Method for identifying clothes image, and labeling method and device of clothes image

A technology of clothing and pictures, which is applied in the field of picture recognition, can solve the problems of reducing recognition accuracy and precision, and recognition results are not equal, and achieve the effect of reducing interference and improving accuracy and precision

Active Publication Date: 2016-04-06
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF3 Cites 51 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the overall picture often contains the background picture, and the clothing picture only accounts for a part of the whole picture, when performing feature information recognition

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for identifying clothes image, and labeling method and device of clothes image
  • Method for identifying clothes image, and labeling method and device of clothes image
  • Method for identifying clothes image, and labeling method and device of clothes image

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0060] Example one

[0061] figure 1 It is a schematic flowchart showing a method for labeling clothing pictures in an exemplary embodiment of the present invention. For example, by Image 6 The device shown executes the method for labeling the clothing picture.

[0062] Reference figure 1 , In step S110, a clothing picture is obtained.

[0063] Specifically, the clothing picture may be a clothing picture obtained by a user by taking a picture, or may be a clothing picture on the Internet or on various storage media.

[0064] In step S120, the information of the clothing wearing area in the clothing picture is obtained according to the clothing classification model established in advance as described above.

[0065] As mentioned above, the clothing wearing areas classified by the clothing classification model may include, but are not limited to, tops, bottoms, upper and lower split full-body clothing, and one-piece clothing.

[0066] Optionally, the clothing classification model is a cl...

Example Embodiment

[0078] Example two

[0079] image 3 It is a schematic flowchart showing a method for recognizing clothing pictures according to an exemplary embodiment of the present invention. For example, by Figure 5 The device shown executes the method of recognizing clothing pictures.

[0080] Reference image 3 In step S310, a clothing picture marked with positioning key points and clothing wearing areas as described above is obtained.

[0081] The positioning key point may be the aforementioned first positioning key point or the second positioning key point.

[0082] In step S320, extract at least one picture area representing a characteristic area in the clothing picture according to the clothing wearing area and the location of the positioning key point.

[0083] Optionally, the characteristic area may include, but is not limited to, at least one of an upper body area, a lower body area, a whole body area, a collar area, a chest area, and a sleeve area.

[0084] Specifically, the characterist...

Example Embodiment

[0096] Example three

[0097] Figure 5 It is a schematic diagram showing the structure of an apparatus for recognizing clothing pictures in an exemplary embodiment of the present invention.

[0098] Reference Figure 5 The apparatus for identifying clothing pictures in the embodiment of the present invention may include: a first clothing picture acquiring unit 510, an area picture extracting unit 520, and a feature information acquiring unit 530.

[0099] The first clothing picture acquiring unit 510 is configured to acquire clothing pictures marked with positioning key points and clothing wearing areas.

[0100] The area picture extraction unit 520 is configured to extract at least one picture area representing a characteristic area in the clothing picture according to the clothing wearing area and the position of the positioning key point.

[0101] The feature information obtaining unit 530 is configured to obtain feature information representing the feature region according to the r...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the present invention provides a method for identifying a clothes image, and a labeling method and device of the clothes image. The method for identifying a clothes image comprises a step of obtaining clothes images which are labelled with positioning key points and clothes wearing areas, a step of extracting an image area which represents a feature region in at least one of the clothes images according to the positions of the clothes wearing areas and the positioning key points, and a step of obtaining feature information which represents the feature region according to the region feature identification model corresponding to the feature region. Through labeling the positioning key points, the image which expresses clothes content in the clothes images is positioned, and the interference of background content in the clothes images is reduced. On the above basis, the image area which represents the feature region are extracted from the clothes images according to the clothes wearing areas and the labelled positioning key points, then the feature information of the feature region is obtained according to the corresponding region feature identification model, and thus the accuracy and precision of the feature information of the clothes in the clothes images are improved.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a method for identifying images of clothing, a method and a device for labeling images of clothing. Background technique [0002] Heart of beauty in everyone. Studies have shown that 55% of the first impression each of us makes on others depends on how we dress. Therefore, dressing up plays a very important role in our daily life. However, if the feature information of the clothing (such as clothing category, clothing color, etc.) can be known in advance when choosing the clothing to wear, it will be beneficial to choose clothing that suits you or you like. [0003] In the prior art, when identifying the feature information of the clothing, the feature information is identified for the overall picture including the picture of the clothing. Since the overall picture often contains the background picture, and the clothing picture only accounts for a part of the...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/32G06K9/62G06V10/25G06V10/764
CPCG06V10/242G06F18/24G06T7/73G06V10/255G06V10/454G06V10/25G06V10/82G06V10/764G06T7/10G06T7/70
Inventor 孟骧龙刘国翌韩树民严灿祥杜宇宁
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap