightly changed from the initial state (step S35),
Returning to step S32, the same processing is performed.
When the scale parameter T within the optimum range is obtained by repeating such rearrangement processing several times, the layout evaluation unit 14 determines whether or not the layout has a defect (step S36). If there is a problem, the process returns to step S35 to perform the same process. If there is no problem, it is displayed (step S37), and the optimal layout is notified to the user. The above is the operation of the layout evaluation apparatus 10 according to the second embodiment.

As described above, in this embodiment, whether or not a layout (frameless layout) that does not consider the margin Y with respect to the layout frame W is determined as good or bad, and a highly evaluated frameless layout is obtained, the layout frame is determined by that layout. Since it is determined whether the layout with a margin Y with respect to W (a layout with a frame) is good or bad and a highly evaluated layout with a frame is obtained, a process for obtaining a previous frame-less layout (frameless layout evaluation process) is performed. Therefore, it is possible to determine whether the layout is good or bad by a combination excluding an inappropriate layout (a low evaluation layout).
As described above, since the processing of this latter stage increases calculation such as approximation by the sigmoid function, the number of times of this processing (the number of scale parameter calculation processes including the calculation of the sigmoid function) can be reduced. It is possible to reduce the amount of processing until the optimum layout is obtained and shorten the processing time.

In this embodiment, the case where the average complexity Cav is calculated from the frameless layout image to narrow down the layout has been described. However, the present invention is not limited to this, and the complexity Cav is calculated from the layout image including the layout frame W. Then you can narrow down the layout. in this case,
By narrowing down the layout to the area before the area “Area” shown in FIG. 16, the optimum case cannot be determined, but at least an inappropriate layout can be roughly specified. After an inappropriate layout is identified in this way, an optimum layout is obtained while reducing the scale parameter calculation process by performing layout evaluation using the scale parameter T described above with a combination excluding this layout. It becomes possible.

In addition, this invention is not limited to the above-mentioned embodiment, The deformation | transformation in the range which can achieve the objective of this invention, improvement, etc. are included in this invention. For example, in each of the above-described embodiments, the present invention is applied to the case of evaluating a binary image layout. However, the present invention is not limited to this, and is applicable to the case of evaluating a multi-value image layout.

Hereinafter, the case where the layout of a multi-valued image is evaluated will be described. In general, many digital devices adopt R (red), G (green), and B (blue) as basic colors, and the color is expressed by a combination of RGB. Note that each of RGB changes from 0 to 255, and a color is expressed by a combination thereof. By the way, black is R
= G = B = 255, white is a combination of R = G = B = 0, and a combination of R = G = B having an intermediate value thereof is an achromatic color (gray). In this way, not only colors but also gradations can be expressed by RGB.
In this case, the calculation is performed as follows by applying the technique of Japanese Patent Application Laid-Open No. 2004-171115 (hereinafter referred to as a reference technical document). More specifically, in FIG. 1, each point p1, p2,
.., Pi,..., Pn are affected by the gradations of R, G, B (for example, 0 to 255). Mp is defined as in equation (5).

Here, Qi (R, G, B) is an independent function (Qi (R), Qi (G
), Qi (B)), and in the case of a binary image, Qi (R = 0, G = 0, B = 0)
= 1, and in the case of a multi-valued image, Qi (R, G, B) is larger than 1 (Qi> 1). These Qi (R), Qi (G), and Qi (B) are curves that draw a substantially S-shaped curve that saturates when the gradation (density) reaches a certain value according to the above-mentioned reference technical literature. It is also known that R (red) is the most sensitive to changes in gradation (density), followed by B (blue) and G (green).
This is consistent with the fact that, for example, when a warning sign is displayed on a traffic sign or the like, colors are used in the order of red and blue, and green is often not used. The magnitude of such a degree of attention is considered to be the strength and energy of the induction field. On the basis of this, the difference in change due to the color of Qi is consistent with the traffic sign example described above. . Therefore, the function for obtaining Qi used in this equation (5) can be determined by psychological experiments or the like.

Therefore, the induced field of the multi-valued image can be calculated by using Expression (5). And if this induction field is decided, the complexity C is calculated by the process similar to the above-mentioned embodiment,
The correspondence relationship between the obtained plurality of complexity C and the potential value p can be approximated by a sigmoid function, and a “scale parameter T” of the sigmoid function can be obtained.
In this way, when evaluating the layout of a multi-valued image, it is not necessary to convert from a multi-valued image to a binary image, so that the determination accuracy can be improved as there is no information loss during such conversion.

However, when evaluating the layout of a multi-valued image, the calculation amount increases and the calculation time becomes longer. For this reason, if priority is given to the determination speed, the layout is evaluated by converting to a binary image, and if priority is given to determination accuracy, which method should be used, such as evaluating the layout as a multi-valued image? May be selectable.
In each of the above-described embodiments, each coefficient and parameter (a, b, P0) of the sigmoid function
, T) has been described as being calculated, but the present invention is not limited to this, and only the scale parameter T may be directly calculated. In this case, calculation of coefficients and parameters other than the scale parameter T can be omitted.
The amount of calculation can be reduced.

In addition, the present invention creates a control program in which the processing procedure for carrying out the present invention described above is described, and makes this control program downloadable via a telecommunication line, The present invention can also be implemented in such a manner that the program is stored and distributed in a computer-readable recording medium such as a recording medium, an optical recording medium, or a semiconductor recording medium.
Note that the layout evaluation apparatus 10 according to the present embodiment includes a camera, a scanner, a projector,
It is also possible to implement in a form provided in all electronic devices such as a television and a printer. For example, a camera or scanner provided with the above-described layout evaluation apparatus 10 can acquire a group of images to be laid out by photographing or reading data, and can display and output the optimum layout of the image. In addition, a printer including the above-described layout evaluation apparatus 10 can input a group of images to be laid out from an external device connected to the printer, and print the image with an optimal layout. In addition, a television provided with the layout evaluation apparatus 10 described above can receive a group of images to be laid out and display them in an optimal layout.

