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

• Published in: Journal of food science Vol. 76; no. 6; pp. E458 - E464
• Main Authors: Mathiassen, John Reidar, Misimi, Ekrem, Toldnes, Bendik, Bondø, Morten, Østvik, Stein Ove
• Format: Journal Article
• Language: English
• Published: Malden, USA Blackwell Publishing Inc 01.08.2011; Wiley; Wiley Subscription Services, Inc
• Subjects: Animals; Belt conveyors; Biological and medical sciences; Body Size; Body Weight; Calibration; Cost Savings; Errors; Fish; Fish and seafood industries; Fishes - growth & development; Food industries; Food processing industry; Food science; Food-Processing Industry - economics; Food-Processing Industry - instrumentation; Food-Processing Industry - methods; Frozen Foods - analysis; Fundamental and applied biological sciences. Psychology; herring; Herrings; High speed; Image Processing, Computer-Assisted; Imaging, Three-Dimensional; laser triangulation; Lasers; Linear Models; linear regression; Machine vision; Mathematical models; Models, Biological; North Sea; Norway; Photography; Seafood - analysis; Seafood - economics; Three dimensional; Time Factors; Two dimensional; Weight; weight estimation; Whole Body Imaging; Norway; North Sea; Edible fish; Linear regression; laser triangulation; Estimation; Weight; machine vision; Vertebrata; Herring; Clupea harengus; Pisces; High speed; Laser; weight estimation
• ISSN: 0022-1147; 1750-3841
• DOI: 10.1111/j.1750-3841.2011.02226.x

:  Weight is an important parameter by which the price of whole herring (Clupea harengus) is determined. Current mechanical weight graders are capable of a high throughput but have a relatively low accuracy. For this reason, there is a need for a more accurate high‐speed weight estimation of whole herring. A 3‐dimensional (3D) machine vision system was developed for high‐speed weight estimation of whole herring. The system uses a 3D laser triangulation system above a conveyor belt moving at a speed of 1000 mm/s. Weight prediction models were developed for several feature sets, and a linear regression model using several 2‐dimensional (2D) and 3D features enabled more accurate weight estimation than using 3D volume only. Using the combined 2D and 3D features, the root mean square error of cross‐validation was 5.6 g, and the worst‐case prediction error, evaluated by cross‐validation, was ±14 g, for a sample (n = 179) of fresh whole herring. The proposed system has the potential to enable high‐speed and accurate weight estimation of whole herring in the processing plants. Practical Application:  The 3D machine vision system presented in this article enables high‐speed and accurate weight estimation of whole herring, thus enabling an increase in profitability for the pelagic primary processors through a more accurate weight grading.