A Face Recognition Method Based on Improved Local Two-Dimensional Pattern

A portrait recognition and portrait technology, which is applied in the fields of feature processing, image segmentation, feature matching, and image processing, can solve the problems of high complexity, slow speed, and high computing requirements of portrait recognition, and achieve effective recognition of portraits, speed up recognition, and fast And recognize the effect of portrait
CN109871825BActive Publication Date: 2020-12-22SOUTH CHINA UNIV OF TECH
8 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
SOUTH CHINA UNIV OF TECH
Publication Date
2020-12-22

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a face recognition method based on an improved local two-dimensional mode. According to the method, an improved local two-dimensional mode (LBP) feature is used; LBP feature values representing portrait textures in the image containing the portrait are obtained by carrying out a large number of feature analysis on the textures in the image containing the portrait, and thenthe feature values are compared with the newly obtained portrait image of the same group of people, so that the purpose of recognizing the portrait of the target crowd can be achieved. According to the improved local two-dimensional mode, on the basis of an equivalent mode, threshold processing is conducted on part of parameters to achieve the effect of smoothing a non-edge area. The improved LBPmode contrast equivalent mode provided by the invention is more accurate in distinguishing capability of texture features in portrait recognition.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical fields of image processing, image segmentation, feature processing, feature matching, etc., and specifically relates to a portrait recognition method based on an improved local two-dimensional pattern. Background technique

[0002] Broadly speaking, the face recognition process mainly includes four parts: face detection, image preprocessing, face feature extraction and face discrimination.

[0003] Face detection refers to judging whether there is a human face in any input image or video, and if so, distinguishing the face area from the background, and giving relevant information such as the position and size of the face. It can also detect faces in real-time in a set of image sequences or dynamic videos for face tracking. Face detection is mainly affected by factors such as illumination, noise, pose and occlusion. As the first step of the face recognition system, face detection is directly related to the accura...

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