Unlock instant, AI-driven research and patent intelligence for your innovation.

Commodity identification method and device based on image segmentation

An image segmentation and recognition method technology, applied in the field of image processing, can solve the problems of product recognition errors, low product recognition accuracy, and large background template interference, and achieve the effect of reducing interference and ensuring recognition speed.

Pending Publication Date: 2022-07-29
GUANGZHOU YOUMI INFORMATION TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, practice has shown that the matching scores of images of the same background and different commodities in the former are no less than those of images of the same commodity and different backgrounds, while the latter is interfered by the background template because it needs to directly extract the features of the entire image To a large extent, when different products correspond to completely consistent image templates, product recognition errors are prone to occur
It can be seen that both of the above-mentioned two product identification methods have the problem of low product identification accuracy

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
  • Commodity identification method and device based on image segmentation
  • Commodity identification method and device based on image segmentation
  • Commodity identification method and device based on image segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0099] see figure 1 , figure 1 It is a schematic flowchart of an image segmentation-based product identification method disclosed in an embodiment of the present invention. in, figure 1 The described method can be applied to a product identification device based on image segmentation, wherein the device can include a server, wherein the server includes a local server or a cloud server, which is not limited in this embodiment of the present invention. like figure 1 As shown, the image segmentation-based product identification method includes the following operations:

[0100] 101. When it is detected that there is an image of a commodity to be identified and a commodity identification operation is required, input the image of the commodity to be identified into a predetermined commodity image subject segmentation model to obtain a target image corresponding to the commodity to be identified in the image of the commodity to be identified .

[0101] In the embodiment of the ...

Embodiment 2

[0155] see figure 2 , figure 2 It is a schematic flowchart of another method for product identification based on image segmentation disclosed in an embodiment of the present invention. in, figure 2 The described method can be applied to a product identification device based on image segmentation, wherein the device can include a server, wherein the server includes a local server or a cloud server, which is not limited in this embodiment of the present invention. like figure 2 As shown, the image segmentation-based product identification method includes the following operations:

[0156] 201. Train an image segmentation model based on a predetermined training sample data set to obtain a commodity image subject segmentation model.

[0157] In the embodiment of the present invention, optionally, the training sample data set includes several training commodity images, each training commodity image is a commodity image whose image background has been segmented, and all trai...

Embodiment 3

[0201] see image 3 , image 3 It is a schematic structural diagram of a product identification device based on image segmentation disclosed in an embodiment of the present invention. in, image 3 The described apparatus may include a server, where the server includes a local server or a cloud server, which is not limited in this embodiment of the present invention. like image 3 As shown, the product identification device based on image segmentation may include:

[0202] The image segmentation module 301 is configured to input the to-be-recognized product image into a pre-determined product image subject segmentation model to obtain the to-be-recognized product image in the to-be-recognized product image when a product identification operation is detected to be present For the corresponding target image, the correlation degree between the target image and the background of the commodity image to be identified is lower than the preset correlation degree threshold.

[0203...

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 a commodity identification method and device based on image segmentation, and the method comprises the steps: inputting a commodity image into a commodity image main body segmentation model to obtain a corresponding target image when it is detected that the commodity image needs to be subjected to the commodity identification operation; inputting the target image into the image feature extraction model to obtain a target feature vector; determining a target existing feature vector matched with the target feature vector according to the target feature vector and each existing feature vector in a commodity image feature library, and determining a commodity identifier of the target existing feature vector according to an image feature-commodity identifier corresponding relation in the commodity image feature library, and taking the result as a commodity identification result of the commodity image. Therefore, the identification speed of the commodity image can be ensured, the interference of the image background on the commodity identification result can be effectively reduced, the accuracy and reliability of the commodity identification result are improved, the accuracy of commodity identification is improved, and the determination efficiency of the commodity identification result is improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, and in particular, to a method and device for product identification based on image segmentation. Background technique [0002] With the rapid development of the e-commerce industry, commodity identification technology plays a vital role. Specifically, the e-commerce platform stores a large amount of commodity image data. Through commodity recognition technology, the e-commerce platform can better manage commodity data, and help advertisers analyze the advertising design of the same type of commodities and discover the potential of different commodities. heat. [0003] At present, the commodity identification methods for commodity images mainly include using target detection technology to detect the position of commodities in commodity images to exclude the interference of large-area background information, or extracting global features of commodity images and extracting global ...

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): G06V10/26G06V10/40G06V10/75G06V10/74G06V10/774G06V10/764G06K9/62
CPCG06F18/22G06F18/241G06F18/214
Inventor 陈畅新钟艺豪
Owner GUANGZHOU YOUMI INFORMATION TECH