Parasite classification in copro images with transfer learning and data augmentation
DOI:
https://doi.org/10.32870/recibe.v10i2.235Keywords:
Parasite Classification, Data Augmentation, Transfer Learning, GAN, AlexNetAbstract
Humans can harbor parasites; hence, it is fundamental an early detection to prevent diseases. Parasites can be observed in microscopic images, and computer vision may be a helpful approach to detect and classify those parasites in digital images. Deep learning models have shown to have a high performance in image classification. Therefore, this article presents various multi-class deep learning classifiers to recognize 8 classes: 7 types of parasites and non-parasite class. The designed classifiers are based on transfer learning from an AlexNet modified architecture. By having a reduce amount of parasite images samples, a data augmentation was done, employing traditional methods and images generation with an adversarial neural network (GAN) designed for this purpose. The classifier with best performance presented a 99.94%, 98.97% and 98.18% accuracy in the for training, validation and testing sets, respectively.References
Bharadwaj A. y Sujitha D. (2019). Transfer Learning with ResNet-50 for Malaria Cell-Image Classification. 2019 International Conference on Communication and Signal Processing (ICCSP), 946-949. DOI: 10.1109/ICCSP.2019.8697909
Chain E., Fang W., Miang Y y Tian J., (2021). Computer vision approaches for detecting missing barricades. Automation in Construction, 131, 103852. https://doi.org/10.1016/j.autcon.2021.103862
Chakradeo K., Delves M. y Titarenko S., (2019). Malaria Parasite Detection Using Deep Learning Methods. 2019 International Conference on Communication and Signal Processing (ICCSP), 15(2), 175-182. https://doi.org/10.1016/j.jns.2017.08.946
Goodfellow I., Pouget-Abadie J., Mirza M., Xu B., Warde-Farley D., Ozair S, Courville A. y Bengio Y., (2014). Generative adversarial networks. Advances in neural information processing systems, 27, 2672–2680.
Huq A. y Pervin T., (2020). Robust Deep Neural Network Model for Identification of Malaria Parasites in Cell Images. 2020 IEEE Region 10 Symposium (TENSYMP), 1456-1459, https://doi.org/10.1109/TENSYMP50017.2020.9230832.
Krizhevsky A. Sutskever I. y Hinton G., (2012). ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, 1097-1105.
Meda K., Milla S. y Rostad B., (2021). Artificial intelligence research within reach: an object detection model to identify rickets on pediatric wrist radiographs, Pediatric Radiology, 51, 782-791. https://doi.org/ 10.1007/s00247-020-04895-8
Nakasi R., Aliija E. y Nakatumba J., (2021). A Poster on Intestinal Parasite Detection in Stool Sample Using AlexNet and GoogleNet Architectures, ACM SIGCAS Conference on Computing and ustainable Societies (COMPASS), 389-395. https://doi.org/10.1145/3460112.3472309
OMS (2 de marzo 2020). Helmintiasis transmitidas por el suelo. https://www.who.int/es/news-room/fact-sheets/detail/soil-transmitted-helminth-infections
Pan S. y Yang Q., (2009). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering. 22(10), 1345-1359. https://doi.org/ 10.1109/TKDE.2009.191
Prakash R. y Chithaluru P., (2020). Active Security by Implementing Intrusion Detection and Facial Recognition. Nanoelectronics, Circuits and Communication Systems, 692, 1-7. https://doi.org/10.1007/978-981-15-7486-3_1
Radford A. y Metz L., (2015). Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. arVix Preprint.
Shah D., Kawale K., Shah M., Randive S. y Mapari R., (2020). Malaria Parasite Detection Using Deep Learning. 2020 4th Proceedings of the International Conference on Intelligent Computing and Control Systems (ICICCS), 984-988. https://doi.org/10.1109/ICICCS48265.2020.9121073
Shorten C. y Khoshgoftaar T., (2019). A survey on Data Augmentation for Deep Learning. Journal of Big Data, 6(60), 1-48. https://doi.org/10.1186/s40537-019-0197-0
Shorten C., Maqsood A., Shahid M., Hassan M. y Grzegorzek M., (2021). Deep Malaria Parasite Detection in Thin Blood Smear Microscopic Images. Applied Sciences, 11(5), 2284. https://doi.org/10.3390/app11052284
Song C., Wang C. y Yang Y., (2020). Automatic Detection and Image Recognition of Precision Agriculture for Citrus Diseases. 2020 IEEE Eurasia Conference on OIT, Communication and Engineering (ECICE), 187-190. https://doi.org/10.1109/ECICE50847.2020.9301932
Suriva M., Chandran V. y Sumithra M., (2019). Enhanced deep convolutional neural network for malaria parasite classification. International Journal of Computers and Applications, 1-10. https://doi.org/10.1080/1206212X.2019.1672277
Var E. y Boray F., (2018). Malaria Parasite Detection with Deep Transfer Learning. 2018 3rd International conference on computer science and engineering (UBMK), 298-302. https://doi.org/10.1109/UBMK.2018.8566549
Weiss K., Khoshgoftaar T. y Wang D., (2016). A survey of transfer learning. Journal of Big Data. 3(9), 1-40. https://doi.org/10.1186/s40537-016-0043-6
Zhuang F., Qi Z., Duan K., Xi D., Zhu Y., Zhu H., Xiong H y He Q., (2020), A Comprehensive Survey on Transfer Learning. Proceedings of the IEEE, 109(1), 43-76. https://doi.org/10.1109/JPROC.2020.3004555
