Machine Vision-Based Automatic Raw Fish Handling and Weighing System of Taiwan Tilapia

High‐Speed Weight Estimation of Whole Herring (Clupea harengus) Using 3D Machine Vision

“…Liang and Chiou (2009) presented a system for estimating the weight of Taiwan Tilapia based on linear regression from the view or projected area of the fish. They obtained an R 2 value of 0.9303 for this regression.…”

“…Mathiassen and others (2006) presented a multimodal image acquisition setup, using diffuse reflectance, interactance, and 3D imaging, which would be suitable for simultaneous weight and quality grading of whole herring—although the focus of that research was on the image acquisition setup and not on the weight and quality grading image processing algorithms. Liang and Chiou (2009) presented a system for estimating the weight of Taiwan Tilapia, based on the (view or projected) area of the fish as seen by a machine vision system. Estimation of the weight of Alaskan Pollack has been done based on the (view or projected) area (Balaban and others 2010a).…”

Individual Weight Estimation of Cynoglossus-gracilis Based on Measurement of Irregular Image Area

“…Liang and Chiou captured projected images of Taiwan tilapia and derived relationships of weight-length, weight-height, weight-perimeter and weight-area of 50 samples. The result showed that tilapia's weight was more closely related to its area (R 2 =0.9303) [5]. In another research of 170 herring(C.harengus) by Mathiassen et al, analysis results showed that a similar correlation between area and weight was obviously, with R 2 values of between 0.919 and 0.938 [6].…”