A rapid, low-cost deep learning system to classify squid species and evaluate freshness based on digital images

Abstract We developed and evaluated a rapid, low-cost system to classify squid in industrial production. This involved designing an easy-to-use handheld image-acquisition system combined with an automated, labor-saving, and efficient deep learning model (named “improved faster recurrent convolutional neural network”) to identify three squid species from the North Pacific Ocean. Three indicators, Accuracy, Intersection-over-Union, and Average Running Time, are used to evaluate the classification, and the average results for the test samples are 85.7%, 80.1%, and 0.144 s, respectively. The proposed network provides better squid classification compared with four other approaches. In addition, to ensure quality, the freshness of the selected squid is also evaluated using global threshold segmentation analysis. This proposed method is demonstrated to be a robust, noninvasive, and high-throughput system for squid classification and can also be expanded to other fine processing of aquatic products.

[1]  Olivier Basset,et al.  Texture image analysis: application to the classification of bovine muscles from meat slice images , 1999 .

[2]  Supapan Chaiprapat,et al.  Development of an Image Processing System in Splendid Squid Grading , 2013 .

[3]  Jenny Lee,et al.  Fully Automated Deep Learning System for Bone Age Assessment , 2017, Journal of Digital Imaging.

[4]  Guang Chen,et al.  Automatic Fish Classification System Using Deep Learning , 2017, 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI).

[5]  Malay Kishore Dutta,et al.  Image processing based technique for classification of fish quality after cypermethrine exposure , 2016 .

[6]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[7]  Ashish Issac,et al.  Image processing based method to assess fish quality and freshness , 2016 .

[8]  Xindong Wu,et al.  Object Detection With Deep Learning: A Review , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Jianrong Li,et al.  Determination of formaldehyde in squid by high-performance liquid chromatography. , 2007, Asia Pacific journal of clinical nutrition.

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Yang Li,et al.  Topic network: topic model with deep learning for image classification , 2015, KSEM.

[12]  Zayde Alçiçek,et al.  Use of polarized light in image analysis: Application to the analysis of fish eye color during storage , 2015 .

[13]  Hyun Myung,et al.  Image-Based Monitoring of Jellyfish Using Deep Learning Architecture , 2016, IEEE Sensors Journal.

[14]  Xinjun Chen,et al.  Identification of three common Loliginidae squid species in the South China Sea by analyzing hard tissues with geometric outline method , 2017, Journal of Ocean University of China.

[15]  Miguel A. Patricio,et al.  A probabilistic, discriminative and distributed system for the recognition of human actions from multiple views , 2012, Neurocomputing.

[16]  Ernestina Casiraghi,et al.  Fish fillet authentication by image analysis , 2018, Journal of Food Engineering.

[17]  Qamar Uz Zaman,et al.  A dual-view computer-vision system for volume and image texture analysis in multiple apple slices drying , 2014 .

[18]  Roberto E. Gonz'alez,et al.  Galaxy detection and identification using deep learning and data augmentation , 2018, Astron. Comput..

[19]  Marcel Salathé,et al.  Using Deep Learning for Image-Based Plant Disease Detection , 2016, Front. Plant Sci..

[20]  L. C. Guan,et al.  The applications of computer vision system and tomographic radar imaging for assessing physical properties of food , 2004 .

[21]  F. Rocha,et al.  A review of reproductive strategies in cephalopods , 2001, Biological reviews of the Cambridge Philosophical Society.

[22]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[23]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Faisal Khan,et al.  Semiparametric PCA and bayesian network based process fault diagnosis technique , 2017 .

[25]  H. Okamura,et al.  Stock assessment of the autumn cohort of neon flying squid (Ommastrephes bartramii) in the North Pacific based on past large-scale high seas driftnet fishery data , 2006 .