CN104200249A - Automatic clothes matching method, device and system - Google Patents

Automatic clothes matching method, device and system Download PDF

Info

Publication number
CN104200249A
CN104200249A CN201410424590.0A CN201410424590A CN104200249A CN 104200249 A CN104200249 A CN 104200249A CN 201410424590 A CN201410424590 A CN 201410424590A CN 104200249 A CN104200249 A CN 104200249A
Authority
CN
China
Prior art keywords
picture
eigenwert
collocation
clothing
pattern
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.)
Granted
Application number
CN201410424590.0A
Other languages
Chinese (zh)
Other versions
CN104200249B (en
Inventor
谢水宁
冉会琼
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.)
Tencent Technology Shenzhen Co Ltd
Chongqing University of Post and Telecommunications
Original Assignee
Chongqing University of Post and Telecommunications
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 Chongqing University of Post and Telecommunications filed Critical Chongqing University of Post and Telecommunications
Priority to CN201410424590.0A priority Critical patent/CN104200249B/en
Publication of CN104200249A publication Critical patent/CN104200249A/en
Application granted granted Critical
Publication of CN104200249B publication Critical patent/CN104200249B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The embodiment of the invention discloses an automatic clothes matching method and device. The automatic clothes matching method comprises the steps of obtaining a first picture of a piece of clothes required to be automatically matched; performing color recognition, shape recognition and image recognition on the first picture to obtain a color characteristic value, a shape characteristic value and a pattern characteristic value; confirming the clothes category matched to the piece of clothes corresponding to the first picture according to the shape characteristic value of the first picture; selecting a second picture meeting a preset image matching rule, a preset pattern matching rule and the clothes category according to the color characteristic value, the shape characteristic value and the pattern characteristic value of the first picture and enabling the second picture to be matched with the first picture. By means of the automatic clothes matching method and device, automatic clothes matching can be achieved on one side of a terminal, clothes management can be completed, network communication is not needed, and achievement cost for automatic clothes matching is reduced.

Description

A method for clothing automatic collocation, Apparatus and system
Technical field
The present invention relates to field of computer technology, a kind of particularly method of clothing automatic collocation, Apparatus and system.
Background technology
Clothing collocation is the problem that needs consideration in people's daily life, can facilitate user to manage the clothing of own wardrobe by computer realization clothing automatic collocation, and can be fast for user provides the scheme of the collocation of wearing the clothes time saving and energy saving.
Clothing automatic collocation has its realistic meaning under a lot of scenes, for example: A: whether user, in the time buying clothes, need to determine and oneself have clothes, accessories to arrange in pairs or groups with it; If had, can save the cost of buying collocation clothes accessories; B: when user has many clothes, clothes collocation is comparatively complicated, by clothing automatic collocation, can, in the time that user selects arbitrarily wherein one, provide arranging scheme automatically fast, reduces the time that user pays for this reason.
At present the scheme of clothing automatic collocation has the Intelligent clothes cabinet based on cloud computing, be a kind of can with the Intelligent clothes cabinet of cloud service network service.The implementation procedure of scheme is as follows: gather clothes data message in Intelligent clothes cabinet by Intelligent clothes cabinet information acquisition terminal, and by its numbering; Network connecting module provides and being connected of network and cloud service platform interface; User's access interface provides message exchange and transmission, coupling and the signal that receives transmission; Cloud service manager adopts distributed file system to manage the clothes data message from user interface obtains numbering, cloud data storage center is by mapping abbreviation (MapReduce, a kind of programming model, is usually used in the concurrent operation of large-scale dataset) mode is to the parallel storage of clothes data message.It mainly utilizes network connecting platform that data are sent to cloud service platform, realizes by network service.
Above scheme needs communication Network Based to realize, and transmits data volume large, realizes cost higher.
Summary of the invention
The embodiment of the present invention provides a kind of method of clothing automatic collocation, and Apparatus and system, for realizing clothing automatic collocation in terminal or server side, need not be realized by network service, reduces clothing automatic collocation and realizes cost.
A method for clothing automatic collocation, comprising:
Obtain the first picture that needs the clothing of automatic collocation; Described the first picture is carried out to color identification, shape recognition and image recognition, obtain eigenwert, the eigenwert of shape and the eigenwert of pattern of color;
Determine according to the eigenwert of the shape of described the first picture the clothing classification that the corresponding clothing of described the first picture need to be arranged in pairs or groups;
Eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of described the first picture of foundation, in selection second picture, meet predetermined image collocation rule and pattern collocation rule, and meet the second picture of described clothing classification, arrange in pairs or groups with described the first picture.
A device for clothing automatic collocation, comprising:
Picture acquiring unit, for obtaining the first picture that needs the clothing of automatic collocation;
Picture recognition unit, for described the first picture is carried out to color identification, shape recognition and image recognition, obtains eigenwert, the eigenwert of shape and the eigenwert of pattern of color;
Classification determining unit, for the clothing classification of determining that according to the eigenwert of the shape of described the first picture the corresponding clothing of described the first picture need to be arranged in pairs or groups;
Picture selected cell, for eigenwert, the eigenwert of shape and the eigenwert of pattern of the color according to described the first picture, in selection second picture, meet predetermined image collocation rule and pattern collocation rule, and meet the second picture of described clothing classification, arrange in pairs or groups with described the first picture.
A system for clothing automatic collocation, comprising: with the terminal and the server that can communication mode connect;
The device of any one that wherein, described server provides for the embodiment of the present invention;
Described terminal, is used to specify for sending specify message to described server the first picture that needs the clothing of automatic collocation, or, for sending the first picture to described server and specifying described the first picture to need automatic collocation;
Described server, also for sending to described terminal by collocation result.
As can be seen from the above technical solutions, the embodiment of the present invention has the following advantages: in the time buying clothes, the first picture can obtain by shooting, can determine the current clothing that whether has with it collocation of user by automatic collocation, reduces the waste of buying unnecessary clothing; In the time selecting to wear which kind of clothing, the first picture can be that user specifies in local picture, can determine rapidly the current clothing of collocation with it of user by automatic collocation, and minimizing user selects the time of clothing.Application scenarios also has a lot, and the embodiment of the present invention just can realize the automatic collocation of clothing in terminal one side, complete the management to clothing, need not realize by network service, reduces clothing automatic collocation and realizes cost.
Brief description of the drawings
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, below the accompanying drawing of required use during embodiment is described is briefly introduced, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is embodiment of the present invention method flow schematic diagram;
Fig. 2 is the algorithm flow schematic diagram of embodiment of the present invention shape recognition technology;
Fig. 3 is the algorithm flow schematic diagram of embodiment of the present invention color recognition technology;
Fig. 4 is the calculation schematic flow sheet of embodiment of the present invention image recognition technology;
Fig. 5 is embodiment of the present invention method flow schematic diagram;
Fig. 6 is embodiment of the present invention apparatus structure schematic diagram;
Fig. 7 is embodiment of the present invention apparatus structure schematic diagram;
Fig. 8 is embodiment of the present invention apparatus structure schematic diagram;
Fig. 9 is embodiment of the present invention apparatus structure schematic diagram;
Figure 10 is embodiment of the present invention apparatus structure schematic diagram;
Figure 11 is embodiment of the present invention apparatus structure schematic diagram;
Figure 12 is embodiment of the present invention apparatus structure schematic diagram;
Figure 13 is embodiment of the present invention server architecture schematic diagram;
Figure 14 is embodiment of the present invention system architecture schematic diagram.
Embodiment
In order to make the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing, the present invention is described in further detail, and obviously, described embodiment is only a part of embodiment of the present invention, instead of whole embodiment.Based on the embodiment in the present invention, those of ordinary skill in the art, not making all other embodiment that obtain under creative work prerequisite, belong to the scope of protection of the invention.
The embodiment of the present invention provides a kind of method of clothing automatic collocation, as shown in Figure 1, comprising:
101: obtain the first picture that needs the clothing of automatic collocation; Above-mentioned the first picture is carried out to color identification, shape recognition and image recognition, obtain eigenwert, the eigenwert of shape and the eigenwert of pattern of color;
In embodiments of the present invention, the first picture is the picture of specifying, and needing equipment is that it completes automatic collocation; The device of realizing clothing automatic collocation can be terminal device, can be also server; For different application scenarioss, can there is different application demands, for example: with the example that is embodied as of end side, in the time buying clothes, the first picture can obtain by shooting; In the time selecting to wear which kind of clothing, the first picture can be that user specifies in local picture.With the example that is embodied as of server side, user in the time of shopping at network, the first picture that server can receiving terminal apparatus be specified, the first picture that server also can receiving terminal apparatus sends and specify this first picture need to carry out automatic collocation.The mode of obtaining the first picture can have different sources according to different application scenarioss, and the source of the first picture does not affect the realization of the embodiment of the present invention, will not limit this embodiment of the present invention.
In embodiments of the present invention, the identification of image recognition, color, shape recognition, graph image recognizer and color management algorithm that can be based on various maturations, the embodiment of the present invention will not uniqueness limit this.In subsequent embodiment, will describe for example respectively.
102: determine according to the eigenwert of the shape of above-mentioned the first picture the clothing classification that the corresponding clothing of above-mentioned the first picture need to be arranged in pairs or groups;
In embodiments of the present invention, the eigenwert of the shape of the first picture, can represent what clothing classification the clothing in the first picture belongs to, such as: be upper garment, trousers, shoes, skirt, Western-style clothes or ornament etc.Clothing classification can preset as required, and broad classification should comprise: upper garment, trousers, shoes, ornament; But can also continue segmentation, as: upper garment can be Western-style clothes, shirt etc., also can also be in conjunction with, for example: the combination of upper garment and trousers can be included in one-piece dress; The classification of clothing can be set according to the demand of classification by technician, and the embodiment of the present invention is not made uniqueness and limited to this.
103: eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of above-mentioned the first picture of foundation, in selection second picture, meet predetermined image collocation rule and pattern collocation rule, and meet the second picture of above-mentioned clothing classification, arrange in pairs or groups with above-mentioned the first picture.
In embodiments of the present invention, buying when clothes, the first picture can obtain by shootings, and whether can determine by automatic collocation that user is current has a clothing of collocation with it, the waste of the unnecessary clothing of minimizing purchase; In the time selecting to wear which kind of clothing, the first picture can be that user specifies in local picture, can determine rapidly the current clothing of collocation with it of user by automatic collocation, and minimizing user selects the time of clothing.Application scenarios also has a lot, and the embodiment of the present invention just can realize the automatic collocation of clothing in terminal one side, complete the management to clothing, need not realize by network service, reduces clothing automatic collocation and realizes cost.
Be stored in the second picture of device this locality, and the eigenwert parameter of corresponding second picture, be used for arranging in pairs or groups with the first picture, the procurement process of second picture and characteristic of correspondence value parameter can be as follows: above-mentioned obtain the first picture that needs the clothing of automatic collocation before, said method also comprises:
Obtain second picture, and above-mentioned second picture is carried out to color identification, shape recognition and image recognition, obtain eigenwert, the eigenwert of shape and the eigenwert of pattern of color;
Determine the clothing classification under above-mentioned second picture according to the eigenwert of the shape of above-mentioned second picture;
Store above-mentioned second picture, and the eigenwert of the color of above-mentioned second picture, the eigenwert of pattern and affiliated clothing classification.
In embodiments of the present invention, second picture can be to concentrate batch input, for example: when the first installation of user can be carried out the application of embodiment of the present invention flow process, concentrate the picture of taking the clothing in own wardrobe, as second picture batch input.The source of second picture can be controlled according to the demand of oneself voluntarily by user, before obtaining second picture, can also show the information of " picture that please take or load own clothes ".
The embodiment of the present invention also provides the specific implementation of how to store second picture and characteristic of correspondence value, facilitate follow-up automatic clothes collocation, be used for improving the matching efficiency of automatic clothes collocation, specific as follows: the above-mentioned second picture of above-mentioned storage, and the eigenwert of the color of above-mentioned second picture, the eigenwert of pattern and affiliated clothing classification comprise:
Above-mentioned second picture and affiliated clothing classification thereof are stored in database, the eigenwert of the color of above-mentioned second picture is stored in color libraries, the eigenwert of the pattern of above-mentioned second picture is stored in pattern storehouse;
Eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of above-mentioned the first picture of above-mentioned foundation, select to meet in second picture predetermined image collocation rule and pattern collocation rule, and the second picture that meets above-mentioned clothing classification comprises:
Eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of above-mentioned the first picture of foundation respectively, to meet predetermined image collocation rule and pattern collocation rule as standard, in above-mentioned color libraries and above-mentioned pattern storehouse, select the second picture of the clothing classification that belongs to above-mentioned needs collocation.
In the time that device carries out automatic clothes collocation, may there is the situation of multiple second pictures, the generation of this situation may be because clothing is a lot, really there is the situation of multiple arranging scheme, also may be because the second picture obtaining respectively according to coupling appropriate level or preset multiple matched rule, the concrete embodiment of the present invention will not limit, in the situation that there is multiple second picture, situation about how to process can be as follows: after second picture is selected, said method also comprises: if the second picture of selecting has at least two, each second picture and the first picture that combination is selected respectively obtain the result of arranging in pairs or groups.
In the situation that there is multiple second picture, the embodiment of the present invention can be carried out priority classification to second picture, realize by the priority of setting in collocation rule in embodiments of the present invention, specific as follows: after the result that obtains arranging in pairs or groups, said method also comprises: the priority of determining each collocation result according to the coupling priority of setting in predetermined image collocation rule and pattern collocation rule.
Be understandable that, occur multiple possibility differences according to second picture, can have the setting means of multiple priorities, for example: can be by setting multiple collocation rule and setting the priority between collocation priority.Therefore above scheme should not be construed as the uniqueness of well-behaved inventive embodiments is limited.
When in embodiments of the present invention the first picture being carried out to Auto-matching for the first time, can carry out above whole flow process, but for the second time when Auto-matching, can carry out above whole flow process, but by the automatic collocation result before recording in advance, realize fast automatic collocation, can reduce like this operand, improve collocation efficiency, specific as follows: after second picture is selected, said method also comprises:
If receive the confirmation instruction of above-mentioned second picture, record the corresponding relation of above-mentioned second picture and the first picture; If when getting above-mentioned the first picture or second picture and needing automatic collocation, determine the picture of arranging in pairs or groups with it according to above-mentioned second picture and the corresponding relation of the first picture.
In the present embodiment, second picture needs automatic collocation also can realize by the history collocation result of record, the in the situation that particularly in wardrobe, article being more stable, carried out when repeatedly coupling has recording of a lot of historical collocation, and also can facilitate and obtain accurately comparatively comprehensively arranging scheme.
Mainly for RGB (Red, Green, Blue, red, green, blue) color space controls and extracts the pixel of image, the color of pixel is mixed according to a certain percentage by RGB three, its three's span is 0~255, each color can represent with three variablees, be the intensity of RGB, once the component of three primary colours determined, the color relation of pixel is completely definite.According to corresponding conversion, RGB can be converted to HLS (Hue colourity, Lightness brightness, Saturation saturation degree), YUV (lightness Luminance, chrominance C hrominance, concentration C hroma) model, can be more careful to the extraction of color.
In embodiments of the present invention, the identification division of graph image is mainly comprised to following three aspects:
1) color identification: according to received information, differentiate corresponding color value, and color is kept a record and preserved.
2) shape recognition: cut apart the shape binary map of image, after obtaining binary map, the shape of target made to qualitative and quantitative analysis, acquisition can for the treatment of data, representing this target by the proper vector of this shape description.
3) image recognition: image recognition is mainly to cut apart and image recognition theory based on image, and the clothing that contains image is carried out to analyzing and processing, thus determine the picture position in clothing, and further propose and identify picture shape.
In embodiments of the present invention, the flow process of automatic clothes collocation relates generally to following four aspects:
1) image pre-service: carry out pretreatment operation to collecting the image obtaining, extract and identify the correlated characteristic of each pictures, by its shape, corresponding picture is identified, and be referred in the storehouses such as clothes, trousers, skirt, shoes, accessories;
2) color identification: select the color of the Target Photo that will identify with a check box, identify the title of this kind of color by comparison color card;
3) image recognition: because mostly there is pattern in clothes, therefore mainly identify by image recognition technology the pattern extracting in clothes;
4) images match: by the picture of processing, by color, shape, image are identified and feature extraction after, according to the common colour match rule in database, and pattern collocation rule is mated clothing accordingly.
In embodiments of the present invention, main functional module has following 9 functional modules:
1, picture load module: want the clothes picture of collocation for gathering user, it can gather by cell-phone camera or this map office, the line number of going forward side by side Data preprocess, preserves the shape of picture, and is categorized in corresponding storehouse.
2, color identification frame: be mainly used for user and want the check box that the extraction of that color in clothes is selected, user can extract own needed color by this module.
3, pattern identification frame: user can select the pattern in clothes by this check box, and identify accordingly the figure of this pattern.
4, automatic collocation module: this module is mainly can be automatically to clothes collocation to processing picture later, and user need not manually just can generate collocation result automatically.
5, the module of manually arranging in pairs or groups: after user imports picture, can select manually and automatic collocation module.In the time that user does not meet the result of automatic collocation, can carry out selecting manual matching function after cls.
6, module is removed in collocation: if when the dissatisfied current clothes of user mates, can carry out the collocation result in screen to remove.
7, collocation sharing module: the collocation result of oneself is shared to space, microblogging etc. for user.
8, module is derived in collocation: user can export to the collocation result of oneself satisfaction in this map office.
9, collocation removing module: for deleting a certain specific user's collocation.
The embodiment of the present invention, in implementation procedure, can be used garment shape recognition technology, realizes by pattern-recognition; Which kind of color is color recognition technology mainly can the value collection based on three primary colours differentiate for, and pattern recognition techniques mainly can be cut apart and image recognition theory based on image, the clothing that contains image is carried out to analyzing and processing, thereby determine the picture position in clothing, and further propose and identify picture shape.Below introduce respectively:
The algorithm of shape recognition technology, as shown in Figure 2, comprises the steps:
201: input picture, what suppose input is the picture of RGB;
202: RGB figure is converted into gray-scale map;
203: carry out the figure image intensifying of histogram equalization method;
204: by level and smooth the gray-scale map image gaussian filtering in 203;
205: the figure in 204 is carried out to canny rim detection, extract and cut apart the image-region with larger shape target, i.e. area-of-interest.
This step can record this area-of-interest position for (region of interest, ROI);
206: use bilinear interpolation that size is normalized to 100*130;
207: use region-growing method to obtain the profile of shape target;
208: set to describe this profile with profile square and profile, as the proper vector of profile;
209: try to achieve successively it by the proper vector in template base and spend similarly;
210: the shape obtaining be classified as with template in the highest class of similarity, complete the Classification and Identification of shape.
The algorithm of color recognition technology, as shown in Figure 3, comprises the steps:
301: obtain the area-of-interest position ROI (region of interest, area-of-interest) producing in shape recognition.Machine vision, image are sketched the contours of and are needed region to be processed in modes such as square frame, circle, ellipse, irregular polygons from processed image in processing, and are called area-of-interest, pluck out the subimage of corresponding position in RGB figure with this position;
302: the RGB color space figure of subimage is converted into YUV color space figure;
303: ask Y, the U of 302 subimages that obtain, the color moment of tri-passages of V, comprising: first moment, second moment and third moment, obtain altogether 9 eigenwerts;
304: with the eigenwert of the color that obtains respectively with color libraries in color moment vector ask for its Euclidean distance (Euclidean distance), ask similarity, if gap excessive (based on setting threshold), is recorded to this color vector in color libraries;
305: the color of subimage is classified as to the colour type of Euclidean distance minimum with it;
306: the color moment recognizing (selecting similar) is selected in colour match information bank, so completed the discriminator of color;
In embodiments of the present invention, collocation is related to that weight table can be set by technician, conventionally can all be set to be less than 1 threshold value, the certain collocation of representative probability.
The algorithm of image recognition technology, as shown in Figure 4, comprises the steps:
401: pre-service: be mainly that image is carried out to gray processing, figure image intensifying, noise remove, Edge extraction, interesting image regions is cut apart etc.
402: feature extraction: responsible handle can fully represent that the form of the feature numerical value of this image uniqueness expresses, and retains real features as far as possible, the false feature of filtering.
403: Images Classification: in picture system, the image of input will mate with tens of even thousands of images up to a hundred, in order to reduce search time, to reduce the complexity of calculating, pattern can be assigned in different pattern storehouses with accurate consistent method.
404: images match: images match is on the basis of image pre-service and feature extraction, the test pattern feature of current input and the template image feature of preserving are in advance compared, by the similarity degree between them, judge that whether this two width image is consistent.
Following examples are illustrated the application scenarios with regard to the embodiment of the present invention, the flow process of manual collocation is also provided in following flow process, and specify and need the graph image of special concern and the region of color by check box by user, as shown in Figure 5, concrete steps are as follows:
501: receive user and import picture to be processed;
502: the picture importing is carried out to shape recognition processing;
503: the shape obtaining by shape recognition is classified picture;
504: user selects oneself to want the form of collocation, automatically still manually; Automatically, jump to step 505, if manually jump to step 508 if selected;
505: receive user by a check box and choose the color of object region of identification, and identify the color in this region, and be recorded in color libraries;
506: receive the target pattern of user's selective recognition by a check box, and identify this pattern, and be recorded in pattern storehouse;
507: according to color libraries, and matched rule in pattern storehouse carries out optimum matching, then jumps to step 509;
508: receive the manually collocation clothes picture of input of user, after having arranged in pairs or groups, jump to step 509;
509: in screen, show matching result; If be satisfied with current results, jump to step 510, if dissatisfied current results jumps to step 504 and re-starts new one and take turns coupling;
510: preserve current matching result, output in this map office.
The embodiment of the present invention also provides a kind of device, as shown in Figure 6, comprising:
Picture acquiring unit 601, for obtaining the first picture that needs the clothing of automatic collocation;
