Acceleration of Retinex Algorithm for Image Processing on Android Device Using Renderscript

The popularity and availability of Android devices have motivated researchers to implement their image processing systems on Android mobile platform. Retinex is considered as an effective method to restore the image’s original appearance and used as a pre-processing step in many computer vision applications. It would give a lot of benefits to implement Retinex on such portable system and optimize it for real-time performance. This is a challenge because of limited computational power and memory of the portable system. This paper presents an implementation of rsRetinex, an optimized Retinex algorithm by using Renderscript technique. The experimental results show that rsRetinex could gain up to five times speedup when applied to different image resolution.

[1]  Zia-ur Rahman,et al.  A multiscale retinex for bridging the gap between color images and the human observation of scenes , 1997, IEEE Trans. Image Process..

[2]  John J. McCann,et al.  Retinex in MATLABTM , 2004, J. Electronic Imaging.

[3]  E. Land.  Recent advances in retinex theory , 1986, Vision Research.

[4]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[5]  Yuan-Kai Wang,et al.  Acceleration of an improved Retinex algorithm , 2011, CVPR 2011 WORKSHOPS.

[6]  Zia-ur Rahman,et al.  Multi-scale retinex for color image enhancement , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[7]  Marc Ebner,et al.  Color Constancy , 2007, Computer Vision, A Reference Guide.

[8]  E. Land.  The retinex theory of color vision. , 1977, Scientific American.

[9]  E H Land,et al.  An alternative technique for the computation of the designator in the retinex theory of color vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.