CN1202471C - Book production system and method - Google Patents

Abstract

The invention provides a book making system, which is used for generating a book comprising a character part and an illustration part and comprises a video receiving module, a decoding module, a character capturing module, an illustration capturing module and a book generating module. In the invention, a video receiving module receives an original video material; the decoding module decodes the original video data into a video data; the character acquisition module acquires a character part from the video data according to a manufacturing policy; the image-inserting capturing module captures at least one key frame from the video data as an image-inserting part according to the production policy; the book generation module typesets the acquired text part and the illustration part to generate a book. The invention also discloses a book making method implemented according to the system.

Description

Book production system and method

technical field

The present invention relates to a book making system and method, in particular to a book making system and method which utilizes a computer software to analyze a video source (Video) to automatically generate book files such as picture books, albums, comics, and electronic books.

Background technique

According to the current technology, when making picture books, picture albums, comics, e-books and other books, the source of the content is usually still using manual drawing, or editing and sorting out single images by computers so as to compile them into books.

However, with the increasing popularization of electronic information products such as digital cameras, TV Tuner Cards, set-top boxes (SetupBox), DVDs, and VCDs, users can easily obtain digital videos. Therefore, using computers to process video sources to Generating book files has become an important application and demand in the field of computer multimedia.

As mentioned above, when the obtained image data is not a single image but a video source of continuous images, the user must decompose the video source of continuous images into multiple images, and then the images can be edited and compiled into a book by the computer. However, for general video content (Video Content), in the NTSC standard, it may be a continuous switch that contains 29.97 images for one second, while in the PAL standard, it may contain 25 images for one second. Continuous switching of images, therefore, a minute-long video content has 1500-1800 images, if the user edits each image one by one, it will be a very time-consuming and inefficient thing.

Therefore, how to effectively use video content to generate book files such as picture books, albums, comics, and e-books is an important topic at present.

Contents of the invention

In order to overcome the deficiencies of the prior art, the object of the present invention is to provide a book making system and method, which can automatically analyze a video source to generate picture books, albums, comics, e-books and other book files.

To achieve the above object, the book production system of the present invention is used to generate a book including a text part and an illustration part, and includes a video receiving module, a decoding module, a text extraction module, an illustration extraction module and a book Generate modules. In the present invention, the video receiving module receives an original video data, and the decoding module decodes the original video data to obtain a video data, and the original video data can be in any video format, and the text extraction module obtains a video data from the video data according to a production policy. The text part is obtained in the image, the illustration extraction module extracts at least one key frame from the video data as the illustration part according to the production policy, and then the book generation module generates a book according to the obtained text part and illustration part.

In addition, the book production system according to the present invention further includes an editing module, a book format (template) selection module, and a production policy selection module. In the present invention, the production policy selection module accepts a user to select a required production policy, the editing module receives the user's operation to edit the content of the book, and the book format selection module receives at least one book format required by the user's selection , and the book generating module applies the selected book format to typeset the text part and the illustration part to generate a book.

As mentioned above, the production policy that can be selected by the production policy selection module includes an audio (audio) analysis algorithm, a caption (caption) analysis algorithm, a scene/shot change analysis algorithm and an image analysis algorithm, wherein, The audio analysis algorithm is an algorithm for analyzing the audio data of the video data; the subtitle analysis algorithm is an algorithm for analyzing the subtitle data of the video data; Algorithm for lens transformation data; image analysis algorithm is an algorithm for analyzing image data of video data, and it can compare and analyze image data with a pre-provided image sample data, or compare image data with pre-provided An object data is provided for comparative analysis, or a subtitle image data in the image data is analyzed.

Therefore, the text extraction module and the illustration extraction module can obtain the text and illustrations required for making a book according to the above-mentioned audio analysis algorithm, subtitle analysis algorithm, scene/camera transition analysis algorithm, or image analysis algorithm. Then, the book generation module inserts the above-mentioned text part and illustration part into the book format, so that book files such as picture books, picture albums, comics, and e-books are automatically generated.

