Fusion Color Information for Image Thresholding Based Wavelet Transform

This paper presents a new global thresholding method based on wavelet fusion of color image sub-bands that we used for image segmentation. At first, a color image has been decomposed three sub-bands that R(red), G(green), B(blue) channel. Second, each sub-bands channel has been decomposed by discrete wavelet transform (DWT) to the same resolution. Third, fusion operation is performed on the transformed images according to some rule. Then all the decomposed sub-bands images are fused that becoming a simple 2-D image. Finally, Ostu’s thresholding methods applied for this 2-D image. Experimental results show that the proposed algorithm yields significantly superior image quality when it is compared to the other well-known algorithms.