Behzad Behzadi; Ali Mohammad Borghei; Arjang Javadi; Saeid Minaei; Morteza Almassi
Abstract
Study on biometric parameters of trout species in the traditional method (based on human and non-automatic factors) are low-efficient due to serious problems such as disease transmission, stress-induced death, inaccuracy, & time-consuming. To overcome the problems of traditional method, an image-based ...
Read More
Study on biometric parameters of trout species in the traditional method (based on human and non-automatic factors) are low-efficient due to serious problems such as disease transmission, stress-induced death, inaccuracy, & time-consuming. To overcome the problems of traditional method, an image-based vision system, including imaging and lighting chambers, was developed in this research. The fish biometric parameters were measured using fish movement videography during passage from the dark chamber. Then the selected images from the video were processed. The length, surface area, weight, amount of food consumed, & growth rate of trout were measured under fully controlled conditions and used as comparison criteria (control). Six mathematical models were used to estimate fish weight through measured parameters and among them the weight/length model was used as the best model for estimating fish weight. The accuracy of the system in estimating fish biometric parameters was above than 90% and the system’s capability to estimate the fish required food during the growth process was 98%.