FISH SKIN FRESHNESS LEVEL BY INTEGRATED RGB MULTICOLOUR IMAGE PROCESSING FROM QUALITY INDEX METHOD (QIM) ASSESSMENT

Abstract

The colour of the fish skin is one of the important factors to determine the freshness of a fish. There is potential to use the fish images as an alternative to determine the fish freshness. However, the freshness relationship of the fish skin image to the Red, Green, Blue (RGB) multiple colour channel needs to be elucidated to achieve an accurate interpretation of fish freshness. The objective of this study is to determine the freshness of the fish samples using QIM assessment and to extract the RGB colour value from fish skin images. Finally, to establish the relationship between the QIM scores ranging from 1 (fresh) to 3 (spoiled) and RGB value for freshness indicator using fish images. The effects of temperature, environment, and storage method have been shown to play an important role in determining the rate of deterioration towards the quality and freshness level in fish. From this study, a freshness indicator based on Quality Index Method (QIM) and RGB value for Queenfish and Threadfin was created. Based on the QIM score, Threadfin was easier to deteriorate as compared to Queenfish from its leaner body type properties. Different fish would reflect different freshness reading as Threadfin is in a fresh state when it possesses QIM score of 1 with RGB values range between of 143 to 172. As deterioration progresses, the QIM score is at 3 and the RGB values are ranging from 132 to 161. While Queenfish is found to be in a fresh state when it acquires QIM score of 1 and the RGB values are in the range of 148 to 170. It starts to spoil when the QIM score is at 3 and the RGB values are ranging from 154 to 184.

Keywords

• fish freshness
• freshness detector
• quality index method
• rgb colour processing