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

Method and device for classifying target object

A technology of target objects and categories, applied in the computer field, can solve the problems of information loss, reduce classification accuracy, loss of texture details, etc., to achieve the effect of improving accuracy and making up for information loss

Active Publication Date: 2021-07-02
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This compression process will lead to information loss, such as the loss of a large amount of texture details, thereby reducing the accuracy of classification

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 classifying target object
  • Method and device for classifying target object
  • Method and device for classifying target object

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The solutions provided in this specification will be described below in conjunction with the accompanying drawings.

[0055] figure 1 It is a schematic diagram of an implementation scenario of an embodiment disclosed in this specification. This implementation scenario involves classifying target objects. refer to figure 1, the target object is a person, a photo containing a portrait, or a statue of a person, etc., wherein the person is a living body, and the photo or statue of a person is not a living body. In face recognition, it is often necessary to detect living body attacks, that is, to perform binary classification on the target object, and the two categories of the binary classification are: the target object is a living body, and the target object is not a living body. In the embodiment of this specification, the client 11 and the server 12 cooperate to realize the classification of the target object. The client 11 first obtains the initial image of the targe...

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 invention provides a method and device for classifying target objects. The method comprises the following steps: a client obtains an initial image of a target object collected by a camera, wherein the initial image has a first resolution; the client obtains a spectrogram corresponding to the initial image through frequency domain transformation; the client compresses the initial image to obtain a compressed image with a second resolution, wherein the second resolution ratio is smaller than the first resolution ratio; and the client sends the spectrogram and the compressed image to a server, so that the server classifies the target object according to the spectrogram and the compressed image. The accuracy of target object classification can be improved.

Description

technical field [0001] One or more embodiments of this specification relate to the computer field, and in particular, to a method and an apparatus for classifying target objects. Background technique [0002] At present, image recognition involves collecting images of target objects and classifying target objects based on the images, which are usually performed jointly by the client and the server. The initial images of the target object collected by the client are generally high-resolution (for example, 1080 or 1920), and considering the processing speed of the entire link, the high-resolution initial image is usually compressed to a low resolution ( For example 224 or 256), upload to the server to classify the target object. This compression process will lead to information loss, such as the loss of a large amount of texture details, thereby reducing the accuracy of classification. [0003] Therefore, it is desirable to have an improved solution that can improve the accu...

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): G06K9/62G06K9/00G06N3/04G06N3/08G06T3/40H04N19/42
CPCG06T3/4092H04N19/42G06N3/08G06V40/172G06N3/045G06F18/24
Inventor 罗嫚刘健郭明宇
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD