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

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 (IDA) 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.