Image-Based Shrimp Length Determination using OpenCV

Abstract

Shrimp species belong to the class of Crustacea under order Decapoda under suborder Natantia. The shrimp species are characterized with semi-transparent body which grow up to more than 20 cm. In terms of economic impact, the shrimp industry is considered highly profitable based on the studies by WorldAtlas and Philippine Statistics Authority. Therefore, as part of the necessary better management principles (BMPs), shrimp growth should be monitored. However, for the shrimp length is typically measured by a manual tool like rulers or calipers which is known to be a tedious process most especially when large number of samples are considered. Hence, in this study, image processing via OpenCV was utilized to estimate the length of shrimp species. The performance of the image-based approach is compared with the manual measurement and yielded a relative percent error of 6.23%. Based on the results, it can be concluded that the image-based approach can be utilized to determine the shrimp length.