Method for compensating for gait binary value distortion
A technology of binary image and gait energy image, which is applied in the field of image processing, can solve problems such as loss of detail information, poor key frame quality, and influence, and achieve good recognition effect and eliminate the effect of noise
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2008-08-13
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention belongs to the technical field of image processing, and in particular relates to the processing of the distortion of the binary image of gait, which can be used to make up for the binary image of gait with serious defect of human body information. Background technique
[0002] As a new biometric identification method, gait recognition mainly refers to identifying people through the analysis of people's walking posture. It is different from face recognition, fingerprint recognition, iris recognition and other biometric technologies. The advantages of long-distance recognition and not easy to be concealed have attracted more and more attention from researchers.
[0003] Early medical research shows that there are 24 different components in a person's gait. If these 24 components are taken into account, the gait is unique to the individual. In 1973, Johansson gave a physical psychology experiment in the document "Visual Perception of biolog...
Examples
Embodiment Construction
[0043] With reference to Fig. 2, concrete process of the present invention comprises:
[0044] 1. Preprocessing the gait binary image
[0045] Image preprocessing refers to the process of initial processing of images using some image processing methods. Although the process of image preprocessing is relatively simple, it has a great influence on the result of gait recognition. Taking the image preprocessing of the 352×240 gait binary image shown in Figure 3a as an example, the specific preprocessing operations are as follows:
[0046] (1) Remove the small noise points in the gait binary image and fill the small holes in the gait binary image with the methods of expansion and erosion in morphology;
[0047] (2) Further process some larger noise regions, and some larger noise regions cannot be removed by morphological methods. It is necessary to further process each connected part of the gait binary image after expansion and erosion, that is, the pixel has Mark the parts with...