A Simple Computer Vision Method for Automatic Detection of Melanin Spots in Atlantic Salmon Fillets

Abstract

In this paper, we describe a simple method for automatic detection of melanin spots in Atlantic salmon fillets. Melanin spots are visible dark spots that reduce the quality grade of the fillets. Atlantic salmon processing lines have several operations that involve manual quality evaluation of fillets. One such operation is the inspection of fillets to detect melanin spots. This inspection is labor intensive, and therefore desirable to automate. Two simple computer vision algorithms for melanin spot detection are presented. One algorithm operates on the red channel of RGB images and the second algorithm uses linear discriminant analysis (LDA) on all three RGB channels. A comparison between these two algorithms shows that, for most detection rates, using LDA gives a lower number of false-detections per fillet. We show that the melanin spot detection task can potentially be automated using computer vision.

Quality Grading of Atlantic Salmon (Salmo salar) by Computer Vision

“…White and others (2006), for example, conclude that a decrease of the classification accuracy is to be expected if fish samples from more than 1 location and from different times of the year are included. In this respect, it is realistic to expect that the increase of the data set and inclusion of fish from different seasons, different fish farms, and graded by different quality inspectors may decrease the classification accuracy; however, it is important to observe that classification of whole Atlantic salmon does not need to accomplish a near‐perfect classification in order to be useful for the salmon processing industry (Mathiassen and others 2007).…”

Development and clinical validation of a novel photography‐based skin erythema evaluation system: a comparison with the calculated consensus of dermatologists

“…). Dayglow colour light, which has a colour temperature of 5700 K, was used to differentiate between erythema and pigmentation precisely . To maintain the same environment while taking photographs, the system was designed to minimize ambient lighting interference when a subject's face was in the apparatus.…”

Spectral Imaging as a Tool in Food Research and Quality Monitoring of Food Production

“…However, the aquaculture and fish processing industries are definitely areas where the added information in a spectral image can be exploited to improve the general quality and/or reduce the production cost e.g. assessment of fat and water content distribution in fillets (ElMasry & Wold, 2008), determination of freshness (Chau et al, 2009), detection of nematodes in cod fillets (Wold et al, 2001;Heia et al, 2007) and detection of melanin spots in Atlantic Salmon fillets (Mathiassen et al, 2007). The consumers associate increased intensity of red in salmonid fishes with superior quality, the fish being fresher and having a better flavour (Gormley, 1992;Anderson, 2000).…”