Eye locating method based on improved Adaboost algorithm and human face geometrical characteristics

Abstract

The invention discloses an eye locating method based on an improved Adaboost algorithm and human face geometrical characteristics. The method is characterized by comprising the following steps: respectively training a human face classifier and an eye classifier; utilizing the trained human face classifier to confirm the position of a human face; utilizing the trained eye classifier to confirm the position of a candidate eye area in a part of 2 / 3 of the upper portion of a detected human face area; utilizing the inherent geometrical characteristics, on statistical significance, of a human face to confirm geometrical characteristic coefficients of various groups of eye pairs; confirming respective judging measurement of each group of candidate eye pairs; comparing judging measurements of various candidate eye pairs, wherein the less the judging measurement is, the higher the confidence level of the candidate eye pairs is. Consequently, an optimum group of eye pair can be confirmed, and the optimum position of the eye can be further confirmed. According to the method, the inherent geometrical characteristics of a human face are utilized for further judging searched eye areas, and the optimum position of the eye can be confirmed accurately and effectively.

Description

technical field [0001] The invention relates to an eye positioning method, in particular to an eye positioning method based on an improved Adaboost algorithm and human face geometric features. Background technique [0002] Face recognition has a very broad prospect in security, videophone and human-computer interaction, etc., and the accuracy of eye position directly affects the recognition rate of faces. [0003] Algorithms for eye positioning mainly include the following categories: edge extraction, grayscale projection, region segmentation, and statistical learning (the most representative of which is the Adaboost algorithm). The edge extraction method is to extract the edge of the face image, use the Hough transform to detect the eyeball, and then realize the construction of the eye template, and use a series of functions to determine the position of the eye from the energy point of view; Project the face image in the vertical direction, and then determine the position ...

AI Technical Summary

Problems solved by technology

Although the Adaboost algorithm has faster detection speed and higher detection accuracy, its disadvantage is that it is easily affected by the sample set.

Strong adaptability and robustness are the main performance requirements of the human eye detection algorithm in a single frame image, but the exhaustive search of all target images frame by frame window leads to high computational complexity, so this method is used The main disadvantage is that it takes a lot of time to collect and train samples, especially when selecting non-human eye samples.

Images