Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image identification method and device

An image recognition and source image technology, which is applied in image analysis, image data processing, character and pattern recognition, etc., can solve problems such as the inability to realize garbage image recognition, and achieve the effect of ensuring effectiveness

Inactive Publication Date: 2009-12-09
ALIBABA GRP HLDG LTD
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The e-commerce system in the prior art can identify the specifications of pictures uploaded by merchants (such as picture size, picture format, etc.), and even convert the pictures into the required specifications, but it is still unable to realize the identification of garbage pictures

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
  • Image identification method and device
  • Image identification method and device
  • Image identification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 Some practical examples of garbage pictures are shown, among which (a) is a store announcement photo, and (b) is a schematic diagram of the clothing size measurement method. These pictures cannot show the appearance of the product. According to the previous description, we think it is a garbage picture. In general, garbage images can be easily seen through artificial means, which shows that garbage images have similar visual characteristics. The technical solution of the present application starts from the visual features, applies image analysis technology, firstly extracts the color features of the image, and then combines predetermined discrimination rules to determine whether the image is a garbage image. The image recognition method of the embodiment of the present application is described below, see figure 2 shown, including the following steps:

[0026] S101, obtaining the color feature value of each pixel in the source image;

[0027] A digital image...

Embodiment 2

[0035] According to the above description, when the main color is black or white, you can continue to make further judgments based on other criteria, see image 3 As shown, the image recognition method of the embodiment of the present application may also include the following steps:

[0036] S104, dividing the source image into several image blocks, and determining the main color of each image block according to the number of pixels corresponding to each color feature value in each image block;

[0037] S105. Identify whether the source image is a garbage image according to the main color of each image block.

[0038] Wherein, the method for determining the main color of the image block is similar to the method for determining the main color of the source image. In the first embodiment, it is judged whether it is a garbage image according to the color characteristics of the entire source image. In this embodiment, by dividing the image block, it can further combine the distr...

Embodiment 3

[0044]The color characteristic value adopted in the present embodiment is RGB value, and the intensity of the three primary colors of R (red), G (green), and B (blue) is divided into 8 equal parts, and the value range of the color characteristic value is RGB000-RGB777. The entire color space is quantized into 512 colors, for example, RGB235 represents a red value of 2, a green value of 3, and a blue value of 5.

[0045] According to the quantification method of the color space mentioned above, in order to facilitate the following description, some special colors are first defined as follows:

[0046] The color with R, G, and B values ​​less than or equal to 1 is black;

[0047] The color with R, G, and B values ​​greater than or equal to 6 is white;

[0048] Among them, black and white can be further divided:

[0049] RGB000 is pure black;

[0050] RGB001, RGB010, RGB011, RGB100, RGB101, RGB110 are dark black;

[0051] RGB666, RGB667, RGB676, RGB766 are dark white; in part...

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 discloses an image identification method and a device. The method comprises the following steps: obtaining the color feature value of each pixel point in a source image; making statistics of the number of pixel points corresponding to the feature value of each type of color and determining the major color of the source image according to the statistical result; and identifying whether the source image is a junk image according to the color feature value corresponding to the major color of the source image. The technical proposal provided by the invention adopts a digital image analysis technology to extract image color feature firstly and then to judge whether the image is a junk image by combining with preset judging rules. The technical proposal can realize automatic differentiation of junk images and non-junk images in an attached drawing so that a system can respectively carry out different processing to ensure the effectiveness of the attached drawing.

Description

technical field [0001] The present application relates to the field of computer applications, in particular to an image recognition method and device. Background technique [0002] The development of multimedia technology has made the forms of expressing information on computers more abundant, which has changed the application fields of computers to a large extent. Among them, images (Images) are widely used media, especially with the development of image processing technology, images have become an important form of information bearing in the field of computers and the Internet. [0003] Taking e-commerce applications as an example, most of the current e-commerce systems support the attached drawing function. When publishing their products online, in addition to providing necessary text descriptions, merchants can also upload one or more pictures of the products. Compared with text, images can display products more intuitively. In many cases, product drawings can also be ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06T7/00G06V30/224G06V10/56
CPCG06K9/4652G06K9/00369G06V40/103G06V10/56
Inventor 贾梦雷
Owner ALIBABA GRP HLDG LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com