The present invention also provides a book production method, which includes a video receiving step, a decoding step, a text extraction step, an illustration extraction step and a book generation step. In the present invention, the video receiving step first receives the original video data, and then the decoding step decodes the original video data to obtain the video data, and then the text extraction step and the illustration extraction step respectively extract the text part required for making a book from the video data and the illustration part, and finally the book generation step generates the book according to the text part and the illustration part.

In addition, the book production method according to the present invention also includes an editing step to edit the content of the book after the book is generated, a book format selection step so that the user can select the required book format, and then let the book generation step apply the book format to generate Books, and a production policy selection module so that users can select the required production policy.

The advantage of the present invention is: because the book production system and method of the present invention can automatically analyze a video source, cooperate with multiple video formats, and integrate technologies such as video content analysis, character recognition, and sound recognition, to produce picture books, picture books, comics, etc. , e-books and other book files, so the video content can be efficiently used to generate book files.

Description of drawings

Below in conjunction with accompanying drawing and embodiment the present invention is described in detail:

Fig. 1 is a schematic diagram showing the structure of a book making system according to a preferred embodiment of the present invention;

Fig. 2 is a flow chart, shows the flow process of the book production method according to the preferred embodiment of the present invention;

FIG. 3 is a schematic diagram showing a schematic diagram of capturing key frames in the book production method according to a preferred embodiment of the present invention.

Explanation of symbols in the figure:

1 Book production system

101 Video receiving module

102 decoding module

103 Make policy selection module

104 text extraction module

105 illustration capture module

106 Book format selection module

107 Book generation module

108 Edit module

2 book making method

201-209 The streaming audio data of the book production method according to the preferred embodiment of the present invention

301 single image

302 key screen

40 Original video material

41 Video material

411 audio data

412 subtitle data

413 Video data

50 production policy

501 Audio Analysis Algorithms

502 subtitle analysis algorithm

503 Image Analysis Algorithms

5031 Image sample data

5032 object data

504 Scene/Shot Change Analysis Algorithm

60 computer equipment

601 Signal source interface

602 memory

603 central processing unit

604 Input device

605 storage device

70 Book Formats

80 books

801 text part

802 Illustration section

Detailed ways

The book production system and method of the preferred embodiments of the present invention will be described below with reference to related drawings, wherein the same components will be described with the same reference symbols.

Please refer to Fig. 1, the book making system 1 of the preferred embodiment of the present invention is used to produce a book 80 including a text part 801 and an illustration part 802, and includes a video receiving module 101, a decoding module 102, a A production policy selection module 103 , a text extraction module 104 , an illustration extraction module 105 , a book format selection module 106 , a book generation module 107 and an editing module 108 .

In this embodiment, the book making system 1 can be applied in a computer device 60, and the computer device 60 can be an existing computer device, which includes a signal source interface 601, a memory 602, a central processing unit (CPU) 603 , an input device 604 and a storage device 605 . Wherein, the signal source interface 601 is connected with a signal source output device or a signal source recording device, such as optical drive, FireWire (IEEE 1394 Interface), universal serial port (USB) and other interface devices, and the signal source output device is, for example, For digital video cameras, the signal source recording device is, for example, VCD, DVD, etc. The memory 602 can be any one or more kinds of temporary memory provided in the computer device, such as DRAM or EEPROM. The central processing unit 603 can adopt any existing central processing unit architecture, for example, including ALU, registers and controllers, etc., to process and calculate various data, and to control the operation of various components in the computer device 60. move. The input device 604 can be a mouse, a keyboard, etc., which can be used by the user to input information or operate various software modules. The storage device 605 may be any one or more computer-readable data storage devices such as a hard disk drive and a floppy disk drive.

Each module in this embodiment refers to a software module stored in the storage device 605 or a recording medium. After the central processing unit 603 reads each module, it can realize the functions of each module through each component in the computer device 60 . However, it should be noted that those skilled in the art can also make the software modules disclosed in this embodiment into hardware, such as application-specific integrated circuit (ASIC) chips, without violating the spirit and spirit of the present invention. category.

The functions of each module in this embodiment will be described in detail below.

