CN106251283A - A kind of reduced graph generating method and equipment - Google Patents
A kind of reduced graph generating method and equipment Download PDFInfo
- Publication number
- CN106251283A CN106251283A CN201610615805.6A CN201610615805A CN106251283A CN 106251283 A CN106251283 A CN 106251283A CN 201610615805 A CN201610615805 A CN 201610615805A CN 106251283 A CN106251283 A CN 106251283A
- Authority
- CN
- China
- Prior art keywords
- picture
- region
- thumbnail
- module
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
- G06F16/168—Details of user interfaces specifically adapted to file systems, e.g. browsing and visualisation, 2d or 3d GUIs
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the present invention provides a kind of reduced graph generating method and equipment, including: according to preset rules, picture is analyzed, determines the significance value of each pixel；Described picture is carried out region segmentation；Determine the significance value of each pixel in each region；Select to generate the region of thumbnail according to significance value；Thumbnail is generated on the basis of described region.Using the scheme that the embodiment of the present invention provides, the thumbnail of generation is to represent artwork sheet, it is possible to well points to, represent artwork sheet, can improve user and check efficiency and the experience of picture library.
Description
Technical field
The present embodiments relate to technical field of image processing, particularly relate to a kind of reduced graph generating method and equipment.
Background technology
Thumbnail has important function in the navigation process of photograph album, it is provided that the browsing mode of batch, thumbnail quality
Improvement is an important need in picture library navigation process, in existing thumbnail generation scheme, is to intercept in the middle of picture
Part or picture entirety is carried out reduction operation, as the thumbnail browsed.
The deficiencies in the prior art are: the thumbnail of generation can not always enable a user to know this by thumbnail
The picture that thumbnail points to, that is, the thumbnail that artwork sheet generates can not point clearly to, represent artwork sheet.
Summary of the invention
The embodiment of the present invention provides a kind of reduced graph generating method and equipment, in order to solve the breviary generated in prior art
The problem that figure can not point clearly to, represent artwork sheet.
Embodiments provide a kind of reduced graph generating method, including:
According to preset rules, picture is analyzed, determines the significance value of each pixel；
Described picture is carried out region segmentation；
Determine the significance value of each pixel in each region；
Select to generate the region of thumbnail according to significance value；
Thumbnail is generated on the basis of described region.
The embodiment of the present invention additionally provides a kind of thumbnail and generates equipment, including:
Analyze module, for picture being analyzed according to preset rules, determine the significance value of each pixel；
Segmentation module, for carrying out region segmentation to described picture；
Determine module, for determining the significance value of each pixel in each region；
Select module, for selecting to generate the region of thumbnail according to significance value；
Generation module, for generating thumbnail on the basis of described region.
A kind of reduced graph generating method of embodiment of the present invention offer and equipment, when generating thumbnail, according to default rule
Then picture is analyzed, determines the significance value of each pixel, preset rules can as required and content is set,
Such as the significance value of face is set high, then after region segmentation, choose the Area generation thumbnail that significance value is high.This
Sample, is most significance owing to generating the region of thumbnail, that is to say the region that can represent artwork sheet, therefore, it is possible to very well
Sensing, represent artwork sheet.Further, more can represent the content of artwork due to thumbnail, therefore also improve user and check
The efficiency of picture library and experience.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is this
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to root
Other accompanying drawing is obtained according to these accompanying drawings.
Fig. 1 is picture Lena schematic diagram in prior art；
Fig. 2 is the thumbnail schematic diagram of picture Lena in prior art；
Fig. 3 is reduced graph generating method implementing procedure schematic diagram in the embodiment of the present invention；
Fig. 4 is thumbnail use schematic flow sheet in mobile phone in the embodiment of the present invention；
Fig. 5 is that in the embodiment of the present invention, thumbnail generates device structure schematic diagram.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
The a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under not making creative work premise, broadly falls into the scope of protection of the invention.
Inventor note that during invention
In existing thumbnail generation scheme, it is to intercept the middle part of picture or picture entirety is reduced behaviour
Make, as the thumbnail browsed.
