WO2014107954A1 - Procédé et système permettant à un terminal de sélectionner des images par lots - Google Patents

Procédé et système permettant à un terminal de sélectionner des images par lots Download PDF

Info

Publication number
WO2014107954A1
WO2014107954A1 PCT/CN2013/080925 CN2013080925W WO2014107954A1 WO 2014107954 A1 WO2014107954 A1 WO 2014107954A1 CN 2013080925 W CN2013080925 W CN 2013080925W WO 2014107954 A1 WO2014107954 A1 WO 2014107954A1
Authority
WO
WIPO (PCT)
Prior art keywords
picture
feature
block
similarity
search
Prior art date
Application number
PCT/CN2013/080925
Other languages
English (en)
Chinese (zh)
Inventor
范志锋
袁景美
林全军
Original Assignee
中兴通讯股份有限公司
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 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2014107954A1 publication Critical patent/WO2014107954A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53—Querying
    • G06F16/532—Query formulation, e.g. graphical querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/759—Region-based matching

Definitions

  • the present invention relates to the field of electronic devices, and particularly to a method and system for selecting batch pictures of terminals.
  • BACKGROUND OF THE INVENTION In the front of the mouth, with the continuous development of electronic technology and the improvement of people's living standards, more and more people are leaving the home for outdoor experience, and mobile phones and cameras become the electronic devices that they should leave the most exciting moments. Often more photos taken by the user, and expect them 111 have common features but dispersed arrangement of photographs bulk selection, to classify different picture.
  • the existing selection of pictures is often based on the order of the files (type, size, name, etc.). The Sichuanese must browse and select each picture, and the same type of pictures can be read through the pictures. Copying to achieve the selection of batch images is extremely cumbersome.
  • the present invention provides a method and system for selecting batch pictures of a terminal, so that the Kawago can obtain themselves in time. The pictures of interest are quickly classified to achieve rapid selection of batch pictures.
  • a method for selecting a batch picture of a terminal comprising: acquiring a reference picture, and obtaining a reference picture 1 1 1 acquiring a reference feature picture block, the reference feature picture block is used for performing image search; searching for a matching picture according to the preset search parameter and the obtained reference feature picture block.
  • the preset search parameters include: a search path, a reference picture acquisition mode, and output the result selection result storage ⁇ recorded reference image acquisition mode comprising: a. from the stored image 'I 1 acquired directly selected reference picture; and / or moving picture image capture function according to a preset reference acquisition searches
  • the parameters and the acquired reference feature picture block search for matching pictures include: Wherein the block image characteristic value as the reference value; search parameters in accordance with a predetermined picture as a stored
  • the picture to be matched is: extracting the feature picture block of the picture to be matched one by one, and acquiring the feature value corresponding to each of the extracted feature picture blocks as the extracted feature value; and according to the acquired extracted feature values and the reference feature value, the reference feature picture block Performing similarity matching with each extracted feature picture block to match the to-be-matched picture corresponding to the extracted feature picture block whose similarity with the reference feature picture block is greater than a preset threshold. And performing similarity matching on the reference feature picture block and the extracted feature picture blocks according to the obtained extracted feature values and the reference feature values, so as to match the extracted feature pictures whose similarity with the reference feature picture block is greater than a preset threshold.
  • the picture to be matched corresponding to the block includes: extracting feature values for each extracted feature picture block; calculating a similarity between the reference feature picture block and each extracted feature picture block; and analyzing whether each of the calculated similarities is greater than a preset threshold; After the calculated similarity is greater than the preset threshold, the image to be matched corresponding to the extracted feature image corresponding to the similarity is matched; and the matched image is stored according to the preset storage path.
  • a system for selecting a batch picture of a terminal comprising: an acquiring module, configured to acquire a reference picture, and obtain a reference feature picture block from the acquired reference picture '1', the reference The feature picture block is used for image search; the search module is configured to search for a matching picture according to the preset search parameter and the acquired basic feature picture block.
  • the search module ⁇ preset search parameters include: search path, reference picture acquisition mode, result output mode and result storage [I record selection.
