Night color image enhancement via statistical law and retinex - Emerging Trends in Image Processing, Computer Vision, and Pattern Recognition - page 209

Table 4
Criteria of Assessment of Figure 6

Mean Standard Deviation Time Consuming (s)

Source image 43.9788 37.4953

Michael Elad 85.4186 28.9512 177.513603

MSRCR 145.5552 27.6842 13.096727

proposed algorithm 94.7658 32.4271 1.450654

As can be seen in Tables 1 - 6 , in terms of the mean, MSRCR algorithm has the most signiic-
ant effect of improving mean, but the enhanced images are too bright overall to protect details.
Compared with the algorithm of Michael Elad, the proposed algorithm has a beter enhancing
effect of the mean which displays the brightness of the whole picture is consistent with human
visual perception. In terms of standard deviation, the proposed algorithm is better than the
other two algorithms. The proposed algorithm has remarkable enhancement of the image con-
trast and significant effect of image detail recovery. In terms of time consuming, the proposed
algorithm has lower time complexity than the other two algorithms. Moreover, our algorithm
does not need manual control parameters increasing the adaptability of our algorithm.

Table 5
Criteria of Assessment of Figure 7

Mean Standard Deviation Time Consuming (s)

Source image 37.186166 32.700994

Michael Elad 87.693053 47.901984 306.097388

MSRCR 141.732310 45.151938 27.631109

proposed algorithm 101.8945 55.9020 2.418071

Table 6
Criteria of Assessment of Figure 8

Mean Standard Deviation Time Consuming (s)

Source image 19.9751 37.1902

Michael Elad 61.4820 36.6652 163.483256

MSRCR 98.9313 36.8997 14.983709

proposed algorithm 84.8932 43.4253 1.330059