Aquaculture America 2024

February 18 - 21, 2024

San Antonio, Texas

A COMPUTER VISION TOOL FOR PRECISE AND RAPID FISH FILLET COLOR CATEGORIZATION

Rakesh Ranjan* ,  Harsh Shroff, Kata Sharrer, Scott Tsukuda, and Christopher Good

 

*The Conservation Fund Freshwater Institute

 1098 Turner Rd, Shepherdstown, WV, 25443

 Email: rranjan@conservationfund.org

 



Fish fillet color plays a crucial role in customer acceptance. Traditional visual fillet color assessments are often labor-intensive, subjective, and lack standardization . Colorimeters  have b een used for meat and fillet color assessments ; however, their accuracy leaves room for improvement as they provide point color measurement and fail to capture the non-uniformity of fillets. Rece nt  computer vision technologies have shown promise in accurately assessing fillet color, but their application is  often limited to algorithm optimization. T his study describes a portable computer vision tool for the rapid and precise  color  profiling of fish fillets. The tool consists of a single-board computer  integrated with  a  red-green-blue (RGB) camera, facilitating data acquisition, onboard image processing, and data visualization. An automated algorithm was developed  and optimized for resource-constrained  edge devices  to segment fish fillets  and  color palettes  on the SalmoFan™ Lineal scale in the field of view of the camera. Various color difference metrics, such as Delta E (CIELAB 1976,  1994,  and  2000), and hue angle were employed to assess the visual disparities in color between color palettes  on the SalmoFan ™ Lineal scale and the fillet. The minimum Delta E and difference of the hue angle were  used  to  rate  fillet color on SalmoFan ™ scale ranging from 20 to 34.  The performance of the tool was validated on  60 fillet portions (2 species × 5 fish/species × 2 fillet/fish × 3 Portions/fillet) obtained from 10 fish (species: Atlantic Salmon and Rainbow Trout) cultured in Recirculating Aquaculture System. The  obtained  fillet color values were compared with the visual ratings provided by three experts. An evaluation of the performance  and accuracy of  the  developed digital tool for  fish fillet color  categorization will be presented.

Keywords: Precision aquaculture,  Internet of  Things (IoT) , Edge computing, Automation ,  Fish processing