  • the obtaining module obtains the reference picture by: directly selecting the acquisition reference picture from the stored picture; and/or moving the picture shooting function to obtain the reference picture.
  • the searching module searches for the matching picture according to the obtained reference picture, and includes: extracting the feature value of the reference feature picture block as the reference feature value; searching for the stored picture as the to-be-matched picture according to the preset search parameter; and extracting the to-be-matched one by one a feature picture block of the picture, and acquiring the feature value corresponding to each extracted feature picture block as the extracted feature value; performing the reference feature picture block and the extracted each feature picture block according to the acquired extracted feature value and the reference feature value
  • the similarity matching is performed to match the to-be-matched picture corresponding to the extracted feature picture block whose similarity with the reference feature picture block is greater than a preset threshold.
  • the search module is further configured to: extract feature values for each extracted feature picture block; calculate a similarity between the base feature picture block and each extracted feature picture block; analyze whether each of the calculated similarities is greater than a preset threshold; When the calculated similarity is greater than the preset threshold, the image to be matched corresponding to the extracted feature image corresponding to the similarity is matched; and the matched image is stored in a preset storage path.
  • the present invention obtains the extracted feature picture block by first acquiring the 'reference picture picture and acquiring the reference feature picture block from the ⁇ as the search matching reference, and extracting the feature picture block after searching the phono picture.
  • FIG. 1 is a flowchart of a specific implementation of a method for selecting a batch picture of a terminal according to the present invention
  • FIG. 2 is a detailed flowchart of step S12 of FIG.
  • FIG. 4 is a functional block diagram of the terminal batch picture selection system of FIG.
  • the implementation, functional features, and advantages of the present invention will be described in conjunction with the embodiments with reference to the accompanying drawings.
  • the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. It should be noted that, in the case of no conflict, the features of the embodiment and the embodiment of the present application 'I' can be grouped with each other.
  • FIG. 1 it is a specific implementation flowchart of a preferred embodiment of a method for selecting a batch picture of a terminal according to the present invention. It should be emphasized that the flowchart shown in FIG. 1 is only a preferred embodiment, and those skilled in the art will recognize that any embodiment constructed around the inventive concept should not be separated from the scope of the following technical solutions:
  • the picture is obtained by acquiring a reference feature picture block from the obtained reference picture, and the reference feature picture block is used for performing picture search, and searching for a matching picture according to the preset search parameter and the obtained reference feature picture block.
  • Step S 1 1 Acquire a reference picture, and obtain a reference feature picture block from the obtained reference picture ,, and the reference feature picture block performs a picture search.
  • the obtained reference feature picture block is an N*N pixel.
  • the obtained reference feature picture block may also be 'N*M pixel picture blocks.
  • the manner of obtaining the reference picture includes: mode -: directly selecting the reference picture from the stored picture ⁇
  • Step S12 Search for a matching picture according to the preset search parameter and the obtained reference feature picture block.
  • the default search features include: selection of the search path, the reference picture acquisition mode, the result output mode, and the result storage port record.
  • the stored image is searched as a to
  • the step of extracting the feature picture block of the picture to be matched is: dividing each of the to-be-matched pictures according to a preset horizontal pixel interval and a vertical pixel interval to divide each divided picture area as extracted.
  • the feature picture block and then, the shape and size of each of the divided picture regions and the acquired reference feature picture block.
  • the step of performing similarity matching between the obtained reference feature picture block and each extracted feature picture block includes: extracting feature values for each extracted feature picture as the extracted feature value (for example, extracting the feature value as S extraction)
  • the special value ⁇ b : , b : , b 3 ...... ⁇ ; the similarity between the obtained reference feature picture block and each extracted feature picture block is calculated (for example, the similarity calculation formula is:
  • the present invention stores the extracted feature picture block and the reference feature picture block by first acquiring a reference picture and acquiring a reference feature picture block from the ⁇ as a search matching reference, and by extracting the feature picture block extracted after the phono picture is searched.
