Face feature data obtaining system

A face feature and data acquisition technology, applied in the field of face feature data acquisition system, can solve the problems of consuming manpower and material resources, high hardware equipment requirements, large amount of calculation, etc., and achieves good real-time performance, increased computational complexity, Grayscale difference encoding for finer effects

CN104268531AInactive Publication Date: 2015-01-07JIANGSU ZHONGYOU PETROLEUM MACHINERY SCI & TECH CO LTD
3 Cites 5 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2015-01-07
Estimated Expiration
Not applicable · inactive patent

Smart Images

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

Abstract

The invention discloses a face feature data obtaining system. The system comprises a comparison unit, an encoding unit, a calculation unit, a calibration unit and a combination unit, wherein the comparison unit obtains and compares grey values of pixel points and surrounding pixel points of a face image in an image library; the calculation unit is used for calculating grey difference value codes in a local binary pattern so that feature vectors in the horizontal direction and feature vectors in the vertical direction can be obtained. The face feature data obtaining system can well meet requirements of an on-line network system for the calculation speed and the recognition speed of a face recognition algorithm. Besides, grey difference value codes obtained by means of the face feature data obtaining system are more accurate, and the recognition rate is much improved though calculation complexity is not improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of image acquisition and processing, in particular to a facial feature data acquisition system. Background technique

[0002] With the development of information and network technology, face recognition has become an issue of much concern in the field of pattern recognition. It is one of the most challenging research directions in the fields of pattern recognition, image processing and artificial intelligence. It has been widely used in man-machine Interactive systems, security verification systems, identity document verification, and criminal identification. Face recognition includes three main technical links, namely preprocessing, face feature extraction and classifier design. The face feature extraction is to describe and model the face pattern in the original high-dimensional space in the low-dimensional feature space, so as to extract low-dimensional features that are beneficial to classification. Feature ext...

Examples

Embodiment 1

[0030] As an implementation, a face feature data acquisition system includes a comparison unit, a coding unit, a calculation unit, a calibration unit and a combination unit, please refer to the attached figure 1 .

[0031] 1) Comparison unit U1

[0032] Obtain and compare the gray value of each pixel of the face image in the image library and its surrounding pixels;

[0033] 2) Coding unit U2

[0034] Perform probability density statistics on the gray level difference, obtain the cumulative probability distribution of the gray level difference, and calculate the gray level difference according to the cumulative probability distribution of the gray level difference and the number of eigenvector coding digits. to encode;

[0035] 3) Computing unit U3

[0036] It is used to calculate the local binary mode for the gray level difference coding to obtain the feature vector in the horizontal direction and the feature vector in the vertical direction;

[0037] 4) Calibration uni...

Embodiment 2

[0050]As an improved implementation, a facial feature data acquisition system includes a comparison unit, a coding unit, a calculation unit, a calibration unit and a combination unit, and also includes a storage unit. For ease of understanding, please refer to the attached figure 2 .

[0051] 1) Comparison unit U1', which acquires and compares the gray value of each pixel of the face image in the image library and its surrounding pixels;

[0052] 2) Encoding unit U2', which performs probability density statistics on the gray-scale difference, obtains the cumulative probability distribution of the gray-scale difference, and according to the cumulative probability distribution of the gray-scale difference and the number of digits required for the eigenvector encoding Encoding the gray level difference;

[0053] 3) The calculation unit U3' is used to calculate the local binary mode of the gray level difference code to obtain the feature vector in the horizontal direction and t...