Method and device for extracting commodity body in commodity picture

A technology in pictures and commodities, applied in the field of the Internet, can solve the problem that the computer cannot obtain the location and coverage of the main body of the commodity.

Active Publication Date: 2014-02-12
ALIBABA GRP HLDG LTD
View PDF8 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in fact, the main body of the product is not necessarily located in the center, and the area occupied by the main body of the product may not be completely covered by

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 and device for extracting commodity body in commodity picture
  • Method and device for extracting commodity body in commodity picture
  • Method and device for extracting commodity body in commodity picture

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0076] Example one:

[0077] Hereinafter, in conjunction with the accompanying drawings, the above method of extracting the main body of the product from the product image will be described in detail. image 3 It is the flow chart of the method for extracting the main body of the product from the product picture provided by this application. As can be seen from the figure, the method includes:

[0078] Step 301: Obtain the saliency of multiple selected regions in the picture corresponding to the picture data;

[0079] In this step, the saliency of multiple selected regions in a picture can be acquired through the existing saliency acquisition method, or through the following Figure 3A Describe the saliency acquisition process to acquire. Figure 3A The saliency acquisition methods shown include:

[0080] Step 3011: Obtain a first probability distribution histogram in the color space of each color in the selected area in the picture corresponding to the picture data;

[0081] Step 3012:...

Example Embodiment

[0121] Example two:

[0122] The following describes in further detail the method of obtaining image quality provided by the embodiments of the present application in conjunction with the accompanying drawings, please refer to Figure 4 , Which provides a flowchart of a method for obtaining image quality for this application. by Figure 4 It can be seen that the method of obtaining the image quality of this kind includes:

[0123] Step 401: Obtain the main body area of ​​a potential product according to the saliency distribution of different selected areas in the picture in the picture;

[0124] In this step, first, in step 4011, the saliency of a plurality of selected regions is obtained; then, in step 4012, the saliency of the plurality of selected regions is normalized to obtain the picture For the saliency distribution of multiple selected regions in the picture, the process can refer to Figure 4A .

[0125] More specifically, in step 4011, all areas in the picture can be scanne...

Example Embodiment

[0177] Example three

[0178] In the following, in conjunction with the accompanying drawings, the aforementioned device for extracting the main body of the product from the product image will be described in more detail. For its structure, please refer Figure 5 The structure diagram shown, such as Figure 5 As shown, the device includes:

[0179] The acquiring unit 501 is configured to acquire the saliency of multiple selected regions in the picture corresponding to the picture data;

[0180] The selection unit 502 is configured to select the center of the selected area with the highest degree of prominence as the center of the potential product main body area;

[0181] The enhancement unit 503 is configured to use the center of the main body area of ​​the potential product as the center of the circle to enhance the salientity of all areas of the picture corresponding to the picture data;

[0182] The selecting unit 504 is configured to select an absolute main area from the main area ...

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 invention relates to a method and device for extracting a commodity body in a commodity picture. The method comprises the steps that significance degrees of a plurality of selected areas of a picture corresponding to picture data are obtained; the center of a selected area with the highest significance degree is selected as the center of potential commodity body areas, the center of the potential commodity body areas is taken a circle center, and the significance degrees of all the areas of the picture corresponding to the picture data are enhanced; according to the enhanced significance degrees, an absolute body area is selected from the potential commodity body areas, and a background area is selected outside the potential commodity body areas; according to the absolute body area and the background area, the commodity body is extracted. Compared with the prior art, the method and device for extracting the commodity body in the commodity picture can obtain the commodity body position in the picture more accurately.

Description

technical field [0001] The present application relates to the field of the Internet, and specifically relates to a method for extracting a product body from a product picture, a method for acquiring picture quality, a device for extracting a product body from a product picture, and a device for acquiring picture quality. Background technique [0002] In the field of e-commerce, such as Yitao, Taobao, Tmall and other websites that provide online product search and online shopping, usually need to provide more product pictures to facilitate consumers to choose. For a picture of a product, merchants often do not have the professional ability to take pictures, so the quality of each picture uploaded is not the same. [0003] However, in e-commerce, the product picture can best reflect the intuitive characteristics of the product, and the main area of ​​the product is the part with the largest amount of information in the product picture. For example, when displaying products an...

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): G06T7/00
Inventor 曹阳
Owner ALIBABA GRP HLDG 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