Seyed Mehran Kazemi - Computer Engineering and IT Department, Amirkabir University of Technology
Bahare Fatemi - Computer Engineering and IT Department, Amirkabir University of Technology
Ehsan Khademi - Computer Engineering and IT Department, Amirkabir University of Technology

Image color reduction is the act of reducing the number of colors in an image, while preserving its quality. Even though nowadays almost all displays handle 24-bit graphics efficiently, reducing the number of colors in an image is still of great importance in many applications. It can simplify image compression, analysis and segmentation and also it can decrease the memory and bandwidth requirements. In this paper, local beam search has been used to find the optimum palette for reducing the number of colors in an image. First, the best number of initial states for local beam search has been determined, and then, the performance of this method has been compared to other approaches applied to this problem. Obtained results show that this method has a better performance in comparison with other well-known methods for image color reduction.

Image color reduction, Local beam search, Optimum Palette