Owing to generating during thumbnail, only it is merely the employing of machinery and intercepts picture mid portion or the most right
Entirety reduces, and does not takes into account the information itself entrained by picture itself, namely does not accounts for image content in picture
Significance level, this content that thumbnail is shown has randomness and blindness, also hence in so that the thumbnail generated can not
Always enable a user to be known by thumbnail the picture that this thumbnail points to, in other words, browse the user of thumbnail
Can not know the content of picture by watching the content of thumbnail, such consequence is, thumbnail is only merely one
The picture that pair reduces, it loses the most important function of picture: carries information, pass on content, also hence in so that thumbnail not
Can be good at pointing to picture, lose the value of thumbnail.Say with image procossing classics picture Lena for example below
Bright, Fig. 1 is picture Lena schematic diagram, and Fig. 2 is the thumbnail schematic diagram of picture Lena, and wherein, Fig. 2 is to use to intercept in the middle of picture
The thumbnail that part generates, the content of thumbnail is the Blocked portion signal filled with twill in the drawings, in concrete thumbnail
Hold shown in figure as little in right side, as it can be seen, it is figure that general picture user can not just know this according to the content shown in Fig. 2
Sheet Lena.
Based on this, the embodiment of the present invention provides a kind of thumbnail and generates scheme, the life of thumbnail can be effectively improved
Become quality, improve the Consumer's Experience in picture library navigation process, be illustrated below.
Fig. 3 is reduced graph generating method implementing procedure schematic diagram, as it can be seen, may include that
Step 301, according to preset rules, picture is analyzed, determines the significance value of each pixel；
Step 302, described picture is carried out region segmentation；
Step 303, determine the significance value of each pixel in each region；
Step 304, according to significance value select generate thumbnail region；
Step 305, on the basis of described region generate thumbnail.
In enforcement, described preset rules based on degree of deep learning style by after picture training generate.
In enforcement, described picture is carried out region segmentation and uses image segmentation algorithm to carry out.
In enforcement, on the basis of described region, generate thumbnail, be the base in described region by the way of bounding box
Generate on plinth.
In enforcement, before the significance value of each pixel determining each region, farther include:
Picture is carried out denoising.
Illustrate below in conjunction with example.
In the present embodiment, will illustrate how the scheme implementing and using the embodiment of the present invention to provide in mobile phone photo album.
Fig. 4 is thumbnail use schematic flow sheet in mobile phone, as it can be seen, mainly comprise the steps that
Step 401: the every pictures to photograph album, carries out significance analysis, obtains the significance scattergram of correspondence.
For input picture, the preset rules obtained by the way of using based on degree of depth study, be converted to corresponding aobvious
Work property figure, each pixel of Saliency maps represents the significance measure of original pixel, such as, in personage's picture, permissible
Preset rules is set as: the significance of face is the highest, next to that hair, torso portion, accordingly, the aobvious of background can be set
Work is relatively low.
Concrete, to photograph album every pictures, carries out significance analysis, and the significance scattergram obtaining correspondence can be as
Under:
(1) by substantial amounts of training picture, including artwork and the actual significance of manual mark, degree of depth network is carried out
Training；
(2) input picture is to training more preferable degree of depth network, the Saliency maps picture that output picture is corresponding；
(3) significance picture is done denoising, remove some noise spots.
Step 402: Saliency maps picture is carried out picture segmentation process, obtains some picture region.
Concrete, the picture after each Zhang Jinhang significance analysis can be passed through common image segmentation algorithm, as
Mean-shift method, carries out dividing processing to Saliency maps picture, and image is divided into and some has erose region.
Step 403: select the region that significance is maximum, obtain the bounding box in this region.
Concrete, segmentation image obtains significance maximum region, and obtains the Rectangular Bounding Volume in this region, as contracting
The foundation of sketch map cutting.Modal OBBs algorithm has AABB bounding box (Axis-aligned bounding box), surrounds
Ball (Sphere), oriented bounding box OBB (Oriented bounding box) and fixed direction hull fdh (Fixed
Directions hulls or k-DOP) etc..
Step 404: based on the bounding box of maximum marking area, artwork is carried out cutting and adaptation, generate thumbnail.
The Rectangular Bounding Volume obtained according to step 403, on this basis, carries out trimming operation to artwork, and adaptive in one's hands
On machine screen, carry out thumbnail and show.
User, when browsing picture library, the most first sees the thumbnail of picture, as seen from the above-described embodiment, uses embodiment to carry
The scheme of confession, the thumbnail generated by significance based on content can allow thumbnail more can represent the content of artwork, it is possible to
Improve user and check efficiency and the experience of picture library.
Based on same inventive concept, the embodiment of the present invention additionally provides a kind of thumbnail and generates equipment, due to this equipment
The principle of solution problem is similar to a kind of reduced graph generating method, and therefore the enforcement of this equipment may refer to the enforcement of method, weight
Multiple part repeats no more.
Fig. 5 is that thumbnail generates device structure schematic diagram, as it can be seen, may include that
Analyze module 501, for picture being analyzed according to preset rules, determine the significance value of each pixel；
Segmentation module 502, for carrying out region segmentation to described picture；
Determine module 503, for determining the significance value of each pixel in each region；
Select module 504, for selecting to generate the region of thumbnail according to significance value；
Generation module 505, for generating thumbnail on the basis of described region.
In enforcement, analyze module and can also be further used for basis based on degree of deep learning style by generating after picture training
Described preset rules picture is analyzed.
In enforcement, segmentation module can also be further used for using image segmentation algorithm that described picture is carried out region and divide
Cut.
In enforcement, generation module can generate in the way of being further used for by bounding box on the basis of described region
Thumbnail.
In enforcement, determine that module can also be further used for before the significance value of each pixel determining each region, right
Picture carries out denoising.
Device embodiment described above is only schematically, and the wherein said unit illustrated as separating component can
To be or to may not be physically separate, the parts shown as unit can be or may not be physics list
Unit, i.e. may be located at a place, or can also be distributed on multiple NE.Can be selected it according to the actual needs
In some or all of module realize the purpose of the present embodiment scheme.Those of ordinary skill in the art are not paying creativeness
Work in the case of, be i.e. appreciated that and implement.
Through the above description of the embodiments, those skilled in the art it can be understood that to each embodiment can
The mode adding required general hardware platform by software realizes, naturally it is also possible to pass through hardware.Based on such understanding, on
State the part that prior art contributes by technical scheme the most in other words to embody with the form of software product, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD etc., including some fingers
Make with so that a computer equipment (can be personal computer, server, or the network equipment etc.) performs each and implements
The method described in some part of example or embodiment.
Last it is noted that above example is only in order to illustrate technical scheme, it is not intended to limit；Although
With reference to previous embodiment, the present invention is described in detail, it will be understood by those within the art that: it still may be used
So that the technical scheme described in foregoing embodiments to be modified, or wherein portion of techniques feature is carried out equivalent；
And these amendment or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (10)
1. a reduced graph generating method, it is characterised in that including:
According to preset rules, picture is analyzed, determines the significance value of each pixel；
Described picture is carried out region segmentation；
Determine the significance value of each pixel in each region；
Select to generate the region of thumbnail according to significance value；
Thumbnail is generated on the basis of described region.
Method the most according to claim 1, it is characterised in that described preset rules is by figure based on degree of deep learning style
Generate after sheet training.
Method the most according to claim 1, it is characterised in that it is to use image segmentation that described picture carries out region segmentation
Algorithm is carried out.
Method the most according to claim 1, it is characterised in that generate thumbnail on the basis of described region, be to pass through
The mode of bounding box generates on the basis of described region.
5. according to the arbitrary described method of Claims 1-4, it is characterised in that determining each pixel notable in each region
Before property value, farther include:
Picture is carried out denoising.
6. a thumbnail generates equipment, it is characterised in that including:
Analyze module, for picture being analyzed according to preset rules, determine the significance value of each pixel；
Segmentation module, for carrying out region segmentation to described picture；
Determine module, for determining the significance value of each pixel in each region；
Select module, for selecting to generate the region of thumbnail according to significance value；
Generation module, for generating thumbnail on the basis of described region.
Equipment the most according to claim 6, it is characterised in that analyze module and be further used for according to based on degree of depth study side
Picture is analyzed by formula by the described preset rules generated after picture training.
Equipment the most according to claim 6, it is characterised in that segmentation module is further used for using image segmentation algorithm pair
Described picture carries out region segmentation.
Equipment the most according to claim 6, it is characterised in that generation module be further used for by the way of bounding box
Thumbnail is generated on the basis of described region.
