Vision System for Quality Assessment of Robotic Cleaning of Fish Processing Plants Using CNN

Abstract

A vision system has been developed for automatic quality assessment of robotic cleaning of fish processing lines. The quality assessment is done by detecting residual fish blood on cleaned surfaces. The system is based on classification using convolutional neural networks (CNNs). The performance of different convolutional neural network architectures and parameters is evaluated. The datasets that simulate various conditions in fish processing plants are generated using data augmentation techniques. Tests using further augmented training data to increase the performance of the neural network are performed, which results in a substantial increase in performance both compared to the color thresholding technique and the same neural network architecture without augmented training data. The performance of the system is validated in experiments in an industrial setting.