Synopsis

Bangladesh is an agricultural country where economy is largely dependent upon production of many types of crops. The main food crops of Bangladesh are potato, paddy, pulse, barley, oilseeds, fruit, vegetables, spices, maize etc. While rice is the primary staple food and the most important crop, wheat and maize are of second and third importance. Pulses and oilseeds are important crops in the context of supplying plant-based proteins for rural people. Jute and sugarcane are important cash crops. However, crop production is hugely affected due to many types of leaf diseases every year. Many a times, farmers fail to identify the diseases within time and it leads to major losses. Deep learning based approaches can help a lot by providing an automatic solution for detecting crop leaf diseases. Early detection of leaf diseases can help farmers to take necessary approaches for the required treatment of the crops. 

Relevance of the Topic

Agriculture is the largest employment sector in Bangladesh, making up 14.2 percent of Bangladesh's GDP in 2017 and employing about 42.7 percent of the workforce. The whole agriculture sector is fully dependent on the production of many crops such as rice, wheat, maize, etc. Hence, working with this topic provides an opportunity to provide a real life solution to the crop disease problems that can eventually help the socio-economic structure of the country.

Future Research/Scope

Build a deep learning model to identify crop diseases.

Build a segmentation model to segment the affected areas of crops. 

Build a mobile application to make the whole process more feasible.

Build a model to suggest potential pesticides.

Skills Learned

• Basics of machine learning.
• Deep learning techniques such as CNN.
• Different CNN architectures such as AlexNet, VGGNet, ResNet, etc.
• Usage of high level neural network APIs such as keras.
• Usage of different libraries such as Numpy, Matplotlib, etc.
• Usage of different model performance metrics such as precision, recall, f1 score, confusion matrix, etc. 

Relevant courses to the topic

• Artificial Intelligence (CSE422)
• Neural Networks (CSE425)
• Machine Learning (CSE427)
• Image Processing (CSE428)

Reading List

• Sardogan, M., Tuncer, A. and Ozen, Y., 2018, September. Plant leaf disease detection and classification based on CNN with LVQ algorithm. In 2018 3rd international conference on computer science and engineering (UBMK) (pp. 382-385). IEEE.
• Saleem, M.H., Potgieter, J. and Arif, K.M., 2019. Plant disease detection and classification by deep learning. Plants, 8(11), p.468.
• Li, L., Zhang, S. and Wang, B., 2021. Plant disease detection and classification by deep learning—a review. IEEE Access, 9, pp.56683-56698.
• Jasim, M.A. and Al-Tuwaijari, J.M., 2020, April. Plant leaf diseases detection and classification using image processing and deep learning techniques. In 2020 International Conference on Computer Science and Software Engineering (CSASE) (pp. 259-265). IEEE.
• Lu, J., Tan, L. and Jiang, H., 2021. Review on convolutional neural network (CNN) applied to plant leaf disease classification. Agriculture, 11(8), p.707.