Picture recognition unit 602, for above-mentioned the first picture is carried out to color identification, shape recognition and image recognition, obtains eigenwert, the eigenwert of shape and the eigenwert of pattern of color;
Classification determining unit 603, for the clothing classification of determining that according to the eigenwert of the shape of above-mentioned the first picture the corresponding clothing of above-mentioned the first picture need to be arranged in pairs or groups;
Picture selected cell 604, for eigenwert, the eigenwert of shape and the eigenwert of pattern of the color according to above-mentioned the first picture, in selection second picture, meet predetermined image collocation rule and pattern collocation rule, and meet the second picture of above-mentioned clothing classification, arrange in pairs or groups with above-mentioned the first picture.
In embodiments of the present invention, the first picture is the picture of specifying, and needing equipment is that it completes automatic collocation; For different application scenarioss, can there is different application demands, for example: in the time buying clothes, the first picture can obtain by shooting; In the time selecting to wear which kind of clothing, the first picture can be that user specifies in local picture.The mode of obtaining the first picture can have different sources according to different application scenarioss, and the source of the first picture does not affect the realization of the embodiment of the present invention, will not limit this embodiment of the present invention.
In embodiments of the present invention, the identification of image recognition, color, shape recognition, graph image recognizer and color management algorithm that can be based on various maturations, the embodiment of the present invention will not uniqueness limit this.
In embodiments of the present invention, the eigenwert of the shape of the first picture, can represent what clothing classification the clothing in the first picture belongs to, such as: be upper garment, trousers, shoes, skirt, Western-style clothes or ornament etc.Clothing classification can preset as required, and broad classification should comprise: upper garment, trousers, shoes, ornament; But can also continue segmentation, as: upper garment can be Western-style clothes, shirt etc., also can also be in conjunction with, for example: the combination of upper garment and trousers can be included in one-piece dress; The classification of clothing can be set according to the demand of classification by technician, and the embodiment of the present invention is not made uniqueness and limited to this.
In embodiments of the present invention, buying when clothes, the first picture can obtain by shootings, and whether can determine by automatic collocation that user is current has a clothing of collocation with it, the waste of the unnecessary clothing of minimizing purchase; In the time selecting to wear which kind of clothing, the first picture can be that user specifies in local picture, can determine rapidly the current clothing of collocation with it of user by automatic collocation, and minimizing user selects the time of clothing.Application scenarios also has a lot, and the embodiment of the present invention just can realize the automatic collocation of clothing in terminal one side, complete the management to clothing, need not realize by network service, reduces clothing automatic collocation and realizes cost.
Be stored in the second picture of device this locality, and the eigenwert parameter of corresponding second picture, be used for arranging in pairs or groups with the first picture, the procurement process of second picture and characteristic of correspondence value parameter can be as follows: further, as shown in Figure 7, above-mentioned picture acquiring unit 601, also for above-mentioned obtain the first picture that needs the clothing of automatic collocation before, obtain second picture;
Above-mentioned picture recognition unit 602, for above-mentioned second picture is carried out to color identification, shape recognition and image recognition, obtains eigenwert, the eigenwert of shape and the eigenwert of pattern of color;
Above-mentioned classification determining unit 603, for determining the clothing classification under above-mentioned second picture according to the eigenwert of the shape of above-mentioned second picture; Said apparatus also comprises:
Storage unit 701, for storing above-mentioned second picture, and the eigenwert of the color of above-mentioned second picture, the eigenwert of pattern and affiliated clothing classification.
In embodiments of the present invention, second picture can be to concentrate batch input, for example: when the first installation of user can be carried out the application of embodiment of the present invention flow process, concentrate the picture of taking the clothing in own wardrobe, as second picture batch input.The source of second picture can be controlled according to the demand of oneself voluntarily by user, before obtaining second picture, can also show the information of " picture that please take or load own clothes ".
The embodiment of the present invention also provides the specific implementation of how to store second picture and characteristic of correspondence value, facilitate follow-up automatic clothes collocation, be used for improving the matching efficiency of automatic clothes collocation, specific as follows: alternatively, said memory cells 701, for above-mentioned second picture and affiliated clothing classification thereof are stored in to database, the eigenwert of the color of above-mentioned second picture is stored in color libraries, the eigenwert of the pattern of above-mentioned second picture is stored in pattern storehouse;
Above-mentioned picture selected cell 604, be used for eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of above-mentioned the first picture of foundation respectively, to meet predetermined image collocation rule and pattern collocation rule as standard, in above-mentioned color libraries and above-mentioned pattern storehouse, select the second picture of the clothing classification that belongs to above-mentioned needs collocation.
In the time that device carries out automatic clothes collocation, may there is the situation of multiple second pictures, the generation of this situation may be because clothing is a lot, really having the situation of multiple arranging scheme, may be also because of the second picture obtaining respectively according to coupling appropriate level or preset multiple matched rule, and the concrete embodiment of the present invention will not limit, in the situation that there is multiple second picture, situation about how to process can be as follows: further, as shown in Figure 8, said apparatus also comprises:
Picture assembled unit 801, for after second picture is selected, if the second picture of selecting has at least two, each second picture and the first picture that combination is selected respectively obtain the result of arranging in pairs or groups.
In the situation that there is multiple second picture, the embodiment of the present invention can be carried out priority classification to second picture, realizes in embodiments of the present invention by the priority of setting in collocation rule, specific as follows: further, as shown in Figure 9, said apparatus also comprises:
Priority determining unit 901, for after the result that obtains arranging in pairs or groups, determines the priority of each collocation result according to the coupling priority of setting in predetermined image collocation rule and pattern collocation rule.
Be understandable that, occur multiple possibility differences according to second picture, can have the setting means of multiple priorities, for example: can be by setting multiple collocation rule and setting the priority between collocation priority.Therefore above scheme should not be construed as the uniqueness of well-behaved inventive embodiments is limited.
When in embodiments of the present invention the first picture being carried out to Auto-matching for the first time, can carry out above whole flow process, but when Auto-matching, can carry out above whole flow process for the second time, but by the automatic collocation result before record in advance, realize fast automatic collocation, can reduce like this operand, improve collocation efficiency, specific as follows: further, as shown in figure 10, said apparatus also comprises:
Record cell 1001, for after second picture is selected, if receive the confirmation instruction of above-mentioned second picture, records the corresponding relation of above-mentioned second picture and the first picture;
Above-mentioned picture selected cell 604, if when also getting above-mentioned the first picture or second picture and need automatic collocation for above-mentioned picture acquiring unit 601, determine the picture of arranging in pairs or groups with it according to above-mentioned second picture and the corresponding relation of the first picture.
In the present embodiment, second picture needs automatic collocation also can realize by the history collocation result of record, the in the situation that particularly in wardrobe, article being more stable, carried out when repeatedly coupling has recording of a lot of historical collocation, and also can facilitate and obtain accurately comparatively comprehensively arranging scheme.
The embodiment of the present invention also provides another kind of device, as shown in figure 11, comprising: receiver 1101, transmitter 1102, processor 1103 and storer 1104;
Wherein, processor 1103, for controlling execution: obtain the first picture that needs the clothing of automatic collocation; Above-mentioned the first picture is carried out to color identification, shape recognition and image recognition, obtain eigenwert, the eigenwert of shape and the eigenwert of pattern of color; Determine according to the eigenwert of the shape of above-mentioned the first picture the clothing classification that the corresponding clothing of above-mentioned the first picture need to be arranged in pairs or groups; Eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of above-mentioned the first picture of foundation, in selection second picture, meet predetermined image collocation rule and pattern collocation rule, and meet the second picture of above-mentioned clothing classification, arrange in pairs or groups with above-mentioned the first picture.
In embodiments of the present invention, the first picture is the picture of specifying, and needing equipment is that it completes automatic collocation; For different application scenarioss, can there is different application demands, for example: in the time buying clothes, the first picture can obtain by shooting; In the time selecting to wear which kind of clothing, the first picture can be that user specifies in local picture.The mode of obtaining the first picture can have different sources according to different application scenarioss, and the source of the first picture does not affect the realization of the embodiment of the present invention, will not limit this embodiment of the present invention.
In embodiments of the present invention, the identification of image recognition, color, shape recognition, graph image recognizer and color management algorithm that can be based on various maturations, the embodiment of the present invention will not uniqueness limit this.In subsequent embodiment, will describe for example respectively.
In embodiments of the present invention, the eigenwert of the shape of the first picture, can represent what clothing classification the clothing in the first picture belongs to, such as: be upper garment, trousers, shoes, skirt, Western-style clothes or ornament etc.Clothing classification can preset as required, and broad classification should comprise: upper garment, trousers, shoes, ornament; But can also continue segmentation, as: upper garment can be Western-style clothes, shirt etc., also can also be in conjunction with, for example: the combination of upper garment and trousers can be included in one-piece dress; The classification of clothing can be set according to the demand of classification by technician, and the embodiment of the present invention is not made uniqueness and limited to this.
In embodiments of the present invention, buying when clothes, the first picture can obtain by shootings, and whether can determine by automatic collocation that user is current has a clothing of collocation with it, the waste of the unnecessary clothing of minimizing purchase; In the time selecting to wear which kind of clothing, the first picture can be that user specifies in local picture, can determine rapidly the current clothing of collocation with it of user by automatic collocation, and minimizing user selects the time of clothing.Application scenarios also has a lot, and the embodiment of the present invention just can realize the automatic collocation of clothing in terminal one side, complete the management to clothing, need not realize by network service, reduces clothing automatic collocation and realizes cost.
Be stored in the second picture of device this locality, and the eigenwert parameter of corresponding second picture, be used for arranging in pairs or groups with the first picture, the procurement process of second picture and characteristic of correspondence value parameter can be as follows: processor 1103, also for controlling execution: above-mentioned obtain the first picture that needs the clothing of automatic collocation before, obtain second picture, and above-mentioned second picture is carried out to color identification, shape recognition and image recognition, obtain eigenwert, the eigenwert of shape and the eigenwert of pattern of color; Determine the clothing classification under above-mentioned second picture according to the eigenwert of the shape of above-mentioned second picture; Store above-mentioned second picture, and the eigenwert of the color of above-mentioned second picture, the eigenwert of pattern and affiliated clothing classification.