  • Step S21 Extracting the feature value of the reference feature picture block as the reference feature detection.
  • Step S22 Search for the stored picture as the to-be-matched picture according to the preset search parameter.
  • the preset search parameters include: selection of a search path.
  • Step S23 extracting feature picture blocks of the to-be-matched picture one by one, and acquiring feature values corresponding to each extracted feature picture block as the extracted feature values.
  • the extracted feature values are:
  • Step S24 Calculate the similarity between the obtained reference feature picture block and each extracted feature picture block, and extract an image with the largest similarity.
  • Step S25 analysis and extraction Whether the similarity of the image with the largest similarity is greater than a preset threshold.
  • Step S26 The matched picture is stored according to a preset storage path.
  • the process may also return to the step S23 to perform the processing of the next picture, so that the cycle processing of the large number of pictures can be realized.
  • FIG. 3 is a system architecture diagram of a preferred embodiment of a terminal batch picture selection system according to the present invention.
  • the terminal batch selection system 1 1 operates on the data processing device 1 .
  • the data processing device 1 can be a mobile phone, a note
  • the data processing device 1 further includes a storage unit 12, a display unit 13, and a processing unit 14.
  • the storage unit 12 is configured to store the web page drawing system 1 1 and the operation data of the terminal batch picture selection system 1 1 .
  • the display device 13 is configured to provide a human-computer interaction interface for inputting instructions to the 1j household, and outputting response data indicating that the data processing device 1 has 11 instructions.
  • the human-computer interaction interface includes, but is not limited to, a picture display interface generated by the terminal batch picture selection system 1 1 .
  • the processing unit 14 is configured to invoke and execute the terminal batch picture selection system 1 1 to obtain a reference picture on the data processing device 1, obtain a feature picture block through the reference picture, search for a matching picture, and reach a batch selection picture. effect.
  • the invention obtains the similarity degree of the extracted feature picture block and the reference feature picture block by acquiring the reference picture and obtaining the reference feature picture block from the ⁇ as the search matching reference, and by extracting the feature picture block extracted after the vocal picture search. Calculated, the pieces whose similarity is greater than the preset threshold are matched and stored according to the preset storage path. No longer ⁇ 3 ⁇ 4 'picture browsing to select, so that Kazuto can get the pictures of their interest and quickly sort, to achieve a quick selection of batch pictures. As shown in FIG.
  • the terminal batch picture selection system includes: an acquisition module 1 1 1 and a search module 1 12.
  • the obtaining module 1 1 1 is configured to acquire a reference picture, and obtain a reference feature picture block from the obtained reference picture ,, and the reference feature picture block performs a picture search.
  • the obtained reference feature picture block is an N*N pixel picture block.
  • the obtained reference feature picture block may also be an N*M pixel picture block.
  • the method for obtaining the preview image includes: mode: directly selecting the reference picture from the stored picture ;; mode 2: the moving picture shooting function acquires the reference picture.
  • the searching module 1 12 is configured to search for a matching picture according to the preset search parameter and the obtained reference feature picture block.
  • the preset search parameters include: selection of the search path, the reference picture acquisition mode, the result output mode, and the result storage port record.
  • searching for the matched picture by the search module 112 includes: extracting the feature value of the feature picture block as the reference feature value (for example, the reference feature value is:
  • the step of extracting the feature picture block of the picture to be matched is: dividing each picture to be matched according to a preset horizontal pixel interval and a vertical pixel interval to divide each of the divided picture areas as The extracted feature picture block, and then, each of the divided picture areas and the shape and size of the acquired feature picture block
  • the step of performing similarity matching between the obtained reference feature picture block and each extracted feature picture block includes: extracting feature values for each extracted feature picture as the extracted feature value (for example, extracting the feature value as S extraction)
  • the special value ⁇ b : , b : , b 3 ...... ⁇ ;
  • Calculate the similarity between the obtained reference feature picture block and each extracted feature picture block for example, the similarity calculation formula is:

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)

Abstract

L'invention concerne un procédé permettant à un terminal de sélectionner des images par lots. Le procédé consiste à acquérir une image de référence et à acquérir un bloc d'image caractéristique de référence à partir de l'image de référence acquise, le bloc d'image caractéristique de référence étant utilisé pour effectuer une recherche d'image; et rechercher des images correspondantes conformément à des paramètres de recherche prédéfinis et au bloc d'image caractéristique de référence acquis. Par comparaison à l'art antérieur, la présente invention acquiert tout d'abord une image de référence et acquiert à partir de celle-ci un bloc d'image caractéristique de référence en tant que référence correspondant à la recherche, extrait des blocs d'image caractéristiques après avoir recherché des images dans des catalogues, et effectue un calcul de ressemblance sur les blocs d'image caractéristiques extraits et sur le bloc d'image caractéristique de référence, effectue une comparaison pour trouver des images présentant une ressemblance supérieure à un seuil prédéfini, et stocke celles-ci conformément à un chemin de stockage prédéfini. Il n'est plus nécessaire de parcourir les images une par une en vue de les sélectionner, de sorte qu'un utilisateur peut acquérir en temps utile des images l'intéressant particulièrement et les trier rapidement pour effectuer une sélection rapide d'images par lots. L'invention concerne également un système permettant à un terminal de sélectionner des images par lots.
PCT/CN2013/080925 2013-01-11 2013-08-06 Procédé et système permettant à un terminal de sélectionner des images par lots WO2014107954A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN2013100112002A CN103092946A (zh) 2013-01-11 2013-01-11 终端批量图片选择的方法及系统
CN201310011200.2 2013-01-11

Publications (1)

Publication Number Publication Date
WO2014107954A1 true WO2014107954A1 (fr) 2014-07-17

Family

ID=48205511

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2013/080925 WO2014107954A1 (fr) 2013-01-11 2013-08-06 Procédé et système permettant à un terminal de sélectionner des images par lots

Country Status (2)

Country Link
CN (1) CN103092946A (fr)
WO (1) WO2014107954A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10146796B2 (en) 2014-08-15 2018-12-04 Baidu Online Network Technology (Beijing) Co., Ltd. Method and apparatus for photograph classification and storage
CN116362973A (zh) * 2023-05-24 2023-06-30 武汉智筑完美家居科技有限公司 图案拼接方法、设备及存储介质

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103092946A (zh) * 2013-01-11 2013-05-08 中兴通讯股份有限公司 终端批量图片选择的方法及系统
CN103677517B (zh) 2013-12-02 2016-06-29 三星电子（中国）研发中心 一种图片查找方法和装置
CN104915344B (zh) * 2014-03-10 2019-04-26 联想(北京)有限公司 一种信息处理方法及电子设备
CN103955481B (zh) * 2014-04-03 2018-04-24 小米科技有限责任公司 图片显示方法和装置
CN104111778B (zh) * 2014-06-25 2018-12-11 小米科技有限责任公司 图片显示方法和装置
CN104199973A (zh) * 2014-09-22 2014-12-10 西安酷派软件科技有限公司 图片检索方法和图片检索装置
CN106407872A (zh) * 2015-07-30 2017-02-15 中兴通讯股份有限公司 一种图片处理装置及其方法
CN106095319A (zh) * 2016-06-16 2016-11-09 珠海市魅族科技有限公司 多媒体信息的处理方法与装置
CN108898081B (zh) * 2018-06-19 2021-07-20 Oppo广东移动通信有限公司 图片处理方法、装置、移动终端及计算机可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101021870A (zh) * 2007-03-20 2007-08-22 北京中星微电子有限公司 一种图片查询方法及系统
CN101795357A (zh) * 2009-01-29 2010-08-04 索尼公司 成像设备、检索方法和程序
CN102096800A (zh) * 2009-12-14 2011-06-15 北京中星微电子有限公司 一种图像信息获取方法及装置
CN102667777A (zh) * 2009-12-24 2012-09-12 株式会社尼康 检索辅助系统、检索辅助方法以及检索辅助程序
CN103092946A (zh) * 2013-01-11 2013-05-08 中兴通讯股份有限公司 终端批量图片选择的方法及系统