In this embodiment, the video receiving module 101 receives an original video data 40, the decoding module 102 decodes the original video data 40 to obtain a video data 41, and the production policy selection module 103 accepts a user's operation to select a desired video data. The production policy 50, the text extraction module 104 obtains the text part 801 from the video data 41 according to the production policy 50, and the illustration extraction module 105 extracts at least one key frame from the video data 41 according to the production policy 50 as an illustration part 802, and the book format selection module 106 receives the user's selection to provide at least one book format 70, the book generation module 107 applies the book format 70, and generates the book 80 according to the obtained text part 801 and illustration part 802, and finally, the editing module 108 Accept user operations to edit the content of the book 80 after the book 80 is generated.

As mentioned above, the video receiving module 101 cooperates with the signal source interface 601, for example, the video receiving module 101 can obtain the original video data 40 stored in the digital camera through FireWire (IEEE 1394 Interface), or obtain and record in VCD, Original video material on DVD 40. The original video data 40 is a video source stored, transmitted, broadcasted or received by various video capture devices or receiving devices such as digital cameras, TV cards, set-top boxes, etc., and various video storage devices such as DVD and VCD , and it can store, transmit, broadcast or receive in various video data formats (such as MPEG-1, MPEG-2, MPEG-4, AVI, ASF, MOV, etc.).

The decoding module 102 can decode and convert the video format, encoding method, or compression method of the input original video material 40 into the data before encoding or approximate the data before encoding, for example, if the encoding method adopts a distortion compression method (Lossy Compression ), then only the data similar to that before encoding can be obtained after decoding, so as to generate a video data 41 . In this embodiment, the video data 41 includes an audio data 411 , a subtitle data 412 and an image data 413 . The audio data 411 is the sound played in the video data 41; the subtitle data 412 is a subtitle stream (caption stream) that appears on the screen in conjunction with the video data 413; the video data 413 is all single images displayed by the video data 41, Usually the video data 41 per second is composed of 25 single images or 29.97 single images played continuously.

The production policy selection module 103 cooperates with the input device 604 so that the user can use the input device 604 to select the policy that must be followed when making the book 80, and the production policy 50 provided in this embodiment includes an audio analysis algorithm 501, a A subtitle analysis algorithm 502 , an image analysis algorithm 503 , and a scene/shot change analysis algorithm 504 .

Continuing from the above, the audio analysis algorithm 501 analyzes the audio data 411 of the video data 41, and uses features extraction (Features Extraction) and feature matching (Features Matching) methods for analysis. The features of the audio data 411 include such as Spectral Features, Volume, Zero Crossing Rate, Pitch and so on. As mentioned above, after extracting the spectral features (Spectral Features), it passes through Noise Reduction (NoiseReduction), segmentation (Segmentation), and uses Fast Fourier Transform (Fast FourierTransform) to transfer the audio data 411 to the frequency domain (Frequency), and then The eigenvalues are extracted by a set of frequency filters (Filters), and this set of eigenvalues forms a spectral feature vector (Spectral Feature Vector). Volume is a feature that is easy to measure. It can use root mean square (RMS, Root Mean Square) to represent its characteristic value, and then through volume (Volume) analysis can assist segmentation (Segmentation), that is, through mute Detection (SilenceDetection) helps audio material 411 to determine paragraph boundaries (Boundaries). Zero Crossing Rate (Zero Crossing Rate) is to calculate the number of intersections between each Clips sound waveform (Waveform) and Zero Axis (Zero Axis). The pitch (Pitch) is the fundamental frequency (Fundamental Frequency) of the sound waveform (Waveform). Therefore, the audio data 411 can use the feature vector (Feature Vector) formed by the above audio features and their eigenvalues to analyze and compare the features of the audio samples (Audiotemplates) in order to obtain the required audio data 411, and through speech recognition The technology obtains the text part 801 and obtains the video data 413 corresponding to the required audio data 411 in the video data 41 as the illustration part 802 . In this embodiment, the audio analysis algorithm 501 can provide audio sample categories in advance, such as music (Music), speech (Speech), animal sound (Animal Sound), male voice (Male Speech) and female voice (FemaleSpeech), etc., for The user selects the audio category to be searched. Therefore, feature matching is convenient for finding the audio sample category with the shortest geometric distance (Euclidean Distance) to the feature vector (Feature Vector) of the audio data 411 within the allowable distance range, if this is the closest If the category of the audio sample is the same as the audio category selected by the user, the audio data 411 meets the search criteria. In addition, the inverse of the shortest geometric distance can be used to represent the confidence of the selected audio data 411 (Confidence) , find the corresponding video clips from the audio data 411 conforming to the audio sample category, and select an image that meets the drawing requirements from each shot of these video clips as the illustration part 802 . In addition, if the video material 41 includes a subtitle stream (Caption Stream), then interpret the subtitle stream in the video material 41 corresponding to the selected audio material 411 as the text part 801 of the book 80; if the video material 41 does not include For the subtitle stream, interpret the audio data 411 in the selected audio data 411 and use speech analysis (Speech Analysis) to convert voice and text (Voice to Text) to serve as the text part 801 of the book 80. In addition, the computational complexity of the audio analysis algorithm 501 is lower than that of video or visual (Visual) analysis, and can be used as guidance and auxiliary data for video or visual (Visual) analysis.

