Night color image enhancement via statistical law and retinex - Emerging Trends in Image Processing, Computer Vision, and Pattern Recognition - page 208

proposed algorithm can beter recover details, eliminates the “halo efect” and suppress noise.
Moreover, the results of our algorithm look more harmonious and natural.
For a more definite description of the experimental results, this article also uses objective
evaluation criteria to test the effectiveness of our algorithm. We examine our algorithm in
mean value, standard deviation and time-consuming (Computer configuration: CPU: Penti-
um(R) 3.00 GHz; Memory: 3.00 GB; Programming Language: Matlab). The image mean re-
lects the brightness level of the image; the standard deviation reflects the image contrast; the
time-consuming reflects the time complexity of the algorithm. The results are shown in Tables
1 - 4 .

Table 1
Criteria of Assessment of Figure 3

Mean Standard Deviation Time Consuming (s)

Source image 32.290669 37.976650

Michael Elad 74.522833 34.043863 125.203029

MSRCR 122.023486 33.550094 8.073667

proposed algorithm 92.0300 38.6720 1.246996

Table 2
Criteria of Assessment of Figure 4

Mean Standard Deviation Time Consuming (s)

Source image 19.074728 28.879643

Michael Elad 54.979484 32.582415 174.404951

MSRCR 105.600284 41.911008 14.030690

proposed algorithm 87.0683 46.6404 1.724475

Table 3
Criteria of Assessment of Figure 5

Mean Standard Deviation Time Consuming (s)

Source image 42.871070 57.089267

Michael Elad 74.523826 51.653054 177.822975

MSRCR 125.407817 52.732457 11.619577

proposed algorithm 81.8586 61.3861 1.39663