10. according to the arbitrary described equipment of claim 6 to 9, it is characterised in that determine that module is further used for determining each district
Before the significance value of each pixel in territory, picture is carried out denoising.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610615805.6A CN106251283A (en) | 2016-07-28 | 2016-07-28 | A kind of reduced graph generating method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610615805.6A CN106251283A (en) | 2016-07-28 | 2016-07-28 | A kind of reduced graph generating method and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106251283A true CN106251283A (en) | 2016-12-21 |
Family
ID=57605475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610615805.6A Pending CN106251283A (en) | 2016-07-28 | 2016-07-28 | A kind of reduced graph generating method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106251283A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107146197A (en) * | 2017-03-31 | 2017-09-08 | 北京奇艺世纪科技有限公司 | A kind of reduced graph generating method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100278443A1 (en) * | 2009-04-30 | 2010-11-04 | Stmicroelectronics S.R.L. | Method and systems for thumbnail generation, and corresponding computer program product |
| CN103903223A (en) * | 2014-04-24 | 2014-07-02 | 厦门美图之家科技有限公司 | Thumbnail acquiring method based on image saliency detection |
| CN103902730A (en) * | 2014-04-15 | 2014-07-02 | 中国科学院自动化研究所 | Thumbnail generation method and system |
| CN104063844A (en) * | 2013-03-21 | 2014-09-24 | 腾讯科技（深圳）有限公司 | Reduced graph generation method and system |
| CN104504651A (en) * | 2015-01-22 | 2015-04-08 | 网易（杭州）网络有限公司 | Preview generation method and device |
-
2016
- 2016-07-28 CN CN201610615805.6A patent/CN106251283A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100278443A1 (en) * | 2009-04-30 | 2010-11-04 | Stmicroelectronics S.R.L. | Method and systems for thumbnail generation, and corresponding computer program product |
| CN104063844A (en) * | 2013-03-21 | 2014-09-24 | 腾讯科技（深圳）有限公司 | Reduced graph generation method and system |
| CN103902730A (en) * | 2014-04-15 | 2014-07-02 | 中国科学院自动化研究所 | Thumbnail generation method and system |
| CN103903223A (en) * | 2014-04-24 | 2014-07-02 | 厦门美图之家科技有限公司 | Thumbnail acquiring method based on image saliency detection |
| CN104504651A (en) * | 2015-01-22 | 2015-04-08 | 网易（杭州）网络有限公司 | Preview generation method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107146197A (en) * | 2017-03-31 | 2017-09-08 | 北京奇艺世纪科技有限公司 | A kind of reduced graph generating method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8687001B2 (en) | Apparatus and method extracting light and texture, and rendering apparatus using light and texture | |
| CN104995657B (en) | System and method for resizing an image | |
| US10528620B2 (en) | Color sketch image searching | |
| TWI398158B (en) | Method for generating the depth of a stereo image | |
| US20160063035A1 (en) | Method and system for 3d model database retrieval | |
| CN107291945A (en) | The high-precision image of clothing search method and system of view-based access control model attention model | |
| US10867428B2 (en) | Enhanced texture packing | |
| CN111768405B (en) | Method, device, equipment and storage medium for processing marked image | |
| CN110097059A (en) | Based on file and picture binary coding method, system, the device for generating confrontation network | |
| CN110084828A (en) | A kind of image partition method, device and terminal device | |
| WO2016175785A1 (en) | Topic identification based on functional summarization | |
| CN106251283A (en) | A kind of reduced graph generating method and equipment | |
| KR102633159B1 (en) | Apparatus and method for restoring 3d-model using the image-processing | |
| CN105975922A (en) | Information processing method and information processing device | |
| CN104751454A (en) | Method and device for determining figure outline in image | |
| Lee et al. | A multi-level depiction method for painterly rendering based on visual perception cue | |
| CN111260757A (en) | Image processing method and device and terminal equipment | |
| CN109508217B (en) | A data processing method, device, equipment and medium | |
| CN112837388A (en) | Multi-light-source picture generation method | |
| JP2017207838A (en) | Image retrieval device, image retrieval method, image retrieval program, index data creation device, index data creation method and index data creation program | |
| Rabitz | Photogrammetric scanning of rock carvings | |
| CN106407215B (en) | A kind of data processing method and device | |
| Obrador | Content selection based on compositional image quality | |
| Mao et al. | Noise Transparentization Approach for High-Precision Visualization of 3D Scanned Point Clouds | |
| Abouzahra et al. | Enhancing point cloud labeling: a scalable superpoint-based approach for efficient data annotation and analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161221 |
|
| WD01 | Invention patent application deemed withdrawn after publication |