Computer vision algorithms for automated channel catfish (Ictalurus punctatus) processing were developed to: (1) detect the orientation of a catfish; 2) identify the head, tail, pectoral, ventral, and dorsal fins of a catfish; and (3) determine cutting lines for deheading, detailing, and definning (dorsal and ventral fins). The algorithms are invariant to translation, rotation, and scaling of a catfish and are robust to noise. They may be applied to most fin fish processing, and are not limited to catfish. Canny edge detection and a labeling and tracking algorithm were applied to locate the boundary of a catfish. A two-stage, model-based, catfish segmentation algorithm was proposed to locate each part of a catfish. A dominant point detection scheme was proposed and applied to find the points that connect each part of a catfish. Then morphological knowledge of the catfish was used to locate the feature points of each part of a catfish and to determine the cutting lines. The angle of the major axis and center of mass were used to represent the orientation of a catfish.
Catfish feature identification via computer vision
Merkmalsidentifikation durch maschinelles Sehen bei Flossenfischen, speziell beim getüpfelten Zwergwels
Transactions of the ASAE ; 39 , 5 ; 1923-1931
1996
9 Seiten, 16 Bilder, 17 Quellen
Article (Journal)
English
Computer vision for music identification
IEEE | 2005
|Mobile computer vision system for hand-based identification
British Library Online Contents | 2015
|Computer Vision and image processing for plant identification
TIBKAT | 1984
|