Method and device for feature extraction, and method and device for object recognition

A technology for extracting features and objects, applied in the field of image recognition, which can solve the problems of low precision, affecting the accuracy of object recognition, high labeling cost, etc., and achieve the effects of strong classification ability, guarantee of distinction, and improvement of recognition accuracy

Active Publication Date: 2022-02-01
BANMA ZHIXING NETWORK HONGKONG CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the prior art, in the second step, it is necessary to construct a training set to mark the position points of the features to be extracted in the located object, and mark the samples in training one by one according to certain rules, such as specifying the distance between the eyebrows on the left side of the image The leftmost 1 / 6, 1 / 3, 1 / 2, and 2 / 3 of the left eyebrow have a position point to be extracted, which needs to be measured and marked one by one. The cost of marking is extremely high, and the accuracy is not high, which will affect the object. The accuracy of the 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 and device for feature extraction, and method and device for object recognition
  • Method and device for feature extraction, and method and device for object recognition
  • Method and device for feature extraction, and method and device for object recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations as sequential processing, many of the operations may be performed in parallel, concurrently, or simultaneously. In addition, the order of operations can be rearranged. The process may be terminated when its operations are complete, but may also have additional steps not included in the figure. The processing may correspond to a method, function, procedure, subroutine, subroutine, or the like.

[0032] The computer equipment includes user equipment and network equipment. Wherein, the user equipment includes, but is not limited to, computers, smart phones, PDAs, etc.; Or a cloud composed of network servers, among them, cloud computing is a kind of distributed computing, a super virtual computer composed of a group of loosely coupled computer sets. Whe...

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 present application provides a method and device for extracting features, and a method and device for object recognition. The method for extracting features includes: convolving the object image or the feature map obtained by convolving the object image; performing linear transformation on the object image or the result of the feature map convolution; using the linear transformation result as a three-dimensional The input of the deformation model, the output of the three-dimensional deformation model is the position point to be extracted in the object image; according to the position point output by the three-dimensional deformation model, the feature is extracted on the object image or the feature map obtained by convolving the object image. The application reduces the cost of object recognition and improves the efficiency of object recognition.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a method and device for extracting features from an object image, and a method and device for object recognition. Background technique [0002] At present, object recognition technology has been widely used. Objects here refer to objects with stable contours, such as human faces, car license plates, etc. Object recognition is a recognition technology based on object feature information for identification. Taking face recognition as an example, a video camera or camera is used to collect images or video streams containing faces, and automatically track faces in the images or video streams, and then perform facial feature extraction on the tracked faces, and compare them with sample faces. The features of each face in the face set are compared, etc., so as to perform face recognition. [0003] Object recognition is generally divided into four steps: 1) object p...

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 Patents(China)
IPC IPC(8): G06V10/46G06V10/764G06K9/62
CPCG06V10/462G06F18/24
Inventor 易东曹恩华楚汝峰
Owner BANMA ZHIXING NETWORK HONGKONG 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