CN107807979A - The searching method and device of a kind of similar pictures - Google Patents

The searching method and device of a kind of similar pictures Download PDF

Info

Publication number
CN107807979A
CN107807979A CN201711019595.5A CN201711019595A CN107807979A CN 107807979 A CN107807979 A CN 107807979A CN 201711019595 A CN201711019595 A CN 201711019595A CN 107807979 A CN107807979 A CN 107807979A
Authority
CN
China
Prior art keywords
target photo
color histogram
color
picture
storehouse
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.)
Withdrawn
Application number
CN201711019595.5A
Other languages
Chinese (zh)
Inventor
朱秋华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201711019595.5A priority Critical patent/CN107807979A/en
Publication of CN107807979A publication Critical patent/CN107807979A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/5838Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour

Landscapes

  • Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)

Abstract

The embodiment of the invention discloses a kind of searching method of similar pictures and system.Wherein, this method includes:Calculate the color histogram of every width picture in Target Photo storehouse and be stored in database;Target Photo is loaded into Target Photo storehouse, the color histogram of Target Photo is calculated and is stored in database;The color histogram of Target Photo is matched with the color histogram of every width picture in Target Photo storehouse, similar pictures are shown according to matching result.The embodiment of the present invention realizes the effective search of similar pictures, reduces the amount of calculation and complexity of similar pictures search, and reduces searching cost.

Description

The searching method and device of a kind of similar pictures
Technical field
The present embodiments relate to the searching method and device of image processing techniques, more particularly to a kind of similar pictures.
Background technology
The outburst of cybertimes, surfing the web turns into the indispensable part of people's daily life.In face of the fast of information Speed is produced and transmitted, and the information content that people receive is also more and more, for example, various text informations and pictorial information.
How in the information pool of Large Copacity quick-pick goes out the information that user wants, turning into cybertimes needs to solve One basic problem.The amount of calculation of picture similarity involved by existing picture searching technology is bigger, computation complexity is high, Corresponding searching cost is also higher, and satisfied experience can not be produced when user searches for desired Target Photo in substantial amounts of picture Impression.
The content of the invention
The embodiment of the present invention provides a kind of searching method and device of similar pictures, to solve similar pictures in the prior art The problem of the Similarity Measure amount that is related to of search is big, computation complexity is high high with searching cost.
In a first aspect, the embodiments of the invention provide a kind of searching method of similar pictures, this method includes:
Calculate the color histogram of every width picture in Target Photo storehouse and be stored in database;
Target Photo is loaded into the Target Photo storehouse, the color histogram of the Target Photo is calculated and is stored in institute State in database;
The color histogram of the color histogram of the Target Photo and every width picture in the Target Photo storehouse is entered Row matching, similar pictures are shown according to matching result.
Further, the color histogram for calculating every width picture in Target Photo storehouse and it is stored in database, Including:
Every width picture in the Target Photo storehouse is subjected to color compressed;
Calculate the color histogram of every width picture after compressing;
The color histogram data for the every width picture being calculated is stored in database file corresponding to every width picture In folder.
Further, described that Target Photo is loaded into the Target Photo storehouse, the color for calculating the Target Photo is straight Side schemes and preserved in the database, including:
The Target Photo is loaded into the Target Photo storehouse;
The Target Photo is subjected to color compressed;
Calculate the color histogram of the Target Photo after compressing;
The color histogram data of the obtained Target Photo is preserved corresponding to Target Photo in the database In file.
Further, the color histogram by the Target Photo and every width picture in the Target Photo storehouse Color histogram is matched, and similar pictures are shown according to matching result, including:
Pre-set picture match result threshold value;
By the color histogram of the every width picture preserved in the color histogram data of the Target Photo and the database Diagram data is matched;
It is similar pictures by the picture recognition that obtained matching result is more than or equal to the threshold value, and shows described similar Picture.
Further, the picture recognition that obtained matching result is more than or equal to the threshold value is similar pictures, And the similar pictures are shown, including:
The matching value that obtained matching result is more than or equal to the threshold value arranges according to order from big to small, and presses Similar pictures corresponding to the matching value are shown successively according to the order.
Second aspect, the embodiment of the present invention additionally provide a kind of searcher of similar pictures, and the device includes:
First computing module, for calculating the color histogram of every width picture in Target Photo storehouse and being stored in database In;
Second computing module, for Target Photo to be loaded into the Target Photo storehouse, calculate the face of the Target Photo Color Histogram simultaneously preserves in the database;
Matching module, for by every width picture in the color histogram of the Target Photo and the Target Photo storehouse Color histogram is matched, and similar pictures are shown according to matching result.
Further, first computing module includes:
First compression unit, for every width picture in the Target Photo storehouse to be carried out into color compressed;
First computing unit, for calculating the color histogram of every width picture after compressing;
First storage unit, the color histogram data for the every width picture being calculated is stored in every width figure in database In file corresponding to piece.
Further, second computing module includes:
Unit is loaded into, for the Target Photo to be loaded into the Target Photo storehouse;
Second compression unit, for the Target Photo to be carried out into color compressed;
Second computing unit, for calculating the color histogram of the Target Photo after compressing;
Second storage unit, for the color histogram data of the obtained Target Photo to be stored in into the database In file corresponding to middle Target Photo.
Further, the matching module includes:
Default unit, for pre-setting picture match result threshold value;
Color-match unit, the every width figure that will be preserved in the color histogram data of the Target Photo and the database The color histogram data of piece is matched;
Display unit, the picture recognition for obtained matching result to be more than or equal to the threshold value is similar pictures, And show the similar pictures.
Further, the display unit is specifically used for:
The matching value that obtained matching result is more than or equal to the threshold value arranges according to order from big to small, and presses Similar pictures corresponding to the matching value are shown successively according to the order.
The embodiment of the present invention calculates each picture by being compressed to every width picture in Target Photo and Target Photo storehouse Corresponding color histogram is simultaneously preserved, and similar pictures are scanned for according to the matching result of picture color histogram, is solved existing The problem of Similarity Measure amount that the search for having similar pictures in technology is related to is big, computation complexity is high high with searching cost, it is real Show the effective search of similar pictures, reduced the amount of calculation and complexity of similar pictures search, and reduce searching cost.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the searching method for similar pictures that the embodiment of the present invention one provides;
Fig. 2 is a kind of structural representation of the searcher for similar pictures that the embodiment of the present invention two provides.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is a kind of flow chart of the searching method for similar pictures that the embodiment of the present invention one provides, and the present embodiment can fit For searching for the situation of similar pictures, this method can be performed by the searcher of similar pictures, and the device can use soft The mode of part and/or hardware is realized.As shown in figure 1, this method specifically includes:
Step S110, calculate the color histogram of every width picture in Target Photo storehouse and be stored in database.
