Face recognition method based on low-illumination self-adaption

A face recognition and self-adaptive technology, applied in the field of image processing, can solve problems such as the impact of face imaging quality, low detection rate of face recognition, and reduced recognition accuracy

Inactive Publication Date: 2019-07-26
HANGZHOU DIANZI UNIV
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In face image acquisition, the lighting environment has a significant impact on the quality of face imaging, especially under low-illumination conditions, face images are easily affected by many factors such as image

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Face recognition method based on low-illumination self-adaption
  • Face recognition method based on low-illumination self-adaption
  • Face recognition method based on low-illumination self-adaption

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The implementation of the technical solutions of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0056] Such as figure 1 with figure 2 Shown, the present invention comprises the steps:

[0057] Step (1) grayscale segmentation of the portrait based on the OTSU algorithm;

[0058] Step (2) carries out adaptive Gamma algorithm correction to the portrait after the segmentation;

[0059] Step (3) evaluates the quality of the corrected portrait;

[0060] Step (4) Adaboost face detection based on Haar-like features is performed on the portrait.

[0061] In step (1), the grayscale segmentation of the portrait is performed based on the OTSU algorithm. The specific implementation steps are as follows:

[0062] Position the input portrait image as a given training data set T for a binary classification:

[0063] T={(x 1 ,y 1 ), (x 2 ,y 2 ),..., (x N ,y N )} (1)

[0064] Among them, each sample point is ...

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

No PUM Login to view more

Abstract

The invention discloses a face recognition method based on low-illumination self-adaption. With popularization and application of face recognition, the requirement of face recognition for recognitionprecision is multiplied, and improvement of recognition accuracy becomes a bottleneck problem of practical application. Due to the fact that under the condition of low illumination, a face image is prone to being influenced by many factors such as image backgrounds, brightness and image noise, the face recognition detection rate is not high and the recognition precision is reduced, and face recognition and application search are restricted. Under the condition, the face image under the low-illumination condition is taken as a sample; a low-illumination adaptive algorithm based on an OTSU segmentation algorithm is innovatively designed. The adaptive low-illumination environment image collection is realized, and the low-illumination face image Adaboost classification detector verifies the low-illumination environment image collection before and after processing, so that the calculation speed of the algorithm is effectively improved, and the face detection accuracy under low illuminationis improved. Verification is performed on a standard face libraries Yale B and CMU-PIE.

Description

technical field [0001] The invention relates to a face recognition method based on low-illuminance self-adaptation, which belongs to the field of image processing and can provide theoretical and technical basis for hot issues such as nighttime security monitoring and complex environment target positioning. Background technique [0002] Face recognition technology has been developed from the development of face recognition and video coding systems in the 1970s, the application of face detection based on image features to principal component analysis (Principal Component Analysis, PCA), probability model, hidden Markov model (Hidden Markov Model, The face change description of HMM), especially the classifier design and training based on neural network (Neural Networks, NN), support vector machine (Support Vector Machine, SVM), and Boosting method, has gradually entered into practical use, but under low illumination However, face recognition accuracy and detection rate have alw...

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
no application Login to view more
IPC IPC(8): G06K9/00G06K9/34G06T7/136G06T5/00G06T7/00
CPCG06T7/136G06T5/007G06T7/0002G06T2207/30168G06V40/172G06V10/267
Inventor 王强杨安宁
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products