In addition, the subtitle analysis algorithm 502 is to analyze the subtitle material 412 in the video material 41 and screen the video frames with subtitles. In other words, if the video material 41 includes a subtitle stream, then interpret the subtitle stream as the text part 801, and find the first video frame corresponding to the subtitle and time-synchronized as the illustration part 802; if the video material 41 does not include the subtitle stream, If the subtitles are included in the video image, the text recognition technology is used to extract the subtitle (Caption) from the video image as a text part 801, and perform image processing on the filtered video image to remove the subtitle (can be performed by the data of the front and back video images) operation processing) to obtain the video image without subtitles as the illustration part 802 . As mentioned above, the text recognition technology mainly uses optical character recognition technology (OCR, Optical Character Recognition) for text recognition.

The image analysis algorithm 503 analyzes an image data 413 in the video data 41 , and uses basic visual features such as color, texture, shape, movement, and position as the basis for analysis and judgment. In this embodiment, when the subtitles are included in the video image, the text recognition technology is used to extract the subtitles from the video image as the text part 801; in addition, the video data 41 is compared with an image sample data 5031, so as to find the video visual A picture with a large feature similarity, or look for a picture with a large dissimilarity in the visual features of the image as the illustration part 802, or compare the video data 41 with an object data 5032, for example, use face detection (Face Detection) technology to find A video frame with a human face in the video material 41 is used as the illustration part 802 . In this embodiment, when selecting a picture with a large visual feature similarity with the image sample data 5031 or object data 5032, or a video picture with a large dissimilarity in the visual feature of the video, as the video data 41 that meets the screening criteria , the same shot can be set to filter only one frame as the illustration part 802 .

The scene/shot change analysis algorithm 504 is to analyze the scene/shot change of the image data 413 in the video material 41, and filter the first qualified picture after the scene/shot change of the image data 413 in the video material 41, as the book 80 The illustration part 802 of and the segmentation point of the paragraph of the video material 41. That is, if the video data 41 includes a subtitle stream, then interpret the subtitle data 412 in the paragraph of the video data 41 as the text portion 801 of the book 80; if the video data 41 does not include a subtitle stream, then interpret the paragraph of the video data 41 The audio data 411 of the book 80 is used as the text part 801 of the book 80 by voice analysis. Generally speaking, the video data 41 is a video sequence (VideoSequence), which is usually composed of many scenes (Scenes), and each scene is composed of multiple shots (Shots). In a movie, the smallest unit is a shot, and the movie is made up of many shots; in a script, the smallest unit is a scene, or a scene, and a scene represents a paragraph of each story or theme , each scene has a definite starting point of event occurrence and a definite ending point, and in such a period of time it is called a scene, or a play. Usually, a shot is composed of multiple frames (Frames) with consistent visual characteristics (such as Color, Texture, Shape, and Motion), and it is based on the direction of camera movement ( Camera Direction) and the camera view angle (View Angle) change, for example, when the camera shoots the same scene with different camera view angles, different shots will be produced, or the same camera view angle but different shooting Different shots are also generated when the area is selected. Since the shots can be distinguished by some basic visual characteristics, it is quite easy to divide the video data 41 into a plurality of continuous shots. This technology mainly consists of analyzing some basic visual characteristic statistical data such as visual characteristic histogram (Histogram), so , when the visual characteristics of a frame differ from those of the previous frame to a certain extent, a split can be made between the frame and the previous frame. This mirroring technique is also widely used in video editing software. As mentioned above, the purpose of scene change analysis is to gather consecutive relevant shots into one scene. Strictly speaking, it must understand the semantic meaning and content of the video data 41, but the analysis combined with audio and visual characteristics can also be reasonably reasonable. Scene change analysis, usually scene changes will produce changes in the nature of audio characteristics (such as music, voice, noise (Noise), silence (Silence)) and visual characteristics (such as color, motion), and the segmentation of the shot is only for visual characteristics For analysis, scene change analysis must rely on the analysis of audio characteristics and visual characteristics at the same time.

The text extraction module 104 and the illustration extraction module 105 can be a software module stored in the storage device 605, and through the operation of the central processing unit 603, the required text part 801 and illustration part 802 are extracted according to the production policy 50, so as to As the contents of the production book 80 .

The book formats 70 provided by the book format selection module 106 such as picture books, picture albums, e-books, comics, etc., and can cooperate with different filters (Filters) such as Artistic Filters (ArtisticFilters), Sketch Filters (Sketch Filters), edge lines Filters (Edge Filters) are used to apply the obtained illustration part 802 to obtain the image processing effects (Effects) desired by the user, and the book format 70 and various filters are stored in the storage device 605 .

The book generation module 107 can be a software module stored in the storage device 605, and through the calculation of the central processing unit 603, so as to apply the book format 70, and use such as resizing (Rescaling), image synthesis (Image Composing), making frame and other image processing (Image processing) functions to process the obtained text part 801 and illustration part 802, so as to produce a book 80 in accordance with the book format 70, font and size selected by the user.

Finally, the editing module 108 can cooperate with the input device 604 so that the user can further edit the content of the book 80 by using the operation of the input device 604 after the book 80 is generated.

In order to make the content of the present invention easier to understand, an example will be given below to illustrate the flow of the book production method according to the preferred embodiment of the present invention.

Please refer to Fig. 2, in the book making method 2 according to the preferred embodiment of the present invention, step 201 is to receive the original video data 40, for example, the data recorded in the digital camera can be sent to the signal source interface 601 via the transmission line, To provide images and contents for making a book 80 .

In step 202, the decoding module 102 identifies the format of the original video data 40 and decodes the original video data 40 to generate the decoded video data 41. For example, the original video data 40 is in Interlaced MPEG-2 format, that is, a message The frame is composed of two fields. Therefore, in this step, MPEG-2 format decoding can be performed first, and then the interpolation method (Interpolation) can be used to deinterlace to obtain the video data 41 .

In step 203, the text extraction module 104 and the illustration extraction module 105 analyze the video data 41 according to the production policy 50 to obtain the text part 801 and the illustration part 802, which can be based on the audio analysis algorithm 501, the subtitle analysis algorithm 502, The image analysis algorithm 503 and the scene/shot change analysis algorithm 504 analyze, search and filter each video frame and content (including audio content) of the video data 41 to obtain the text part 801 and the illustration part 802 that meet the production policy 50 For example, if the video material 41 includes a subtitle stream, then interpret the subtitle stream of the video material 41 as the text part 801; The text conversion process is used as the text part 801, and the key frame is captured in the video corresponding to the subtitle stream or audio as the illustration part 802. It should be noted that in this embodiment, multiple key frames can be captured as the illustration part 802. As shown in Figure 3, after the original video data 40 is decoded, the video data 41 will be obtained, which includes a plurality of single images 301 (25 or 29.97 per second), and after analyzing and searching according to the production policy 50, it will be obtained from the The key frame 302 is extracted from a single image as the illustration part 802 .

