Generalized Histogram Equalization Based on Local Characteristics

From time to time, state-of-the-art contrast enhancement algorithms face undesired drawbacks, like loss of tiny details, enhancement of image noise, occasional overenhancement, and unnatural look of the processed images. In this paper, we propose a new approach for contrast enhancement based on localized image analysis. Starting from the commonly used histogram equalization method, we design two measures f1 and f2 to measure local characteristics around each pixel. The global statistics of these two local measures are then recorded into an extended histogram. Based on this extended histogram, we develop a complete procedure to generate the intensity transfer function for contrast enhancement. This approach may not only avoid the enhancement of image noise but also avoid undesired over-enhancement. Experimental results show that the proposed algorithm does provide a flexible and reliable way for contrast enhancement.

• Type: Conference
• Year: 2006
• Where: ICIP
• Authors: Tzu-Cheng Jen, Sheng-Jyh Wang
• Keywords: Histogram Equalization, ICIP 2006, Image Processing