A Human Eye Positioning Method Based on Point-by-Point Scanning

Abstract

The invention belongs to the field of image processing and machine vision, and is specifically a point-by-point scanning-based human eye positioning method. Firstly, the grid analysis method is used to determine the human face area, and then the point-by-point scanning method is used to perform human eye positioning in the human face area. eye positioning. The specific positioning steps are as follows, take the image containing the face as the original image, divide the original image into multiple image blocks by grid division, and perform binarization processing on each pixel in all image blocks; in the binarized image Among them, the face area is determined by counting the pixel ratio information of each image block; the obtained face image is grayscaled, and the left and right scanning areas are determined in the grayscale image, and then each pixel is scanned point by point in the left and right scanning areas; By point-by-point scanning comparison, the gray value of the left and right scanning areas is obtained, and the position of the human eye is determined according to the pixel corresponding to the maximum value of the gray value. The invention has the advantage that it is not affected by race, skin color, hair, etc., and can be applied to the field of human eye recognition.

Description

technical field

[0001] The invention belongs to the field of image processing and machine vision, and relates to a human eye positioning method based on point-by-point scanning. Background technique

[0002] In the field of machine vision and image processing, human eye positioning has always been a hot research issue, and it is also one of the key technical issues in the research of driver fatigue monitoring and eye tracking. Human eye positioning mainly studies how to detect and locate human eyes in a given face image. At present, there are many mature human eye positioning algorithms, such as detection methods based on Hough transform, template matching methods, edge feature extraction methods, Geometric feature method, detection method based on AdaBoost classifier, gray integral projection method, etc. Although these methods can achieve human eye positioning under certain conditions, each method has its own advantages and disadvantages. For example, the existing gray-s...

Examples

Embodiment Construction

[0025] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0026] 1. The grid analysis method is used to obtain face images, such as figure 1 shown, including the following steps:

[0027] (a) Read in the original image containing the face, the original image is as figure 1 (a);

[0028] (b) If the image data is a three-dimensional RGB color image, the image needs to be converted into a one-dimensional image through image grayscale processing. The specific method is: according to the importance of the three indicators R, G, and B, the color image R, G, B The three components of G and B are weighted average with different weights. According to the formula f(i,j)=0.30R(i,j)+0.59G(i,j)+0.11B(i,j), the weighted average of the three components of R, G and B can get a more reasonable gray scale image, thus converting the 3D color image into a 1D grayscale image.

[0029] (c) Divide the processed image in...

technical field

[0001] The invention belongs to the field of image processing and machine vision, and relates to a human eye positioning method based on point-by-point scanning. Background technique

[0002] In the field of machine vision and image processing, human eye positioning has always been a hot research issue, and it is also one of the key technical issues in the research of driver fatigue monitoring and eye tracking. Human eye positioning mainly studies how to detect and locate human eyes in a given face image. At present, there are many mature human eye positioning algorithms, such as detection methods based on Hough transform, template matching methods, edge feature extraction methods, Geometric feature method, detection method based on AdaBoost classifier, gray integral projection method, etc. Although these methods can achieve human eye positioning under certain conditions, each method has its own advantages and disadvantages. For example, the existing gray-s...

Examples

Embodiment Construction

[0025] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0026] 1. The grid analysis method is used to obtain face images, such as figure 1 shown, including the following steps:

[0027] (a) Read in the original image containing the face, the original image is as figure 1 (a);

[0028] (b) If the image data is a three-dimensional RGB color image, the image needs to be converted into a one-dimensional image through image grayscale processing. The specific method is: according to the importance of the three indicators R, G, and B, the color image R, G, B The three components of G and B are weighted average with different weights. According to the formula f(i,j)=0.30R(i,j)+0.59G(i,j)+0.11B(i,j), the weighted average of the three components of R, G and B can get a more reasonable gray scale image, thus converting the 3D color image into a 1D grayscale image.

[0029] (c) Divide the processed image in...

Images