基于边缘检测和灰度投影的人眼定位

Eye Localization Method based on Edge Detection and Gray Projection

【目的】针对肤色检测易受光照影响的问题,提出一种基于边缘检测和灰度投影的人眼定位方法。【方法】首先结合肤色检测和Sobel边缘检测来提取人脸主要特征,得到人脸特征的二值化图像;其次根据人眼在人脸的几何位置关系得到人眼的粗定位;然后通过对数变换处理定位后的图片;最后进行水平和垂直方向的灰度投影,经过曲线拟合寻找极值进行人眼瞳孔的精确定位。同时,将本算法与其他类似算法进行比较分析。【结果】本算法对于不同光照和干扰环境有一定的适应性,对于不同姿势的人脸也能准确定位,相对于传统的肤色检测在精准度上有所提升,但在人脸图像受到环境或者噪声干扰严重时,本算法的定位成功率明显降低。【结论】该方法简单实用,对光照和复杂的干扰环境有一定的适应性,并且在一定的角度范围内,具有较高的准确性。

[Objectiveiln eye localization,human skin color is easily affected by light.To solvethis problem well?this paper proposed an eye localization algorithm based on edge detection andgray projection.【Methods】Firstly,the proposed method extracted the main characteristics ofhuman face by jointly using the Sobel edge detection method and the detection of the skin colorto get the binary images of human faces.Secondly?the rough localization was obtained accord-ing to the geometrical positions of human faces.Afterwards?Logarithmic transforming wasused to enhance the contrast of pupils and eyeballs.Finally,gray projection was performed inboth horizontal direction and vertical direction,and the accurate position of the eye pupil waslocated by using curve fitting method to find the extreme value.Meanwhile?the algorithm wascompared with other similar algorithms.[Results】The algorithm which adapts to different lightintensity and complex interference environment can pinpoint the face with pose variation accu-rately.Compared with the traditional skin color detection,the accuracy is improved.But whenthe face image is disturbed seriously by theenvironment or the noise?the localization successrate of this algorithm is obviously reduced.【Conclusion】The experiment results showed thatthe proposed method could be adapted to differ-ent light intensity and complex interference envi-ronment.In a certain angle range?the proposedmethod achieved high accuracy.