In embodiments of the present invention, second picture can be to concentrate batch input, for example: when the first installation of user can be carried out the application of embodiment of the present invention flow process, concentrate the picture of taking the clothing in own wardrobe, as second picture batch input.The source of second picture can be controlled according to the demand of oneself voluntarily by user, before obtaining second picture, can also show the information of " picture that please take or load own clothes ".
The embodiment of the present invention also provides the specific implementation of how to store second picture and characteristic of correspondence value, facilitate follow-up automatic clothes collocation, be used for improving the matching efficiency of automatic clothes collocation, specific as follows: above-mentioned processor 1103, be used for controlling execution: store above-mentioned second picture, and the eigenwert of the color of above-mentioned second picture, the eigenwert of pattern and affiliated clothing classification comprise:
Above-mentioned second picture and affiliated clothing classification thereof are stored in database, the eigenwert of the color of above-mentioned second picture is stored in color libraries, the eigenwert of the pattern of above-mentioned second picture is stored in pattern storehouse;
Eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of above-mentioned the first picture of above-mentioned foundation, select to meet in second picture predetermined image collocation rule and pattern collocation rule, and the second picture that meets above-mentioned clothing classification comprises:
Eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of above-mentioned the first picture of foundation respectively, to meet predetermined image collocation rule and pattern collocation rule as standard, in above-mentioned color libraries and above-mentioned pattern storehouse, select the second picture of the clothing classification that belongs to above-mentioned needs collocation.
In the time that device carries out automatic clothes collocation, may there is the situation of multiple second pictures, the generation of this situation may be because clothing is a lot, really there is the situation of multiple arranging scheme, also may be because the second picture obtaining respectively according to coupling appropriate level or preset multiple matched rule, the concrete embodiment of the present invention will not limit, in the situation that there is multiple second picture, situation about how to process can be as follows: processor 1103, also for controlling execution: after second picture is selected, if the second picture of selecting has at least two, each second picture and the first picture that combination is selected respectively obtain the result of arranging in pairs or groups.
In the situation that there is multiple second picture, the embodiment of the present invention can be carried out priority classification to second picture, realize by the priority of setting in collocation rule in embodiments of the present invention, specific as follows: processor 1103, also for controlling execution: after the result that obtains arranging in pairs or groups, determine the priority of each collocation result according to the coupling priority of setting in predetermined image collocation rule and pattern collocation rule.
Be understandable that, occur multiple possibility differences according to second picture, can have the setting means of multiple priorities, for example: can be by setting multiple collocation rule and setting the priority between collocation priority.Therefore above scheme should not be construed as the uniqueness of well-behaved inventive embodiments is limited.
When in embodiments of the present invention the first picture being carried out to Auto-matching for the first time, can carry out above whole flow process, but for the second time when Auto-matching, can carry out above whole flow process, but by the automatic collocation result before recording in advance, realize fast automatic collocation, can reduce like this operand, improve collocation efficiency, specific as follows: processor 1103, also for controlling execution: after second picture is selected, if receive the confirmation instruction of above-mentioned second picture, record the corresponding relation of above-mentioned second picture and the first picture; If when getting above-mentioned the first picture or second picture and needing automatic collocation, determine the picture of arranging in pairs or groups with it according to above-mentioned second picture and the corresponding relation of the first picture.
In the present embodiment, second picture needs automatic collocation also can realize by the history collocation result of record, the in the situation that particularly in wardrobe, article being more stable, carried out when repeatedly coupling has recording of a lot of historical collocation, and also can facilitate and obtain accurately comparatively comprehensively arranging scheme.
The embodiment of the present invention also provides another kind of device, as shown in figure 12, for convenience of explanation, only shows the part relevant to the embodiment of the present invention, and concrete ins and outs do not disclose, and please refer to embodiment of the present invention method part.This terminal can be for comprising mobile phone, panel computer, PDA (Personal Digital Assistant, personal digital assistant), POS (Point of Sales, point-of-sale terminal), any device such as vehicle-mounted computer, take terminal as example as mobile phone:
Shown in Figure 12 is the block diagram of the part-structure of the mobile phone that the terminal that provides to the embodiment of the present invention is relevant.With reference to Figure 12, mobile phone comprises: radio frequency (Radio Frequency, RF) parts such as circuit 1210, storer 1220, input block 1230, display unit 1240, sensor 1250, voicefrequency circuit 1260, Wireless Fidelity (wireless fidelity, WiFi) module 1270, processor 1280 and power supply 1290.It will be understood by those skilled in the art that the handset structure shown in Figure 12 does not form the restriction to mobile phone, can comprise the parts more more or less than diagram, or combine some parts, or different parts are arranged.
Below in conjunction with Figure 12, each component parts of mobile phone is carried out to concrete introduction:
RF circuit 1210 can be used for receiving and sending messages or communication process in, the reception of signal and transmission, especially, after the downlink information of base station is received, process to processor 1280; In addition, the up data of design are sent to base station.Conventionally, RF circuit 1210 includes but not limited to antenna, at least one amplifier, transceiver, coupling mechanism, low noise amplifier (Low Noise Amplifier, LNA), diplexer etc.In addition, RF circuit 1210 can also be by radio communication and network and other devices communicatings.Above-mentioned radio communication can be used arbitrary communication standard or agreement, include but not limited to global system for mobile communications (Global System of Mobile communication, GSM), general packet radio service (General Packet Radio Service, GPRS), CDMA (Code Division Multiple Access, CDMA), Wideband Code Division Multiple Access (WCDMA) (Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE), Email, Short Message Service (Short Messaging Service, SMS) etc.
Storer 1220 can be used for storing software program and module, and processor 1280 is stored in software program and the module of storer 1220 by operation, thereby carries out various function application and the data processing of mobile phone.Storer 1220 can mainly comprise storage program district and storage data field, wherein, and the application program (such as sound-playing function, image player function etc.) that storage program district can storage operation system, at least one function is required etc.; The data (such as voice data, phone directory etc.) that create according to the use of mobile phone etc. can be stored in storage data field.In addition, storer 1220 can comprise high-speed random access memory, can also comprise nonvolatile memory, for example at least one disk memory, flush memory device or other volatile solid-state parts.
Input block 1230 can be used for receiving numeral or the character information of input, and generation is inputted with the key signals that user arranges and function control is relevant of mobile phone.Particularly, input block 1230 can comprise contact panel 1231 and other input equipments 1232.Contact panel 1231, also referred to as touch-screen, can collect user or near touch operation (using any applicable object or near the operations of annex on contact panel 1231 or contact panel 1231 such as finger, stylus such as user) thereon, and drive corresponding coupling arrangement according to predefined formula.Optionally, contact panel 1231 can comprise touch detecting apparatus and two parts of touch controller.Wherein, touch detecting apparatus detects user's touch orientation, and detects the signal that touch operation brings, and sends signal to touch controller; Touch controller receives touch information from touch detecting apparatus, and converts it to contact coordinate, then gives processor 1280, and the order that energy receiving processor 1280 is sent is also carried out.In addition, can adopt the polytypes such as resistance-type, condenser type, infrared ray and surface acoustic wave to realize contact panel 1231.Except contact panel 1231, input block 1230 can also comprise other input equipments 1232.Particularly, other input equipments 1232 can include but not limited to one or more in physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse, control lever etc.
Display unit 1240 can be used for showing the information inputted by user or the various menus of the information that offers user and mobile phone.Display unit 1240 can comprise display panel 1241, optionally, can adopt the form such as liquid crystal display (Liquid Crystal Display, LCD), Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED) to configure display panel 1241.Further, contact panel 1231 can cover display panel 1241, when contact panel 1231 detect thereon or near touch operation after, send processor 1280 to determine the type of touch event, corresponding vision output is provided according to the type of touch event with preprocessor 1280 on display panel 1241.Although in Figure 12, contact panel 1231 and display panel 1241 be as two independently parts realize input and the input function of mobile phone, but in certain embodiments, can be by integrated to contact panel 1231 and display panel 1241 and realize the input and output function of mobile phone.
Mobile phone also can comprise at least one sensor 1250, such as optical sensor, motion sensor and other sensors.Particularly, optical sensor can comprise ambient light sensor and proximity transducer, and wherein, ambient light sensor can regulate according to the light and shade of ambient light the brightness of display panel 1241, proximity transducer can, in the time that mobile phone moves in one's ear, cut out display panel 1241 and/or backlight.As the one of motion sensor, accelerometer sensor can detect the size of the acceleration that (is generally three axles) in all directions, when static, can detect size and the direction of gravity, can be used for identifying application (such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as passometer, knock) of mobile phone attitude etc.; As for also other sensors such as configurable gyroscope, barometer, hygrometer, thermometer, infrared ray sensor of mobile phone, do not repeat them here.
Voicefrequency circuit 1260, loudspeaker 1261, microphone 1262 can provide the audio interface between user and mobile phone.Voicefrequency circuit 1260 can, by the electric signal after the voice data conversion receiving, be transferred to loudspeaker 1261, is converted to voice signal output by loudspeaker 1261; On the other hand, the voice signal of collection is converted to electric signal by microphone 1262, after being received by voicefrequency circuit 1260, be converted to voice data, after again voice data output processor 1280 being processed, through RF circuit 1210 to send to such as another mobile phone, or export voice data to storer 1220 so as further process.
WiFi belongs to short range wireless transmission technology, mobile phone by WiFi module 1270 can help that user sends and receive e-mail, browsing page and access streaming video etc., it provides wireless broadband internet access for user.Although Figure 12 shows WiFi module 1270, be understandable that, it does not belong to must forming of mobile phone, completely can be as required in the essential scope that does not change invention and omit.
Processor 1280 is control centers of mobile phone, utilize the various piece of various interface and the whole mobile phone of connection, by moving or carry out the software program and/or the module that are stored in storer 1220, and call the data that are stored in storer 1220, carry out various functions and the deal with data of mobile phone, thereby mobile phone is carried out to integral monitoring.Optionally, processor 1280 can comprise one or more processing units; Preferably, processor 1280 can integrated application processor and modem processor, and wherein, application processor is mainly processed operating system, user interface and application program etc., and modem processor is mainly processed radio communication.Be understandable that, above-mentioned modem processor also can not be integrated in processor 1280.
Mobile phone also comprises the power supply 1290 (such as battery) to all parts power supply, preferably, power supply can be connected with processor 1280 logics by power-supply management system, thereby realizes the functions such as management charging, electric discharge and power managed by power-supply management system.
Although not shown, mobile phone can also comprise camera, bluetooth module etc., does not repeat them here.
In embodiments of the present invention, the included processor 1280 of this terminal also has following functions:
Wherein, processor 1280, for controlling execution: obtain the first picture that needs the clothing of automatic collocation; Above-mentioned the first picture is carried out to color identification, shape recognition and image recognition, obtain eigenwert, the eigenwert of shape and the eigenwert of pattern of color; Determine according to the eigenwert of the shape of above-mentioned the first picture the clothing classification that the corresponding clothing of above-mentioned the first picture need to be arranged in pairs or groups; Eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of above-mentioned the first picture of foundation, in selection second picture, meet predetermined image collocation rule and pattern collocation rule, and meet the second picture of above-mentioned clothing classification, arrange in pairs or groups with above-mentioned the first picture.
In embodiments of the present invention, the first picture is the picture of specifying, and needing equipment is that it completes automatic collocation; For different application scenarioss, can there is different application demands, for example: in the time buying clothes, the first picture can obtain by shooting; In the time selecting to wear which kind of clothing, the first picture can be that user specifies in local picture.The mode of obtaining the first picture can have different sources according to different application scenarioss, and the source of the first picture does not affect the realization of the embodiment of the present invention, will not limit this embodiment of the present invention.
In embodiments of the present invention, the identification of image recognition, color, shape recognition, graph image recognizer and color management algorithm that can be based on various maturations, the embodiment of the present invention will not uniqueness limit this.In subsequent embodiment, will describe for example respectively.
In embodiments of the present invention, the eigenwert of the shape of the first picture, can represent what clothing classification the clothing in the first picture belongs to, such as: be upper garment, trousers, shoes, skirt, Western-style clothes or ornament etc.Clothing classification can preset as required, and broad classification should comprise: upper garment, trousers, shoes, ornament; But can also continue segmentation, as: upper garment can be Western-style clothes, shirt etc., also can also be in conjunction with, for example: the combination of upper garment and trousers can be included in one-piece dress; The classification of clothing can be set according to the demand of classification by technician, and the embodiment of the present invention is not made uniqueness and limited to this.
In embodiments of the present invention, buying when clothes, the first picture can obtain by shootings, and whether can determine by automatic collocation that user is current has a clothing of collocation with it, the waste of the unnecessary clothing of minimizing purchase; In the time selecting to wear which kind of clothing, the first picture can be that user specifies in local picture, can determine rapidly the current clothing of collocation with it of user by automatic collocation, and minimizing user selects the time of clothing.Application scenarios also has a lot, and the embodiment of the present invention just can realize the automatic collocation of clothing in terminal one side, complete the management to clothing, need not realize by network service, reduces clothing automatic collocation and realizes cost.
Be stored in the second picture of device this locality, and the eigenwert parameter of corresponding second picture, be used for arranging in pairs or groups with the first picture, the procurement process of second picture and characteristic of correspondence value parameter can be as follows: processor 1280, also for controlling execution: above-mentioned obtain the first picture that needs the clothing of automatic collocation before, obtain second picture, and above-mentioned second picture is carried out to color identification, shape recognition and image recognition, obtain eigenwert, the eigenwert of shape and the eigenwert of pattern of color; Determine the clothing classification under above-mentioned second picture according to the eigenwert of the shape of above-mentioned second picture; Store above-mentioned second picture, and the eigenwert of the color of above-mentioned second picture, the eigenwert of pattern and affiliated clothing classification.
In embodiments of the present invention, second picture can be to concentrate batch input, for example: when the first installation of user can be carried out the application of embodiment of the present invention flow process, concentrate the picture of taking the clothing in own wardrobe, as second picture batch input.The source of second picture can be controlled according to the demand of oneself voluntarily by user, before obtaining second picture, can also show the information of " picture that please take or load own clothes ".
The embodiment of the present invention also provides the specific implementation of how to store second picture and characteristic of correspondence value, facilitate follow-up automatic clothes collocation, be used for improving the matching efficiency of automatic clothes collocation, specific as follows: above-mentioned processor 1280, be used for controlling execution: store above-mentioned second picture, and the eigenwert of the color of above-mentioned second picture, the eigenwert of pattern and affiliated clothing classification comprise:
Above-mentioned second picture and affiliated clothing classification thereof are stored in database, the eigenwert of the color of above-mentioned second picture is stored in color libraries, the eigenwert of the pattern of above-mentioned second picture is stored in pattern storehouse;
Eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of above-mentioned the first picture of above-mentioned foundation, select to meet in second picture predetermined image collocation rule and pattern collocation rule, and the second picture that meets above-mentioned clothing classification comprises:
Eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of above-mentioned the first picture of foundation respectively, to meet predetermined image collocation rule and pattern collocation rule as standard, in above-mentioned color libraries and above-mentioned pattern storehouse, select the second picture of the clothing classification that belongs to above-mentioned needs collocation.
In the time that device carries out automatic clothes collocation, may there is the situation of multiple second pictures, the generation of this situation may be because clothing is a lot, really there is the situation of multiple arranging scheme, also may be because the second picture obtaining respectively according to coupling appropriate level or preset multiple matched rule, the concrete embodiment of the present invention will not limit, in the situation that there is multiple second picture, situation about how to process can be as follows: processor 1280, also for controlling execution: after second picture is selected, if the second picture of selecting has at least two, each second picture and the first picture that combination is selected respectively obtain the result of arranging in pairs or groups.
In the situation that there is multiple second picture, the embodiment of the present invention can be carried out priority classification to second picture, realize by the priority of setting in collocation rule in embodiments of the present invention, specific as follows: processor 1280, also for controlling execution: after the result that obtains arranging in pairs or groups, determine the priority of each collocation result according to the coupling priority of setting in predetermined image collocation rule and pattern collocation rule.
Be understandable that, occur multiple possibility differences according to second picture, can have the setting means of multiple priorities, for example: can be by setting multiple collocation rule and setting the priority between collocation priority.Therefore above scheme should not be construed as the uniqueness of well-behaved inventive embodiments is limited.
When in embodiments of the present invention the first picture being carried out to Auto-matching for the first time, can carry out above whole flow process, but for the second time when Auto-matching, can carry out above whole flow process, but by the automatic collocation result before recording in advance, realize fast automatic collocation, can reduce like this operand, improve collocation efficiency, specific as follows: processor 1280, also for controlling execution: after second picture is selected, if receive the confirmation instruction of above-mentioned second picture, record the corresponding relation of above-mentioned second picture and the first picture; If when getting above-mentioned the first picture or second picture and needing automatic collocation, determine the picture of arranging in pairs or groups with it according to above-mentioned second picture and the corresponding relation of the first picture.
In the present embodiment, second picture needs automatic collocation also can realize by the history collocation result of record, the in the situation that particularly in wardrobe, article being more stable, carried out when repeatedly coupling has recording of a lot of historical collocation, and also can facilitate and obtain accurately comparatively comprehensively arranging scheme.
Figure 13 is a kind of server architecture schematic diagram that the embodiment of the present invention provides, this server 1300 can because of configuration or performance is different produces larger difference, can comprise one or more central processing units (central processing units, CPU) 1322 (for example, one or more processors) and storer 1332, the storage medium 1330 (for example one or more mass memory units) of one or more storage application programs 1342 or data 1344.Wherein, storer 1332 and storage medium 1330 can be of short duration storage or storage lastingly.The program that is stored in storage medium 1330 can comprise one or more modules (diagram does not mark), and each module can comprise a series of command operatings in server.Further, central processing unit 1322 can be set to communicate by letter with storage medium 1330, carries out a series of command operatings in storage medium 1330 on server 1300.
Server 1300 can also comprise one or more power supplys 1326, one or more wired or wireless network interfaces 1350, one or more IO interface 1358, and/or, one or more operating systems 1341, for example Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc.
The server architecture that in above-described embodiment, the step of embodiment of the method can be based on shown in this Figure 13.
The embodiment of the present invention also provides a kind of system of clothing automatic collocation, as shown in figure 14, comprising: with the terminal 1401 and the server 1402 that can communication mode connect;
The device of any one that wherein, described server 1402 provides for the embodiment of the present invention;
Described terminal 1401, is used to specify for sending specify message to described server 1402 the first picture that needs the clothing of automatic collocation, or, for sending the first picture to described server 1402 and specifying described the first picture to need automatic collocation;
Described server 1402, also for sending to collocation result described terminal 1401.
In embodiments of the present invention, when terminal specifies the situation of the clothing that needs automatic collocation to be shopping at network, the first picture of selecting on the website providing in server one side, then server carries out automatic collocation; In addition, being sent the situation of the first picture by terminal, can be the first picture of taking of user or the first picture of subscriber's local storage, for example: the picture of the own wardrobe that user takes, send to server to need server that arranging scheme is provided, conveniently carry out shopping at network use.
It should be noted that in said apparatus embodiment, included unit is just divided according to function logic, but is not limited to above-mentioned division, as long as can realize corresponding function; In addition, the concrete title of each functional unit also, just for the ease of mutual differentiation, is not limited to protection scope of the present invention.
In addition, one of ordinary skill in the art will appreciate that all or part of step realizing in above-mentioned each embodiment of the method is can carry out the hardware that instruction is relevant by program to complete, corresponding program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium of mentioning can be ROM (read-only memory), disk or CD etc.
These are only preferably embodiment of the present invention; but protection scope of the present invention is not limited to this; any be familiar with those skilled in the art the embodiment of the present invention disclose technical scope in, the variation that can expect easily or replacement, within all should being encompassed in protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claim.

Claims (13)

1. a method for clothing automatic collocation, is characterized in that, comprising:
Obtain the first picture that needs the clothing of automatic collocation; Described the first picture is carried out to color identification, shape recognition and image recognition, obtain eigenwert, the eigenwert of shape and the eigenwert of pattern of color;
Determine according to the eigenwert of the shape of described the first picture the clothing classification that the corresponding clothing of described the first picture need to be arranged in pairs or groups;
Eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of described the first picture of foundation, in selection second picture, meet predetermined image collocation rule and pattern collocation rule, and meet the second picture of described clothing classification, arrange in pairs or groups with described the first picture.
2. method according to claim 1, is characterized in that, described obtain the first picture that needs the clothing of automatic collocation before, described method also comprises:
Obtain second picture, and described second picture is carried out to color identification, shape recognition and image recognition, obtain eigenwert, the eigenwert of shape and the eigenwert of pattern of color;
Determine the clothing classification under described second picture according to the eigenwert of the shape of described second picture;
Store described second picture, and the eigenwert of the color of described second picture, the eigenwert of pattern and affiliated clothing classification.
3. method according to claim 2, is characterized in that, the described second picture of described storage, and the eigenwert of the eigenwert of the color of described second picture, pattern and affiliated clothing classification are stored in and comprise:
Described second picture and affiliated clothing classification thereof are stored in database, the eigenwert of the color of described second picture is stored in color libraries, the eigenwert of the pattern of described second picture is stored in pattern storehouse;
Eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of described the first picture of described foundation, select in second picture, meets predetermined image collocation rule and pattern collocation rule, and the second picture that meets described clothing classification comprises:
Eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of described the first picture of foundation respectively, to meet predetermined image collocation rule and pattern collocation rule as standard, in described color libraries and described pattern storehouse, select the second picture of the clothing classification that belongs to described needs collocation.
4. according to method described in claims 1 to 3 any one, it is characterized in that, after second picture is selected, described method also comprises: if the second picture of selecting has at least two, each second picture and the first picture that combination is selected respectively obtain the result of arranging in pairs or groups.
5. method according to claim 4, is characterized in that, after the result that obtains arranging in pairs or groups, described method also comprises: the priority of determining each collocation result according to the coupling priority of setting in predetermined image collocation rule and pattern collocation rule.
6. according to method described in claims 1 to 3 any one, it is characterized in that, after second picture is selected, described method also comprises:
If receive the confirmation instruction of described second picture, record the corresponding relation of described second picture and the first picture;
If when getting described the first picture or second picture and needing automatic collocation, determine the picture of arranging in pairs or groups with it according to described second picture and the corresponding relation of the first picture.
7. a device for clothing automatic collocation, is characterized in that, comprising:
Picture acquiring unit, for obtaining the first picture that needs the clothing of automatic collocation;
Picture recognition unit, for described the first picture is carried out to color identification, shape recognition and image recognition, obtains eigenwert, the eigenwert of shape and the eigenwert of pattern of color;
Classification determining unit, for the clothing classification of determining that according to the eigenwert of the shape of described the first picture the corresponding clothing of described the first picture need to be arranged in pairs or groups;
Picture selected cell, for eigenwert, the eigenwert of shape and the eigenwert of pattern of the color according to described the first picture, in selection second picture, meet predetermined image collocation rule and pattern collocation rule, and meet the second picture of described clothing classification, arrange in pairs or groups with described the first picture.
8. install according to claim 7, it is characterized in that,
Described picture acquiring unit, also for described obtain the first picture that needs the clothing of automatic collocation before, obtain second picture;
Described picture recognition unit, for described second picture is carried out to color identification, shape recognition and image recognition, obtains eigenwert, the eigenwert of shape and the eigenwert of pattern of color;
Described classification determining unit, for determining the clothing classification under described second picture according to the eigenwert of the shape of described second picture; Described device also comprises:
Storage unit, for storing described second picture, and the eigenwert of the color of described second picture, the eigenwert of pattern and affiliated clothing classification.
9. install according to claim 8, it is characterized in that,
Described storage unit, for described second picture and affiliated clothing classification thereof are stored in to database, is stored in the eigenwert of the color of described second picture in color libraries, and the eigenwert of the pattern of described second picture is stored in pattern storehouse;
Described picture selected cell, be used for eigenwert, the eigenwert of shape and the eigenwert of pattern of the color of described the first picture of foundation respectively, to meet predetermined image collocation rule and pattern collocation rule as standard, in described color libraries and described pattern storehouse, select the second picture of the clothing classification that belongs to described needs collocation.
10. described in claim 7 to 9 any one, install, it is characterized in that, described device also comprises:
Picture assembled unit, for after second picture is selected, if the second picture of selecting has at least two, each second picture and the first picture that combination is selected respectively obtain the result of arranging in pairs or groups.
11. install according to claim 10, it is characterized in that, described device also comprises:
Priority determining unit, for after the result that obtains arranging in pairs or groups, determines the priority of each collocation result according to the coupling priority of setting in predetermined image collocation rule and pattern collocation rule.
12. install described in claim 7 to 9 any one, it is characterized in that, described device also comprises:
Record cell, for after second picture is selected, if receive the confirmation instruction of described second picture, records the corresponding relation of described second picture and the first picture;
Described picture selected cell, if when also getting described the first picture or second picture and need automatic collocation for described picture acquiring unit, determine the picture of arranging in pairs or groups with it according to described second picture and the corresponding relation of the first picture.
The system of 13. 1 kinds of clothing automatic collocations, comprising: with the terminal and the server that can communication mode connect, it is characterized in that,
Described server is the device described in claim 8~12 any one;
Described terminal, is used to specify for sending specify message to described server the first picture that needs the clothing of automatic collocation, or, for sending the first picture to described server and specifying described the first picture to need automatic collocation;
Described server, also for sending to described terminal by collocation result.
CN201410424590.0A 2014-08-26 2014-08-26 A kind of method of clothing automatic collocation, apparatus and system Active CN104200249B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410424590.0A CN104200249B (en) 2014-08-26 2014-08-26 A kind of method of clothing automatic collocation, apparatus and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410424590.0A CN104200249B (en) 2014-08-26 2014-08-26 A kind of method of clothing automatic collocation, apparatus and system

