A New Detection Method for Fish Freshness

Fish freshness is an important index of fishes and fish products which indicates their qualities. Rapid detection of fish freshness has very important guiding significance for processing, storage and marketing of fishes and fish products. Aiming at the disadvantages of fish freshness detection techniques at present, a rapid and nondestructive fish freshness detection method was proposed in this paper. We got the statistics features of gray values for eye iris image at first, and then the surface texture features of fish body were obtained and down sampled. Finally, the combined feature vectors by these two features were used to accomplish freshness detection. The method was verified by using carps randomly purchased and the detection accuracy rate got 86.3%. The experimental results show that the proposed method can achieve accurate fish freshness detection rapidly and nondestructively.