Face image illumination compensation method

Abstract

The present invention discloses a face image illumination compensation method. The method comprises the following steps that: step 1, classical retinex illumination compensation is performed on an original image; step 2, edge detection is performed, a pseudo edge is judged by using an equation (13), and a low-illuminance region C (x, y) corresponding to the pseudo edge is marked by using an equation (17); step 3, structural tensors and eigenvalues mu1 and mu2 corresponding to the structural tensors are obtained according to equations (14) and (16); step 4, values are re-assigned to mu1 and mu2, the values obtained in the step 2 and step 3 are introduced into an equation (20); and step 5, the environment function of the Retinex algorithm is improved, illumination processing is performed on the original image, and an illumination-compensated image is obtained by using an equation (5). With the method of the invention adopted, the inadequacies of traditional Retinex and PCNN in eliminating shadows and causing fogging phenomena in illumination compensation can be eliminated, shadows in the image can be diluted to a certain extent, the shadow edges of the image can be eliminated, detail information can be presented, a face recognition rate can be improved, and a face misjudgment rate can be decreased.

Description

technical field [0001] The invention relates to face recognition technology, in particular to a face image illumination compensation method. Background technique [0002] Compared with other biometric identification technologies, face recognition is widely used due to its non-contact nature. With the expansion of its application scope, the application environment of face recognition is becoming more and more complex, especially the face images with uneven illumination. Existing face recognition algorithms have a high success rate for face recognition under normal lighting conditions. However, they cannot meet the needs of applications for face recognition under changing lighting environments. Moreover, with the development of digital technology, the information of collected face images is becoming more and more abundant. For face images with both high light and dark areas where local information cannot be recognized under the environment of changing illumination, many metho...

AI Technical Summary

Problems solved by technology

The above method can improve the overall brightness of the image and restore the detailed information of the shadow area, but there are still some shortcomings: 1) There are many parameters involved, which are not easy to select. If the parameters are not selected properly, the effect will be unsatisfactory; 2) The contrast is not strong and loss some texture detail information, shadow edges cannot be completely eliminated

[0019] For images containing low brightness, high brightness and shadow areas at the same time, the multi-scale Retinex algorithm cannot effectively remove shadow edges

Based on the Retinex algorithm proposed by Ge Wei et al., the transfer function of the gradient domain was introduced into the Retinex algorithm, and an improved adaptive smoothing Retinex algorithm was proposed to highlight the main features of the face; but they only considered the single Diffusion in the same direction, smoothing some useful edge information while smoothing the pseudo edge caused by illumination, and there is a lot of salt and pepper noise in the image; Tang Lei et al. proposed an anisotropy based on center surround for road image shadows Retinex algorithm, this algorithm has a relatively uniform grayscale, only two large blocks of shadow and non-shadow, and achieves admirable results; but for the face, which has many grayscales, rich texture information, and non-rigid objects, this This method is not applicable

Images