SEARCH RESULT

Image Enhancement is a required and indispensable technique in order to improve the image quality of digital images. Much as the digital cameras and mobile phones are available everywhere, lack of clearness on the side textures, emerging of dark or bright areas and creation of noise occurs due to reasons such as failure of camera foci, lack of lighting and atmospheric disturbances. As such, it is necessary and beneficial to develop an effective improvement algorithm in digital images addressing such negative issues and noises. The fundamental function of image improvement is to generate a new density value for each pixel value in the image through utilization of the transformation function after the density value of each pixel of introduction image is received. The proposed conversion function is named Regional Similarity Transfer Function (RSTF) in the study and the conversion is applied by taking into account the density distribution similarity between neighbor pixels. The intuitional optimization technique preferred mostly in engineering applications recently, named Gravitational Search Algorithm (GSA) has been utilized with an eye to optimize the parameter values of the proposed RSTF conversion function (1). An objective evaluation criterion was employed with a view to measure the quality of the images by finding the parameters of the conversion function with GSA. The objective function three performance measures-namely entropy value of images, sum of edge densities and number of edges- of which were combined, was preferred (2). Our experimental results reveal the fact that the proposed method efficiently eliminates the noises received from the images while increasing the image quality.

International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES

Ferzan Katircioglu Zafer Cingiz