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101093491A (zh) * 2006-06-23 2007-12-26 郝红卫 交互式图像检索方法
JP2010231277A (ja) * 2009-03-25 2010-10-14 Fuji Xerox Co Ltd 画像処理装置、記憶制御装置及びプログラム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101021870A (zh) * 2007-03-20 2007-08-22 北京中星微电子有限公司 一种图片查询方法及系统
CN101795357A (zh) * 2009-01-29 2010-08-04 索尼公司 成像设备、检索方法和程序
CN102096800A (zh) * 2009-12-14 2011-06-15 北京中星微电子有限公司 一种图像信息获取方法及装置
CN102667777A (zh) * 2009-12-24 2012-09-12 株式会社尼康 检索辅助系统、检索辅助方法以及检索辅助程序
CN103092946A (zh) * 2013-01-11 2013-05-08 中兴通讯股份有限公司 终端批量图片选择的方法及系统

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10146796B2 (en) 2014-08-15 2018-12-04 Baidu Online Network Technology (Beijing) Co., Ltd. Method and apparatus for photograph classification and storage
CN116362973A (zh) * 2023-05-24 2023-06-30 武汉智筑完美家居科技有限公司 图案拼接方法、设备及存储介质
CN116362973B (zh) * 2023-05-24 2023-09-19 武汉智筑完美家居科技有限公司 图案拼接方法、设备及存储介质

Also Published As

Publication number Publication date
CN103092946A (zh) 2013-05-08

Similar Documents

Publication Publication Date Title
WO2014107954A1 (fr) Procédé et système permettant à un terminal de sélectionner des images par lots
US10846324B2 (en) Device, method, and user interface for managing and interacting with media content
US8194940B1 (en) Automatic media sharing via shutter click
WO2018214772A1 (fr) Procédé et appareil de traitement de données multimédia et support de stockage
US20180054564A1 (en) Apparatus and method for providing user's emotional information in electronic device
WO2019134587A1 (fr) Procédé et dispositif de traitement de données vidéo, dispositif électronique et support d'informations
US8315463B2 (en) User interface for face recognition
WO2017107672A1 (fr) Procédé et appareil de traitement d'informations, et appareil de traitement d'informations
US20170109912A1 (en) Creating a composite image from multi-frame raw image data
EP3005055B1 (fr) Appareil et procédé pour représenter et manipuler des métadonnées
CN111444366B (zh) 图像分类方法、装置、存储介质及电子设备
WO2020259449A1 (fr) Procédé et dispositif pour générer une courte vidéo
TW201339863A (zh) 圖像識別搜索方法及裝置
WO2014127624A1 (fr) Méthode et dispositif d'affichage de fichier
CN104298694A (zh) 一种照片信息添加方法、装置及移动终端
TW201503675A (zh) 媒體檔案管理方法及系統
JP2014006680A5 (ja) 情報処理装置、情報処理システム、情報処理方法および記録媒体
KR102313339B1 (ko) 영상 검색 장치 및 그것의 영상 수집 방법
Tsai et al. Rate-efficient, real-time CD cover recognition on a camera-phone
JP2017021672A (ja) 検索装置
WO2018166275A1 (fr) Procédé de lecture et appareil de lecture, et support de stockage lisible par ordinateur
KR20200024541A (ko) 동영상 컨텐츠 검색 지원 방법 및 이를 지원하는 서비스 장치
TWI514289B (zh) 電子裝置及該電子裝置之圖像管理方法
KR20150096552A (ko) 사진 앨범 또는 사진 액자를 이용한 온라인 사진 서비스 시스템 및 방법
US20140324921A1 (en) Electronic device, method, and storage medium

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13870640

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 13870640

Country of ref document: EP

Kind code of ref document: A1