Sudden Illumination Change Detection and Image Contrast Enhancement
Sudden illumination change is considered as one of crucial issue in many computer and robot vision (CRV) applications. Most CRV algorithms fail when sudden illumination change occurs; therefore, it is essential that images to be detected then the illumination change occurred images need to be enhanced in order to keep the appropriate algorithm processing in real time. We introduce a new method for detecting sudden illumination change efficiently in real time by using local region information and fuzzy logic. The effective way for detecting illumination changes in lighting area and the edge of the area is to analyze the mean and variance of the histogram of each area and in order to reflect the changing trends previous frame’s mean and variance for each area of the histogram is used as an input. The changes of mean and variance make specific patterns when sudden illumination change occurs. Fuzzy rules were defined based on the patterns of the input for detecting illumination changes. Proposed method was tested with different datasets through the evaluation metrics; in particular, the specificity, recall and precision have showed high rates. We also proposed an automatic parameter selection method for contrast limited adaptive histogram equalization method by using entropy of image and adaptive neural fuzzy inference system. The results showed that the contrast of images could be improved. The proposed algorithm is robust to detect both global sudden illumination change and big moving object, and it is also computationally efficient in real time applications.
KeywordsFuzzy Logic Fuzzy Rule Region Information Image Histogram Adaptive Neural Fuzzy Inference System Contrast Limited Adaptive Histogram Equalization
Unable to display preview. Download preview PDF.
- 1.Le, V.H., Mai, Q.H., Lee, C.-H.: Moving Object Detection from Video Sequence Using Optical Flow Estimation and Wavelet Decomposition. In: Proceedings of KIIS Spring Conference 2012, vol. 22(1) (2012)Google Scholar
- 2.Bascle, B., Bernier, O., Lemaire, V.: Learning invariants to illumination changes typical of indoor environments: Application to image color correction. International Journal of Imaging Systems and Technology 17(3) (October 2007)Google Scholar
- 4.Choi, Y.-J., Lee, J.-S., Cho, W.-D.: A Robust Hand Recognition In Varying Illumination. In: Advances in Human-Computer Interaction, ch. 4, pp. 53–70. InTech Education and Publishing (October 2008)Google Scholar
- 5.Bayanmunkh, O., Lee, C.-H.: Sudden Illumination Change Detection Using Local Region Information and Fuzzy Logic. In: Proceedings of KIIS Spring Conference 2013, vol. 23(1) (2013)Google Scholar
- 6.Khusanov, U., Lee, C.-H.: Image Enhancement Based on Local Histogram Specification. Journal of Korean Institute of Intelligent Systems 23(1), 18–23 (2013)Google Scholar
- 7.Kapitanova, K., Son, S.H., Kang, K.-D.: Using fuzzy logic for robust event detection in wireless sensor networkGoogle Scholar
- 8.Jyh-Shing, Jang, R.: Adaptive Network-Based Fuzzy Inference System. IEEE Transactions on Systems, Man, and Cybernetics 23(3) (May/June 1993)Google Scholar
- 9.Patnaik, S., Yang, Y.-M.: Soft Computing Techniques in Vision ScienceGoogle Scholar
- 10.Ritika, R., Kaur, S.: Contrast Enhancement Techniques for Images A Visual Analysis. International Journal of Computer Applications 64(17), 0975–8887 (2013)Google Scholar
- 11.Hou, Z., Yau, W.-Y.: Visible Entropy: A Measure for Image Visibility. In: 2010 International Conference on Pattern Recognition (2010)Google Scholar
- 12.Evaluation metrics, http://www.changedetection.net