Publications (2)

Publication Number Publication Date
CN104200249A true CN104200249A (en) 2014-12-10
CN104200249B CN104200249B (en) 2017-07-21

Family

ID=52085538

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410424590.0A Active CN104200249B (en) 2014-08-26 2014-08-26 A kind of method of clothing automatic collocation, apparatus and system

Country Status (1)

Country Link
CN (1) CN104200249B (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104821000A (en) * 2015-05-22 2015-08-05 京东方科技集团股份有限公司 Color identification system, color identification method and display device
CN104834524A (en) * 2015-05-04 2015-08-12 小米科技有限责任公司 Information prompting method and device
CN104835062A (en) * 2015-05-04 2015-08-12 小米科技有限责任公司 Apparel and accessory collocation method and collocation apparatus
WO2017012597A1 (en) * 2015-07-23 2017-01-26 青岛海尔洗衣机有限公司 Clothes matching recommendation method and smart terminal
CN106846122A (en) * 2017-02-20 2017-06-13 北京京东尚科信息技术有限公司 Commodity data treating method and apparatus
CN107665238A (en) * 2017-08-24 2018-02-06 北京搜狗科技发展有限公司 Image processing method and device, the device for picture processing
CN110363203A (en) * 2018-04-09 2019-10-22 青岛有屋科技有限公司 A kind of control method and wardrobe system, terminal of Intelligent Selection clothing
CN110859047A (en) * 2018-06-21 2020-03-03 深圳市蚂蚁雄兵物联技术有限公司 Clothing management method and device and intelligent dressing mirror
CN112817437A (en) * 2019-11-15 2021-05-18 苹果公司 Colored visual indicia for variable use
CN113470125A (en) * 2021-07-21 2021-10-01 杭州万事利丝绸文化股份有限公司 Method and system for matching colors of patterns

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1908978A (en) * 2006-08-16 2007-02-07 林�智 Network dress appraisal and collocation system and method
CN101477560A (en) * 2009-02-02 2009-07-08 林�智 Clothing matching system and method based on scheme database
CN103246810A (en) * 2013-05-10 2013-08-14 中国地质大学(武汉) Closet device, closet system, and intelligent match recommending method for closet system based on internet of things
CN103440587A (en) * 2013-08-27 2013-12-11 刘丽君 Personal image designing and product recommendation method based on online shopping
CN103455920A (en) * 2012-05-30 2013-12-18 盛乐信息技术(上海)有限公司 Fitting method and fitting system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1908978A (en) * 2006-08-16 2007-02-07 林�智 Network dress appraisal and collocation system and method
CN101477560A (en) * 2009-02-02 2009-07-08 林�智 Clothing matching system and method based on scheme database
CN103455920A (en) * 2012-05-30 2013-12-18 盛乐信息技术(上海)有限公司 Fitting method and fitting system
CN103246810A (en) * 2013-05-10 2013-08-14 中国地质大学(武汉) Closet device, closet system, and intelligent match recommending method for closet system based on internet of things
CN103440587A (en) * 2013-08-27 2013-12-11 刘丽君 Personal image designing and product recommendation method based on online shopping

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陈起进: "基于图像内容的服装检索与搭配技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 *

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104834524A (en) * 2015-05-04 2015-08-12 小米科技有限责任公司 Information prompting method and device
CN104835062A (en) * 2015-05-04 2015-08-12 小米科技有限责任公司 Apparel and accessory collocation method and collocation apparatus
US10204424B2 (en) 2015-05-22 2019-02-12 Boe Technology Group Co., Ltd. Color identifying system, color identifying method and display device
WO2016188021A1 (en) * 2015-05-22 2016-12-01 京东方科技集团股份有限公司 Color identification system, color identification method, and display device
CN104821000A (en) * 2015-05-22 2015-08-05 京东方科技集团股份有限公司 Color identification system, color identification method and display device
CN106375544B (en) * 2015-07-23 2020-11-06 青岛海尔洗衣机有限公司 Clothing matching recommendation method and intelligent terminal
CN106375544A (en) * 2015-07-23 2017-02-01 青岛海尔洗衣机有限公司 Clothing collocation recommendation method and intelligent terminal
WO2017012597A1 (en) * 2015-07-23 2017-01-26 青岛海尔洗衣机有限公司 Clothes matching recommendation method and smart terminal
CN106846122A (en) * 2017-02-20 2017-06-13 北京京东尚科信息技术有限公司 Commodity data treating method and apparatus
WO2018149237A1 (en) * 2017-02-20 2018-08-23 北京京东尚科信息技术有限公司 Article data processing method and device, and computer readable storage medium
CN107665238A (en) * 2017-08-24 2018-02-06 北京搜狗科技发展有限公司 Image processing method and device, the device for picture processing
CN107665238B (en) * 2017-08-24 2021-10-22 北京搜狗科技发展有限公司 Picture processing method and device for picture processing
CN110363203A (en) * 2018-04-09 2019-10-22 青岛有屋科技有限公司 A kind of control method and wardrobe system, terminal of Intelligent Selection clothing
CN110859047A (en) * 2018-06-21 2020-03-03 深圳市蚂蚁雄兵物联技术有限公司 Clothing management method and device and intelligent dressing mirror
CN112817437A (en) * 2019-11-15 2021-05-18 苹果公司 Colored visual indicia for variable use
CN113470125A (en) * 2021-07-21 2021-10-01 杭州万事利丝绸文化股份有限公司 Method and system for matching colors of patterns
CN113470125B (en) * 2021-07-21 2024-01-12 杭州万事利丝绸文化股份有限公司 Method and system for carrying out color matching on patterns

Also Published As

Publication number Publication date
CN104200249B (en) 2017-07-21

Similar Documents

Publication Publication Date Title
CN104200249A (en) Automatic clothes matching method, device and system
CN111368934B (en) Image recognition model training method, image recognition method and related device
CN108875451B (en) Method, device, storage medium and program product for positioning image
CN106296617B (en) The processing method and processing device of facial image
CN109918975A (en) A kind of processing method of augmented reality, the method for Object identifying and terminal
CN109977859A (en) A kind of map logo method for distinguishing and relevant apparatus
CN111476780A (en) Image detection method and device, electronic equipment and storage medium
CN108259758B (en) Image processing method, image processing apparatus, storage medium, and electronic device
CN107784271B (en) Fingerprint identification method and related product
CN109213732A (en) A kind of method, mobile terminal and computer readable storage medium improving photograph album classification
CN110995810B (en) Object identification method based on artificial intelligence and related device
CN105303149A (en) Figure image display method and apparatus
CN109086680A (en) Image processing method, device, storage medium and electronic equipment
CN110263729A (en) A kind of method of shot boundary detector, model training method and relevant apparatus
CN108170817A (en) Differentiation video acquiring method, device and the readable storage medium storing program for executing of photo main body
CN109376781A (en) A kind of training method, image-recognizing method and the relevant apparatus of image recognition model
CN109063558A (en) A kind of image classification processing method, mobile terminal and computer readable storage medium
CN104598127A (en) Method and device for inserting emoticon in dialogue interface
CN104463105A (en) Guide board recognizing method and device
CN110555171A (en) Information processing method, device, storage medium and system
CN108038431A (en) Image processing method, device, computer equipment and computer-readable recording medium
CN109993234A (en) A kind of unmanned training data classification method, device and electronic equipment
EP4287068A1 (en) Model training method, scene recognition method, and related device
CN111222563A (en) Model training method, data acquisition method and related device
CN107704514A (en) A kind of photo management method, device and computer-readable recording medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
ASS Succession or assignment of patent right

Owner name: TENGXUN SCI-TECH (SHENZHEN) CO., LTD.

Effective date: 20141127

C41 Transfer of patent application or patent right or utility model
TA01 Transfer of patent application right

Effective date of registration: 20141127

Address after: 400065 Chongwen Road, Nan'an District, Chongqing, No. 2

Applicant after: Chongqing University of Posts and Telecommunications

Applicant after: Tencent Technology (Shenzhen) Co., Ltd.

Address before: 400065 Chongwen Road, Nan'an District, Chongqing, No. 2

Applicant before: Chongqing University of Posts and Telecommunications

C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant