In-vivo fish sorting by computer vision

An image-processing algorithm, applied to images of common carp (Cyprinus c arpio), St. Peter's fish (Oreochromis sp.) and grey mullet (Mugil cephalus) , successfully discriminated among the species. Fish images were acquired w hile they were swimming in an aquarium with their side to the camera. The a lgorithm was based on the method of moment-invariants (MI) coupled with geo metrical considerations and was, therefore, insensitive to fish size, two-d imensional orientation and location in the camera's field of view. One hund red and forty three images (47 grey mullet, 43 St. Peter's fish and 53 carp images) were acquired and divided into two sets: 20 grey mullet, 20 St. Pe ter's fish and 20 carp images in one set and the rest of the images in the other set. Each of these two sets was used as a training set for selection of feature thresholds, which were then applied to the other set as a test c ase (two-fold cross-validation test). Fish species identification reached 1 00, 91 and 91% for grey mullet, carp and St. Peter's fish, respectively. To the best of our knowledge this is the first report on successful discrimin ation among fish species in vivo. We also report the results of a prelimina ry experiment, conducted to test the capability of fish to be trained to sw im through a narrow Plexiglas channel which could be part of a sorting syst em, and through which fish images could possibly be acquired. (C) 2000 Else vier Science B.V. All rights reserved.