Image Quality Evaluation Metric of Brightness Contrast
An image quality evaluation method of brightness contrast is proposed. It is assumed that the change trend of gradual enhancement of an image with a high contrast is different with that of an image with a low contrast; the proposed calculation steps are as follows: First, regarding an image, a series of control parameters of gamma correction (GC) is generated orderly and they are used to implement the GC computation. Second, one reference image is selected from the image set above and the structural similarity (SSIM) method is employed to compute the evaluation results among the selected reference image and each image in the enhanced image set. Third, the control parameters of GC and the computation results of SSIM are used to build a curve. Finally, the Gaussian function is used to fit the curve above and the standard deviation of it is regarded as the brightness contrast metric. Many experiment results have shown the validity of proposed method.
KeywordsImage quality evaluation Brightness contrast Gamma correction SSIM Gaussian function fitting
This work is supported by the National Nature Science Foundation of China under Grant No. 61501016 and the open project of the State Key Laboratory of Intense Pulsed Radiation Simulation and Effect under Grant No. SKLIPR1713.
- 3.Li Y, Wang Z, Dai G, Wu S, Yu S, Xie Y (2017) Evaluation of realistic blurring image quality by using a shallow convolution neural network. In: ICIA, pp 853–857Google Scholar
- 7.Winkler S, Vandergheynst P (1999) Computing isotropic local contrast from oriented pyramid decompositions. ICIP 4:420–424Google Scholar
- 9.Xu G, Su J, Pan H, Zhang Z, Gong H (2009) An image enhancement method based on Gamma correction. In: ISCID, pp 60–63Google Scholar
- 11.Wu C-C, Chang H-T, Tsai S-A, Lin C (2017) Least square fitting of Pollock model for tree detection and crown delineation. In: IGARSS, pp 5802–5805Google Scholar