FISH FRESHNESS CLASSIFICATION USING WAVELET TRANSFORMATION AND FUZZY LOGIC TECHNOLOGY

Abstract

Freshness plays a vital role to measure the quality of fish by consumers. The quality of a fish may be affected by characteristic changes deeply which result in a progressive loss of food characteristic in terms of taste and a general concept of quality. The aim of this study is to classify fish freshness based on image processing by using clustering based methods and its features are extracted in the wavelet transformation domain using Haar filter. First and second level decomposition in the wavelet domain is performed and the coefficients obtained at each level have been used as input to fuzzy logic to achieve this objective. There are three types of fuzzy input methods that have been discussed which are Wavelet Mean values divided into 5 parts as per day, Median absolute deviation values are taken as the range of 3 and RGB Mean also has been taken as 3 ranges which are calculated separately. The experimental result indicates better performance based on fuzzy logic in terms of freshness percentage.