An improved fast scanning algorithm based on distance measure and threshold function in region image segmentation

Segmentation is an essential and important process that separates an image into regions that have similar characteristics or features. This will transform the image for a better
image analysis and evaluation. An important benefit of segmentation is the identification
of region of interest in a particular image. Various algorithms have been proposed for
image segmentation and this includes the Fast Scanning algorithm which has been employed on food, sport and medical image segmentation. The clustering process in Fast Scanning algorithm is performed by merging pixels with similar neighbor based on an identified threshold and the use of Euclidean Distance as distance measure. Such an approach leads to a weak reliability and shape matching of the produced segments. Hence, this study proposes an Improved Fast Scanning algorithm that is based on Sorensen distance measure and adaptive threshold function. The proposed adaptive
threshold function is based on the grey value in an image’s pixels and variance. The
proposed Improved Fast Scanning algorithm is realized on two datasets which contains images of cars and nature. Evaluation is made by calculating the Peak Signal to Noise Ratio (PSNR) for the Improved Fast Scanning and standard Fast Scanning algorithm. Experimental results showed that proposed algorithm produced higher PSNR compared to the standard Fast Scanning. Such a result indicate that the proposed Improved Fast Scanning algorithm is useful in image segmentation and later contribute in identifying region of interesting in pattern recognition.