It is a figure which shows the pixel arrangement | sequence of the digital image for demonstrating the visual induction field. It is a figure explaining the shielding conditions at the time of calculating | requiring the intensity | strength of a visual induction field. (A) is a figure which shows the case where the visual guidance field of character "A" is calculated | required in consideration of shielding conditions, (B) is the figure which shows the case where the visual guidance field is calculated | required without considering shielding conditions. It is. It is a figure which shows an example of a layout image with a frame. It is a figure which shows an example of a sigmoid function. It is a figure which shows the result of having evaluated the several layout image with a frame by psychological experiment. It is a figure which shows the correspondence of the complexity C of the induction field distribution of the image of FIG. 6, and the potential value p. It is a figure which shows the correspondence of "the scale parameter of a sigmoid function" and "readability". It is a block diagram which shows the function structure of a layout evaluation apparatus. It is a flowchart which shows the main operation | movement of a layout evaluation apparatus. It is a flowchart which shows a scale parameter acquisition process. It is a block diagram which shows the function structure of the layout evaluation apparatus which concerns on 2nd Embodiment. It is a flowchart which shows the main operation | movement of a layout evaluation apparatus. 14 is a flowchart continued from FIG. 13. (A) is a figure which shows the example of a document image without a layout frame, (B) is a figure which shows the example of a document image with a layout frame. It is a figure which shows the correspondence of "complexity Cav calculated including a layout frame" and "readability".

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Layout evaluation apparatus, 11 ... Layout object image input part (image input means), 12
... storage unit (storage unit), 13 ... visual guidance field calculation unit (guidance field calculation unit, average complexity calculation unit), 14 ... layout evaluation unit (evaluation unit), 15 ... display unit (notification unit), 20 ... Layout changing unit (layout changing unit), 30 ... scale parameter calculating unit (complexity calculating unit, evaluation index calculating unit), 40 ... complexity evaluating unit (complexity evaluating unit), C ... complexity, Cav ... average Complexity, T ... scale parameter, W ... layout frame.

Claims (8)

A layout evaluation apparatus for evaluating a layout of a layout image with a frame in which a group of images are laid out in a layout frame,
A `` field '' existing around the grouped image and the image representing the layout frame with respect to the framed layout image, and the strength of the `` field '' depends on the distance from the image,
A guidance field calculation means for calculating a visual guidance field having a larger value as it is closer to the image;
Complexity calculating means for calculating the complexity of a closed curved surface of lines connecting equipotential values in the visual induction field;
An evaluation index calculating means for calculating a scale parameter of a sigmoid function when the correspondence between the complexity and the equipotential value is approximated by a sigmoid function;
An evaluation means for evaluating a layout based on the scale parameter;
A layout evaluation apparatus comprising: The layout evaluation apparatus according to claim 1,
The sigmoid function has complexity C, potential value p, scale parameter T, range a
When the offset value is b and the parameter is p0,

A layout evaluation apparatus defined by In the layout evaluation apparatus according to claim 1 or 2,
A layout evaluation device comprising: a layout changing unit that changes the framed layout image to be evaluated to a framed layout image of a different layout when the scale parameter is not within a predetermined range. In the layout evaluation apparatus according to any one of claims 1 to 3,
The group of images includes either characters or figures,
Storage means for storing a template that defines at least one of the layout frame, a margin between the layout frame and a line;
The guidance field calculation means calculates the visual guidance field for the framed layout image, wherein the group of images are laid out in the layout frame based on the template. apparatus. In the layout evaluation apparatus according to any one of claims 1 to 4,
Average complexity calculation means for calculating an average value of the complexity,
A complexity evaluation means for evaluating a layout based on the average value of the complexity,
A layout evaluation apparatus for calculating the visual induction field for the framed layout image evaluated as high by the complexity evaluation means. An electronic apparatus comprising the layout evaluation device according to claim 1. A layout evaluation method for evaluating a layout of a layout image with a frame in which a group of images are laid out in a layout frame,
A `` field '' existing around the grouped image and the image representing the layout frame with respect to the framed layout image, and the strength of the `` field '' depends on the distance from the image,
A guidance field calculation step for calculating a visual guidance field having a larger value as it is closer to the image;
A complexity calculation step for calculating the complexity of a closed curved surface of lines connecting equipotential values in the visual induction field;
An evaluation index calculation step for calculating a scale parameter of the sigmoid function when the correspondence between the complexity and the equipotential value is approximated by a sigmoid function;
An evaluation step of evaluating a layout based on the scale parameter;
A layout evaluation method comprising: A layout evaluation program for evaluating a layout of a layout image with a frame in which a group of images are laid out in a layout frame,
Computer
A `` field '' existing around the grouped image and the image representing the layout frame with respect to the framed layout image, and the strength of the `` field '' depends on the distance from the image,
A guidance field calculation means for calculating a visual guidance field having a larger value as it is closer to the image,
Complexity calculating means for calculating the complexity of a closed curved surface of lines connecting equipotential values in the visual induction field;
An evaluation index calculating means for calculating a scale parameter of a sigmoid function when the correspondence between the complexity and the equipotential value is approximated by a sigmoid function;
An evaluation means for evaluating a layout based on the scale parameter;
Layout evaluation program to function as

Images