Evaluation of Gabor Filter Parameters for Image Enhancement and Segmentation
Devendra Kumar Somwanshi, Abhay Krishan · 2009
Abstract— This work provides the knowledge about the working of Gabor filters for ten different types of images. A comparative study is based on the output of the noisy and the filtered images using Gabor filter. This process of getting the noisy images is based on three types of images: Gaussian, Poisson and Speckle. Finally an algorithm is developed that performs all the filtering techniques on the input image and the statistical parameters are calculated as per the comparison between output and input images. These statistical parameters are displayed graphically and they are compared for both the noisy and the filtered images. For the evaluation of the performance of Gabor filters statistical parameters like signal to noise ratio, correlation coefficient and Structure similarity are used and the MATLAB codes required in calculating these parameters are developed. These parameters are used to calculate the image quality of the output image obtained from Gabor filter, based on the values of these parameters the results of all the output images is discussed