Step 204 is to judge whether the analysis and comparison of all content in the video material 41 has been completed, and when the analysis and comparison of all content in the video material 41 has not been completed, step 203 is repeated; when the analysis and comparison of all content in the video material 41 is completed , go to step 205.

Step 205 is to judge whether the book format 70 needs to be applied to the book 80, and if the book 80 needs to apply the book format 70, proceed to step 206;

In step 206, the book format selection module 106 provides the user with the required book format 70 to select. The book format 70 includes various book templates with pictures, images, photos, paintings or drawings, such as comics, picture books, picture books, E-books, etc., and various layouts (Layout).

In step 207, the book generation module 107 is based on the text part 801 and illustration part 802 obtained in step 203, and when step 206 is performed, the book format 70 provided in step 206 is applied, and different filters are used , such as artist filter, sketch filter, edge filter, etc., to process the illustration part 802 to obtain the desired image processing effect, and then use image processing functions such as resizing, image synthesis, and frame making to obtain The image screen in the format 70, and then convert the text part 801 and the illustration part 802 according to the book format 70 and the font and size to generate the book 80.

Step 208 is to determine whether the user manually edits the book 80 , and if the user wants to manually edit the book 80 , proceed to step 209 .

In step 209 , the user utilizes the editing module 108 to preview, modify (Refine), modify (Modify) the content of the book 80 . For example, the user can add an underline to the text part of the important content of the book 80, or make the text bold; or the user can insert a pattern and the like.

To sum up, since the book production system and method of the preferred embodiment of the present invention can analyze the video data 41, to integrate video content analysis and text recognition for the audio data 411, subtitle data 412 and image data 413 of the video data 41 , voice recognition and other technologies, so it can efficiently use video data to generate book files.

The above description is for illustration only, not for limitation. Any equivalent modification or change without departing from the spirit and scope of the present invention shall be included in the protection scope of this patent.

Claims (20)

1, a kind of book makign system, it is to be used for producing books, and these books comprise a word segment and an illustration part, and this book makign system comprises:

One video reception module, it receives a former video data;

One decoder module, its this former video data of decoding is to obtain a video data, and wherein this video data comprises at least one image data, and an audio data or a captions data;

One literal acquisition module, it is made policy according to one and obtain this word segment in this video data;

One illustration acquisition module, it is made policy according to this and captures a key picture with as this illustration part in this video data; And

One books generation module, it partly produces these books according to obtained this word segment and this illustration;

Wherein this making policy comprises by at least one calculation rule in the group that audio analysis calculation rule, captions analysis calculation rule, image analysing computer calculation rule and one scene/shot transition analysis calculation rule is formed.

2, according to the described book makign system of claim 1, it is characterized in that: also comprise:

One editor module, it is after these books produce, and the operation that receives a user is to edit the content of these books.

3, according to the described book makign system of claim 1, it is characterized in that: also comprise:

One figure book format is selected module, and its selection that receives a user to be providing at least one figure book format, and this books generation module is applied mechanically this figure book format and produced this books.

4, according to the described book makign system of claim 1, it is characterized in that: also comprise:

One makes policy selects module, and its selection of accepting a user is to provide this making policy.

5, according to the described book makign system of claim 1, it is characterized in that: this audio analysis algorithm is analyzed this audio data in this video data, this literal acquisition module captures this audio data obtaining this word segment according to this audio analysis algorithm, and this illustration acquisition module acquisition and corresponding this image data of this audio data are with as this illustration part.

6, according to the described book makign system of claim 1, it is characterized in that: this captions analytical algorithm is then analyzed this captions data in this video data, this literal acquisition module then captures this captions data obtaining this word segment according to this captions analytical algorithm, and this illustration acquisition module acquisition and corresponding this image data of this captions data are with as this illustration part.

7, according to the described book makign system of claim 1, it is characterized in that: this image analysing computer algorithm is according to this image data in this video data of image case study, this illustration acquisition module captures this image data obtaining this illustration part according to this image analysing computer algorithm, and this literal acquisition module from corresponding this video data of this image data obtain this word segment.

8, according to the described book makign system of claim 1, it is characterized in that: this image analysing computer algorithm foundation one object is analyzed this image data in this video data, this illustration acquisition module captures this image data obtaining this illustration part according to this image analysing computer algorithm, and this literal acquisition module from corresponding this video data of this image data obtain this word segment.

9, according to the described book makign system of claim 1, it is characterized in that: this image analysing computer algorithm is analyzed this image data in this video data, this literal acquisition module captures captions in this image data with as this word segment, and this illustration acquisition module captures this image data with as this illustration part.

10, according to the described book makign system of claim 1, it is characterized in that: this scene/shot transition analytical algorithm is then analyzed the scene/shot transition of this image data in this video data, this literal acquisition module and this illustration acquisition module with this scene/shot transition analytical algorithm then as the selection of this word segment and this illustration part and the foundation of segmentation.

11, a kind of books method for making, it is used for producing books, and these books comprise a word segment and an illustration part, and this books method for making comprises:

One video reception step, it receives a former video data;

One decoding step, its this former video data of decoding is to obtain a video data, and wherein this video data comprises at least one image data, and an audio data or a captions data;

One literal acquisition step, it is made policy according to one and obtain this word segment in this video data;

One illustration acquisition step, it is made policy according to this and captures a key picture with as this illustration part in this video data; And

One books produce step, and it partly produces these books according to obtained this word segment and this illustration;

Wherein this making policy comprises by at least one calculation rule in the group that audio analysis calculation rule, captions analysis calculation rule, image analysing computer calculation rule and one scene/shot transition analysis calculation rule is formed.

12, according to the described books method for making of claim 11, it is characterized in that: also comprise:

One edit step, it is after these books produce, and the operation that receives a user is to edit the content of these books.

13, according to the described books method for making of claim 11, it is characterized in that: also comprise:

One figure book format is selected step, and its selection that receives a user to be providing at least one figure book format, and these books produce step and apply mechanically this figure book format and produce this books.

14, according to the described books method for making of claim 11, it is characterized in that: also comprise:

One makes policy selects step, and its selection of accepting a user is to provide this making policy.

15, according to the described books method for making of claim 11, it is characterized in that: this audio analysis algorithm is analyzed this audio data in this video data, this literal acquisition step captures this audio data obtaining this word segment according to this audio analysis algorithm, and this illustration acquisition step acquisition and corresponding this image data of this audio data are with as this illustration part.

16, according to the described books method for making of claim 11, it is characterized in that: this captions analytical algorithm is then analyzed this captions data in this video data, this literal acquisition step then captures this captions data obtaining this word segment according to this captions analytical algorithm, and this illustration acquisition step acquisition and corresponding this image data of this captions data are with as this illustration part.

17, according to the described books method for making of claim 11, it is characterized in that: this image analysing computer algorithm is according to this image data in this video data of image case study, this illustration acquisition step captures this image data obtaining this illustration part according to this image analysing computer algorithm, and this literal acquisition step from corresponding this video data of this image data obtain this word segment.

18, according to the described books method for making of claim 11, it is characterized in that: this image analysing computer algorithm foundation one object is analyzed this image data in this video data, this illustration acquisition step captures this image data obtaining this illustration part according to this image analysing computer algorithm, and this literal acquisition step from corresponding this video data of this image data obtain this word segment.

19, according to the described books method for making of claim 11, it is characterized in that: this image analysing computer algorithm is analyzed this image data in this video data, this literal acquisition step captures captions in this image data with as this word segment, and this illustration acquisition step captures this image data with as this illustration part.

20, according to the described books method for making of claim 11, it is characterized in that: this scene/shot transition analytical algorithm is then analyzed the scene/shot transition of this image data in this video data, this literal acquisition step and this illustration acquisition step with this scene/shot transition analytical algorithm then as this word segment and this illustration partly selection and the foundation of segmentation.

Images