Revolutionizing Ripeness Detection with Roasted Shima Aji Fish and Deep Learning on Embedded Devices

Naphat Keawpibal, Ajaree Naco, Noppamas Pukkhem

Abstract


Object detection is a fundamental concept in computer vision, which is widely recognized and has numerous applications in various domains, including agriculture, medicine, sports, and the food industry. The detection of ripeness in roasted fish is a particularly challenging task in the food processing industry. This study aims to compare the performance of two deep learning algorithms, YOLOv5s and MobileNetv2-SSD, for detecting the ripeness of roasted shima aji fish. The optimal model is selected for deployment on an embedded device. The dataset for this research comprises 689 images without data augmentation and 944 images with data augmentation of cut-open aji fish. The experimental results demonstrate that the YOLOv5s-DA model achieved the highest accuracy in detecting the ripeness of roasted shima aji fish, which is 98.30% of precision, and took approximately 30 minutes for model creation, outperforming MobileNetv2-SSD. Moreover, a prototype ripeness detection system for roasted shima aji fish is developed using a real-time camera and a Raspberry Pi 4, confirming the practical applicability of the proposed model.

Full Text:

PDF

References


Bunluedaj C., Noranarttragoon P., Boonjorn N, et.al, Stock Assessment of Yellow stripe scad (Selaroides leptolepis (Cuvier, 1833)) in the Gulf of Thailand, Technical Report, 2016.

Yang, G., Feng, W., Jin, J., Lei, Q., Li, X., Gui, G., & Wang, W. (2020, December). Face Mask Recognition System with YOLOV5 Based on Image Recognition. In 2020 IEEE 6th International Conference on Computer and Communications (ICCC) (pp. 1398-1404). IEEE.

Iyer, R., Ringe, P. S., & Bhensdadiya, K. P. (2021). Comparison of YOLOv3, YOLOv5s and MobileNet-SSD V2 for real-time mask detection. Artic. Int. J. Res. Eng. Technol, 8, 1156-1160.

Karthi, M., Muthulakshmi, V., Priscilla, R., Praveen, P., & Vanisri, K. (2021, September). Evolution of yolo-v5 algorithm for object detection: automated detection of library books and performace validation of dataset. In 2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES) (pp. 1-6). IEEE.

Redmon, J., and Ali F. (2018). "Yolov3: An incremental improvement." arXiv preprint arXiv:1804.02767.

Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.

Jocher, G., Stoken, A., Borovec, J., Changyu, L., & Hogan, A. (2020). ultralytics/yolov5: v3. 0. Zenodo.

Everingham, M., Eslami, S. A., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. International journal of computer vision, 111, 98-136.

Lin, T.Y.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Dollár, P.; Zitnick, C.L. Microsoft coco: Common objects in context. In Proceedings of the 13th European Conference on Computer Cision (ECCV 2014), Zurich, Switzerland, 6–12 September 2014; pp. 740–755.

Chiu, Yu-Chen, et al. "Mobilenet-SSDv2: An improved object detection model for embedded systems." 2020 International Conference on System Science and Engineering (ICSSE). IEEE, 2020.

Pattansarn, N., & Sriwiboon, N. (2020). Image processing for classifying the quality of the Chok-Anan mango by simulating the human vision using deep learning. Journal of Information Science and Technology, 10(1), 24-29.

Hongboonmee, N., & Jantawong, N. (2020). Apply of Deep Learning Techniques to Measure the Sweetness Level of Watermelon via Smartphone. Journal of Information Science and Technology, 10(2), 59-69.

Ashtiani, S. H. M., Javanmardi, S., Jahanbanifard, M., Martynenko, A., & Verbeek, F. J. (2021). Detection of mulberry ripeness stages using deep learning models. IEEE Access, 9, 100380-100394.

M. Zhou, J. Zhu and X. Li, "Safety helmet detection system of smart construction site based on YOLOv5S," 2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP), Xi'an, China, 2022, pp. 1223-1228, doi: 10.1109/ICSP54964.2022.9778524.

Z. Wu et al., "Using YOLOv5 for Garbage Classification," 2021 4th International Conference on Pattern Recognition and Artificial Intelligence (PRAI), Yibin, China, 2021, pp. 35-38, doi: 10.1109/PRAI53619.2021.9550790.

F. Muding, A. Moolman and N. Keawpibal. Real-time Wearing Face Mask Detection with Deep Learning Algorithm. In: The 13th National Science Research Conference. Phatthalung, Thailand, 12 – 13 May 2022, pp. 847-856.


Refbacks

  • There are currently no refbacks.