Optionally, the step may particularly include:Every width picture in Target Photo storehouse is subjected to color compressed;Calculate compression The color histogram of every width picture afterwards;The color histogram data for the every width picture being calculated is stored in database In file corresponding to every width picture.
Wherein, color compressed is carried out to every width picture, exemplary, the pixel value of colour picture is 0 to 255, corresponding The species number of color point is 255 cube, colour picture is carried out into color compressed, 255 grades of pixels zoom to about 8 grades of ashes Degree, so total face variety of color points just only have 600 kinds or so, can not only reduce amount of calculation when calculating color histogram, and And amount of calculation when can reduce similar pictures matching primitives.Also, by the way that obtained color histogram data is preserved, When being searched for next time, the picture for the histogram data that saved colors in picture library does not have to compute repeatedly its color histogram Figure, further reduces amount of calculation.
Step S120, Target Photo is loaded into Target Photo storehouse, calculates the color histogram of Target Photo and be stored in In database.
Optionally, the step may particularly include:Target Photo is loaded into Target Photo storehouse;Target Photo is subjected to color Compression;Calculate the color histogram of the Target Photo after compressing;The color histogram data of obtained Target Photo is preserved In database in file corresponding to Target Photo.Wherein, exemplary, user can pass through mouse or input through keyboard mesh File is marked, by specified search engine, e.g., Baidu and Google etc., Target Photo is loaded into target figure corresponding to search engine In valut.
Step S130, the color histogram of the color histogram of Target Photo and every width picture in Target Photo storehouse is entered Row matching, similar pictures are shown according to matching result.
Optionally, the step may particularly include:Pre-set picture match result threshold value;By the face of obtained Target Photo Color Histogram data are matched with the color histogram data of the every width picture preserved in database;The matching result that will be obtained Picture recognition more than or equal to threshold value is similar pictures, and shows similar pictures.
Further, obtained matching result is more than or equal to the matching value of predetermined threshold value according to order from big to small Arrangement, and show similar pictures corresponding to the matching value successively according to same sequence.
Wherein, the otherness of color histogram is smaller between picture, and picture match end value is bigger, and similarity is higher.Example Property, user pre-sets matching result threshold value as 95%, obtained Target Photo and picture a in Target Photo storehouse, picture b, Picture c, picture d matching result are respectively 92%, 98%, 95%, 97%, and picture a of the matching value less than 95% is not similar Picture, remaining picture b, picture c, matching result is ordered as 98%, 97%, 95% from big to small corresponding to picture d, then by suitable The similar pictures that sequence is shown are picture b, picture d, picture c.
The embodiment of the present invention calculates each picture by being compressed to every width picture in Target Photo and Target Photo storehouse Corresponding color histogram is simultaneously preserved, and similar pictures are scanned for according to the matching result of picture color histogram, is solved existing The problem of Similarity Measure amount that the search for having similar pictures in technology is related to is big, computation complexity is high high with searching cost, it is real Show the effective search of similar pictures, reduced the amount of calculation and complexity of similar pictures search, and reduce searching cost.
Embodiment two
A kind of structural representation of the searcher for similar pictures that Fig. 2 provides for the embodiment of the present invention two, the present embodiment It is applicable to search for the situation of similar pictures.The device that the present embodiment is provided can perform what any embodiment of the present invention was provided Method, possess the corresponding functional module of execution method and beneficial effect.As shown in Fig. 2 the device specifically includes:
First computing module 210, for calculating the color histogram of every width picture in Target Photo storehouse and being stored in number According in storehouse.
Further, the first computing module 210 includes the first compression unit, the first computing unit and the first storage unit, Wherein:
First compression unit, for every width picture in Target Photo storehouse to be carried out into color compressed;
First computing unit, for calculating the color histogram of every width picture after compressing;
First storage unit, the color histogram data for the every width picture being calculated is stored in every width figure in database In file corresponding to piece.
Second computing module 220, for Target Photo to be loaded into the Target Photo storehouse, calculate the color of Target Photo Histogram simultaneously preserves in the database.
Further, the second computing module 220 includes being loaded into unit, the second compression unit, the second computing unit and second Storage unit, wherein:
Unit is loaded into, for Target Photo to be loaded into Target Photo storehouse;
Second compression unit, for Target Photo to be carried out into color compressed;
Second computing unit, for calculating the color histogram of the Target Photo after compressing;
Second storage unit, for the color histogram data of obtained Target Photo to be stored in into target figure in database In file corresponding to piece.
Matching module 230, for by the color of every width picture in the color histogram of Target Photo and Target Photo storehouse Histogram is matched, and similar pictures are shown according to matching result.
Further, matching module 230 includes default unit, color-match unit and display unit, wherein:
Default unit, for pre-setting picture match result threshold value;
Color-match unit, by the color of the every width picture preserved in the color histogram data of Target Photo and database Histogram data is matched;
Display unit, the picture recognition for obtained matching result to be more than or equal to predetermined threshold value is similar pictures, And show similar pictures.
Further, display unit is specifically used for:By obtained matching result be more than or equal to threshold value matching value according to Order arrangement from big to small, and show similar pictures corresponding to the matching value successively in sequence.
The embodiment of the present invention calculates each picture by being compressed to every width picture in Target Photo and Target Photo storehouse Corresponding color histogram is simultaneously preserved, and similar pictures are scanned for according to the matching result of picture color histogram, is solved existing The problem of Similarity Measure amount that the search for having similar pictures in technology is related to is big, computation complexity is high high with searching cost, it is real Show the effective search of similar pictures, reduced the amount of calculation and complexity of similar pictures search, and reduce searching cost.
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes, Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.

Claims (10)

  1. A kind of 1. searching method of similar pictures, it is characterised in that including:
    Calculate the color histogram of every width picture in Target Photo storehouse and be stored in database;
    Target Photo is loaded into the Target Photo storehouse, the color histogram of the Target Photo is calculated and is stored in the number According in storehouse;
    By the color histogram progress of every width picture in the color histogram of the Target Photo and the Target Photo storehouse Match somebody with somebody, similar pictures are shown according to matching result.
  2. 2. according to the method for claim 1, it is characterised in that the color for calculating every width picture in Target Photo storehouse Histogram is simultaneously stored in database, including:
    Every width picture in the Target Photo storehouse is subjected to color compressed;
    Calculate the color histogram of every width picture after compressing;
    The color histogram data for the every width picture being calculated is preserved into file corresponding to every width picture in the database In folder.
  3. 3. according to the method for claim 1, it is characterised in that it is described that Target Photo is loaded into the Target Photo storehouse, Calculate the color histogram of the Target Photo and preserve in the database, including:
    The Target Photo is loaded into the Target Photo storehouse;
    The Target Photo is subjected to color compressed;
    Calculate the color histogram of the Target Photo after compressing;
    The color histogram data of the obtained Target Photo is preserved into file corresponding to Target Photo in the database In folder.
  4. 4. according to the method for claim 1, it is characterised in that the color histogram by the Target Photo with it is described The color histogram of every width picture in Target Photo storehouse is matched, and similar pictures are shown according to matching result, including:
    Pre-set picture match result threshold value;
    By the color histogram number of the every width picture preserved in the color histogram data of the Target Photo and the database According to being matched;
    It is similar pictures by the picture recognition that obtained matching result is more than or equal to the threshold value, and shows the similar diagram Piece.
  5. 5. according to the method for claim 4, it is characterised in that described that obtained matching result is more than or equal to the threshold The picture recognition of value is similar pictures, and shows the similar pictures, including:
    The matching value that obtained matching result is more than or equal to the threshold value arranges according to order from big to small, and according to institute State order and show similar pictures corresponding to the matching value successively.
  6. A kind of 6. searcher of similar pictures, it is characterised in that including:
    First computing module, for calculating the color histogram of every width picture in Target Photo storehouse and being stored in database;
    Second computing module, for Target Photo to be loaded into the Target Photo storehouse, the color for calculating the Target Photo is straight Side schemes and preserved in the database;
    Matching module, for by the color of every width picture in the color histogram of the Target Photo and the Target Photo storehouse Histogram is matched, and similar pictures are shown according to matching result.
  7. 7. device according to claim 6, it is characterised in that first computing module includes:
    First compression unit, for every width picture in the Target Photo storehouse to be carried out into color compressed;
    First computing unit, for calculating the color histogram of every width picture after compressing;
    First storage unit, the color histogram data for the every width picture being calculated is preserved into every width figure in the database In file corresponding to piece.
  8. 8. device according to claim 6, it is characterised in that second computing module includes:
    Unit is loaded into, for the Target Photo to be loaded into the Target Photo storehouse;
    Second compression unit, for the Target Photo to be carried out into color compressed;
    Second computing unit, for calculating the color histogram of the Target Photo after compressing;
    Second storage unit, for the color histogram data of the obtained Target Photo to be preserved into mesh in the database Mark on a map in file corresponding to piece.
  9. 9. device according to claim 6, it is characterised in that the matching module includes:
    Default unit, for pre-setting picture match result threshold value;
    Color-match unit, by the every width picture preserved in the color histogram data of the Target Photo and the database Color histogram data is matched;
    Display unit, the picture recognition for obtained matching result to be more than or equal to the threshold value is similar pictures, and is shown Show the similar pictures.
  10. 10. device according to claim 9, it is characterised in that the display unit is specifically used for:
    The matching value that obtained matching result is more than or equal to the threshold value arranges according to order from big to small, and according to institute State order and show similar pictures corresponding to the matching value successively.
CN201711019595.5A 2017-10-27 2017-10-27 The searching method and device of a kind of similar pictures Withdrawn CN107807979A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711019595.5A CN107807979A (en) 2017-10-27 2017-10-27 The searching method and device of a kind of similar pictures

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711019595.5A CN107807979A (en) 2017-10-27 2017-10-27 The searching method and device of a kind of similar pictures

Publications (1)

Publication Number Publication Date
CN107807979A true CN107807979A (en) 2018-03-16

Family

ID=61591294

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711019595.5A Withdrawn CN107807979A (en) 2017-10-27 2017-10-27 The searching method and device of a kind of similar pictures

Country Status (1)

Country Link
CN (1) CN107807979A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108416066A (en) * 2018-03-29 2018-08-17 平安好房(上海)电子商务有限公司 Image searching method, user equipment, storage medium and picture searching device
CN108596280A (en) * 2018-04-27 2018-09-28 佛山市日日圣科技有限公司 Image identification method for literature search
CN114741553A (en) * 2022-03-31 2022-07-12 慧之安信息技术股份有限公司 Image feature-based picture searching method

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120269429A1 (en) * 2011-04-25 2012-10-25 Electronics And Telecommunications Research Institute Apparatus and method for searching image
CN103942272A (en) * 2014-03-27 2014-07-23 北京百度网讯科技有限公司 Image search method and device
CN105808645A (en) * 2016-02-26 2016-07-27 北京金山安全软件有限公司 Picture processing method and device and electronic equipment
CN106547744A (en) * 2015-09-16 2017-03-29 杭州海康威视数字技术股份有限公司 A kind of image search method and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120269429A1 (en) * 2011-04-25 2012-10-25 Electronics And Telecommunications Research Institute Apparatus and method for searching image
CN103942272A (en) * 2014-03-27 2014-07-23 北京百度网讯科技有限公司 Image search method and device
CN106547744A (en) * 2015-09-16 2017-03-29 杭州海康威视数字技术股份有限公司 A kind of image search method and system
CN105808645A (en) * 2016-02-26 2016-07-27 北京金山安全软件有限公司 Picture processing method and device and electronic equipment

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108416066A (en) * 2018-03-29 2018-08-17 平安好房(上海)电子商务有限公司 Image searching method, user equipment, storage medium and picture searching device
CN108596280A (en) * 2018-04-27 2018-09-28 佛山市日日圣科技有限公司 Image identification method for literature search
CN114741553A (en) * 2022-03-31 2022-07-12 慧之安信息技术股份有限公司 Image feature-based picture searching method

Similar Documents

Publication Publication Date Title
CN103366186B (en) Method and apparatus for dynamically changing terminal background
CN110413816B (en) Color Sketch Image Search
CN107807979A (en) The searching method and device of a kind of similar pictures
CN101369281A (en) Retrieval method based on video abstract metadata
CN114241277A (en) Attention-guided multi-feature fusion disguised target detection method, device, equipment and medium
CN105488470A (en) Method and apparatus for determining character attribute information
CN114758054A (en) Light spot adding method, device, equipment and storage medium
CN114494751A (en) License information identification method, device, equipment and medium
CN104410867A (en) Improved video shot detection method
CN112149568A (en) Short video positioning method and device, electronic equipment and computer readable storage medium
CN111833285A (en) Image processing method, image processing device and terminal equipment
CN104850600B (en) A kind of method and apparatus for searching for the picture comprising face
US20200311901A1 (en) Classifying panoramic images
CN104866818A (en) Method and device for searching pictures including human faces
CN110942056A (en) Clothing key point positioning method and device, electronic equipment and medium
CN104318236A (en) Method and system for obtaining image local features
CN114039958A (en) Multimedia processing method and device
CN108268533A (en) A kind of Image Feature Matching method for image retrieval
Constantin et al. Content description for Predicting image Interestingness
Prasad et al. A compact mobile image quality assessment using a simple frequency signature
Nguyen et al. Augmented media for traditional magazines
CN107077590B (en) Method and system for comparing video shots
CN111339465A (en) Picture processing method and device, computer equipment and storage medium
Jang et al. Accurate approximation of the earth mover’s distance in linear time
CN107609195A (en) One kind searches topic method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20180316