ENHANCED EDGE DETECTION TECHNIQUES FOR IDENTIFICATION OF FISH THROUGH ITS MORPHOLOGICAL FEATURESJournal: International Journal of Computer Science and Mobile Computing - IJCSMC (Vol.6, No. 11)
Publication Date: 2017-11-15
Authors : G.T.Shrivakshan;
Page : 48-53
Keywords : Image analysis; Edge detection; Sobel; Prewitt; Roberts; Haar wavelet transformation; Gabor Filter;
In image analysis the Edge detection technique is the most frequently used operations. The edges of the image defined the boundaries and regions of the image. Image of different categories of Fishes like Fresh water fish, Salt water fish, Poisonous Fish, Dangerous fish and all fishes are belongs to different fish family and fish classification in image processing using different filters which are basically based on gradient method like Sobel, Prewitt ,Roberts ,Log Based and Canny edge detector . This paper classifying shark fishes based on image processing using Wavelet Transformation for detecting the edges, specially the two dimensional Haar wavelet transformation of images. The morphological features of various types of sharks compared with the given sample shark that is being identified to which category it belongs to. This paper proposes the enhanced edge detection technology and uses the concept of concurrency to identify the shark image. The body length of the fish is calculated through which the age of the fish is calibrated. The length of the fish is being calculated using edged detection technology. The proposed method uses the edged detection algorithm, Sober Filter and Gabor Filter. Gabor filter for texture, projection segmentation and geometrical shape feature extraction to find the fish's distinctive dark lines that mark the body and tail, through which the age of the fish can be computed. Finally very important problem is taken to understand the fundamental concepts of various filters and apply these filters in identifying a shark fish type which is taken as a case study. The experimentation done in software MATLAB 12.0.
Other Latest Articles
Last modified: 2017-11-30 16:27:21