偏振图像融合的人脸图像增强研究

Face image enhancement based on polarization image fusion

为提升人脸图像的整体质量,便于人脸图像的快速精准识别与处理,提出了基于偏振图像融合的人脸图像增强方法。首先获得人脸光强图像与偏振度图像,结合小波包变换方法分解和融合两种人脸图像的高、低频信息,实现人脸图像的增强处理。实验结果表明,该方法所获得的人脸增强图像可保留原有图像的低频信息,增强后的人脸图像清晰度高,脸部细节与轮廓特征明显,信息量与反差对比度较高,整体综合质量较好,增强效果较为理想。

In order to improve the overall quality of face image and facilitate the rapid and accurate recognition and processing of face image,a face image enhancement method based on polarization image fusion is proposed.Firstly,the face light intensity image and polarization image are obtained.Combined with the wavelet packet transform method,the high and low frequency information of the two face images are decomposed and fused to realize the enhancement of face image.The experimental results show that the face enhancement image obtained by this method can retain the low-frequency information of the original image.The enhanced face image has high definition,obvious facial details and contour features,high amount of information and contrast contrast,good overall comprehensive quality and ideal enhancement effect.