Adaptive local constraint-based discriminative dictionary learning algorithm and face recognition system
A local constraint, dictionary learning technology, applied in the field of image recognition, can solve problems such as reducing the classification performance of face recognition systems
Active Publication Date: 2016-11-02
HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
View PDF6 Cites 12 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, face images are easily affected by factors such as illumination, posture, and occlusion. As a result, local features calculated directly using face images may not truly reflect the feature relationship between faces, which reduces the classification of face recognition systems based on dictionary learning. performance
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
[0056] Specific implementation plan
[0057] Hereinafter, the present invention will be further described in detail through specific embodiments in conjunction with the drawings.
[0058] If the dictionary is learned using the k-means algorithm, the dictionary can inherit the structural features in the training sample. According to this idea, consider using the local features of atoms to inherit the structural features of the training samples, and design discriminant constraints to improve the discriminative performance of the dictionary. On this basis, a discriminant dictionary learning algorithm based on adaptive local constraints is designed to improve the classification performance of face recognition. The algorithm steps proposed by the present invention are as follows:
[0059] Step 1: Use atoms to construct a local feature model of the dictionary. Since graphs can effectively represent the relationship between data, graphs can be used to represent the similarity features bet...
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 proposes an adaptive local constraint-based discriminative dictionary learning algorithm. The objective of the invention is to solve problems of a dictionary learning algorithm in face recognition. According to the adaptive local constraint-based discriminative dictionary learning algorithm, atoms are utilized to construct an adaptive laplacian diagram, and the adaptive laplacian diagram is made to keep the local structural features of a dictionary; the row vector of an encoding coefficient matrix and the laplacian diagram of the dictionary are utilized to design a local constraint discriminant term, so that the dictionary has higher discrimination performance; and an adaptive local constraint discriminative dictionary learning-based face recognition model is designed; and therefore, the classification performance of face recognition can be improved. The smooth implementation of the algorithm of the present invention will enrich and develop a constraint-based dictionary learning theoretical system and plays an importable role for the strengthening of dictionary discrimination performance and the improvement of face recognition.
Description
Technical field [0001] The invention relates to the technical field of image recognition, in particular to a discriminative dictionary learning algorithm and a face recognition system. Background technique [0002] The local features of training samples play a very important role in improving the discriminative performance based on dictionary learning. However, face images are susceptible to factors such as illumination, posture, and occlusion. As a result, local features calculated directly from face images may not truly reflect the feature relationship between faces, which reduces the classification of face recognition systems based on dictionary learning. performance. Summary of the invention [0003] The purpose of the present invention is to provide a discriminative dictionary learning algorithm based on adaptive local constraints to solve the problems of the dictionary learning algorithm in face recognition. [0004] In order to achieve the above objectives, the present inve...
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 Applications(China)
IPC IPC(8): G06K9/00
CPCG06V40/172
Inventor 李争名徐勇
Owner HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL