Eyebrow Recognition Method Based on Sparse Representation
A recognition method and sparse representation technology, applied in the field of electronic information, can solve problems such as unsatisfactory eyebrow image recognition effects, achieve good scalability, enhance robustness, and improve the recognition rate
Inactive Publication Date: 2015-12-02
BEIJING UNIV OF TECH
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
But they also have shortcomings: the recognition effect is not ideal when the eyebrow image is corroded or polluted
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
[0033] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.
[0034] The hardware devices involved in the present invention include image acquisition devices and computers. The eyebrow image acquired by the image acquisition device is sent to the computer for processing to realize eyebrow recognition. The specific eyebrow recognition program module composition is as attached figure 1 shown.
[0035] The flow chart of the eyebrow recognition method based on sparse representation is as follows figure 2 shown. A kind of eyebrow recognition method based on sparse representation, it is characterized in that comprising the following steps:
[0036] Step 1: Collect p (≥ 2) original eyebrow images for each of M people, segment the pure eyebrow images after grayscale, and normalize them to the same size.
[0037] Step 2, each pure eyebrow image matrix is concatenated by row and transposed into a column vec...
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 belongs to the technical field of electronic information, and discloses an eyebrow recognition method based on sparse representation. The eyebrow recognition method comprises the following steps of: acquiring original eyebrow image; graying the original eyebrow image; splitting to obtain pure eyebrow images; carrying out normalization processing; connecting each pure eyebrow image matrix in rows; connecting and converting into column vectors; calculating the vector mean value; calculating the overall divergence matrix; obtaining the first m characteristic values and the characteristic vectors of the overall divergence matrix C; calculating the volumes of an eyebrow sample and the characteristic vectors; establishing a proximal vector of the eyebrow sample; inputting a testing eyebrow image, and processing the testing eyebrow image to obtain the proximal vector of the testing eyebrow image; calculating the optimal sparse coefficient vector; calculating the difference between the testing eyebrow and the image; and determining the type of the testing eyebrow. By adopting the eyebrow recognition method based on the sparse representation, the recognition rate of the eyebrow can be improved, and the recognition robustness of the image at corrosion and pollution states also can be improved; and in addition, the eyebrow recognition method can be used for recognizing other biological characteristics such as human face, fingerprint and iris, and is high in expansibility.
Description
technical field [0001] The invention belongs to the technical field of electronic information, and in particular relates to an eyebrow recognition method based on sparse representation. Background technique [0002] Eyebrows are an important part of the human face, and relevant literature research shows that the role of eyebrows in human faces is even greater than that of eyes, but eyebrows are still hardly paid attention to in face recognition. In fact, eyebrows have a sharp contour and their features are simple and easy to extract. Compared with the human face, it is less affected by factors such as expression changes and aging; and compared with the iris, it is easier to capture. Although various evidences show that eyebrows have a variety of shapes and have good identity specificity, there are still few researches on purely using eyebrows for identification. [0003] Eyebrow recognition is a new biometric recognition technology that has emerged in recent years, and has...
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): G06K9/00
Inventor 李玉鑑苏萍萍
Owner BEIJING UNIV OF TECH