Glasses detection method and system for face recognition
A technology for glasses detection and face recognition, which is applied in the field of glasses detection methods and systems for face recognition, can solve the problems of single feature extraction, low classification performance, single classifier, etc., achieve strong stability and discrimination ability, and reduce feature The effect of dimensionality and complexity reduction
Active Publication Date: 2017-09-29
智慧眼科技股份有限公司
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The invention provides a glasses detection method and system for face recognition to solve the technical problems of low classification performance and low reliability caused by single feature extraction and single classifier when the existing glasses detection adopts the pattern recognition method
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0055] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings, but the present invention can be implemented in many different ways defined and covered by the claims.
[0056] A preferred embodiment of the present invention provides a method for detecting glasses for face recognition. The feature classifier used in the method for detecting glasses in this embodiment has the characteristics of low feature dimension, good feature description stability and high classification accuracy. The feature classifier classifies the face images to be tested, and has the characteristics of high computing efficiency and high detection accuracy. refer to figure 1 , the present embodiment glasses detection method comprises:
[0057] Step S101, acquiring an image of the glasses area from the face image to be tested;
[0058] In an optional implementation manner, the step of acquiring an image of the glasses area may include:
[0...
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
Login to View More Abstract
The invention discloses a glasses detection method and system for face recognition. The method comprises: obtaining a glasses area image from a face image to be tested; using a feature classifier to classify the glasses area image to obtain a detection result; The generation of the classifier includes: selecting a predetermined number of segmentation regions from the feature pool as feature selection; extracting features for each sample to select the corresponding feature values of multiple segmentation regions, and combining the feature values of multiple segmentation regions as samples The description; the model of the feature classifier is obtained by training multiple samples through the support vector machine SVM classifier. The feature description of the feature classifier used in the glasses detection method and system of the present invention has strong stability and distinguishing ability, and compared with the feature extraction of the whole image, the feature dimension of classification is greatly reduced, and the complexity of classification operations is also reduced. The detection accuracy has been improved.
Description
technical field [0001] The invention relates to the field of biological pattern recognition, in particular to a method and system for detecting glasses for face recognition. Background technique [0002] Since most people wear glasses, it is of great practical value to improve the performance of face recognition algorithms, face synthesis, and face cartoons by detecting whether glasses are worn in the face image and calculating the position and shape of the glasses. For example, in face recognition, if the position of glasses is detected in a face wearing glasses, a naked face without glasses can be obtained by removing the glasses. [0003] Due to the influence of factors such as the diversity of glasses shapes and image quality, there are many difficulties in glasses detection. Existing glasses detection can be realized by image processing or pattern recognition methods. Image processing methods include edge and color detection, etc. Since the glasses part has obvious hor...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCG06V40/171G06V40/172G06F18/2411
Inventor 孔凡静申意萍
Owner 智慧眼科技股份有限公司