Plant Disease Detection using

Image Processing Techniques

2 Outline

 Motivation & objective

 Importance of image processing in agricultural research
 Literature survey
 Benefits
 Conclusion
 References
3 Motivation & Objective

 Agriculture acts as the major contributor of Indian economy which is enhanced by image
processing techniques and nearly 70% of people in our country depends on agriculture [3].
 Plant diseases due to their spreading nature is considered as major factor affecting
cultivation yield. These agricultural practices need to be transformed in order to overcome
future food scarcity.
 Image processing along with availability of communication network can increase the level
of adoption of technological based systems as it can contribute in many aspects of the
Agriculture sector [2].
 The objective of the project is to design a low-cost agriculture system for monitoring
agricultural field and to develop an efficient system to detect and classify the diseases of
different plants using image processing.
4 Importance of image processing in agricultural
research
 The rapid advancement of technology has made the future of agriculture a bright one.
 What with scientists discovering exciting new research in plant and animal sciences every
year [1].
 Image processing has been proved to be effective tool for analysis in various fields and
applications of an agriculture sector [3].
 The image processing can be used in agricultural applications for following purposes:
1. To detect diseased leaf, stem, fruit 2. To quantify affected area by disease. 3. To find
shape of affected area. 4. To determine color of affected area 5. To determine size & shape
of fruits [5].
 Our standard of living keeps improving every day through agricultural research.
 Literature survey
5
Title Description Inference
1. Garg, Kanish, et al, (2021). A deep framework for simultaneous The experimental results
"Automatic Quantification of Plant segmentation of individual leaf instances and show:
Disease from Field Image Data Using corresponding diseased region using a unified Disease correlation = 73%,
Deep Learning." Proceedings of the feature map with a multi-task loss function for Run-time efficiency = 5fps.
IEEE/CVF Winter Conference on an end-to-end training.
Applications of Computer Vision.
2. Zhu, J., Wu, A., Wang, X, et al, Based on image analysis and back–propagation The methodology adopted
(2020).“Identification of grape diseases neural network (BPNN) an automatic detection. has a high classification
using image analysis and BP neural It has efficiently detected and recognized five accuracy of 91%.
networks”. Multimed Tools Appl 79, grape leaf diseases.
14539–14551.

3. Cristin, R., Kumar, B.S., Priya, C. et An efficient method for disease identification The experimental results
al, (2020).“Deep neural network based using Rider-CSA by integrating the rider proved that the Rider-CSA-
Rider-Cuckoo Search Algorithm for optimization algorithm (ROA) and Cuckoo DBN with maximal
plant disease detection”. Artif Intell Rev Search (CS). accuracy of 0.877.
53, 4993–5018. Deep Belief Network (DBN) is used for the
classification phase.
 Literature survey
6
Title Description Inference
4. T. N. Pham, L, et al., (2020). A multi-class mango leaf disease Compared to the results of CNN
"Early Disease Classification of classification using deep neural networks ANN's provides a better result with
Mango Leaves Using Feed-Forward with a wrapper-based feature selection a simpler network structure
Neural Network and Hybrid approach using an Adaptive Particle-Grey 89.41%.
Metaheuristic Feature Selection," in Wolf metaheuristic (APGWO).
IEEE Access, vol. 8, pp. 189960-
189973.
5. Suma, V., Shetty, R.A., et al., Plant disease detection using image The classification accuracy from
(2019). “CNN based Leaf Disease processing approach where convolution the color images is better than the
Identification and Remedy system and semi supervised techniques are gray scale with 88.20%.
Recommendation System”. used to characterize crop species and
3 International conference IEEE.
rd
detect the sickness status of 4 distinct
classes.
6. P. Jiang, Y. Chen, et al, (2019). A deep learning approach that is based on The INAR-SSD model realizes a
"Real-Time Detection of Apple Leaf improved convolutional neural networks detection performance of 78.80%
Diseases Using Deep Learning (CNNs) for the real-time detection of mAP on ALDD, with a high-
Approach Based on Improved apple leaf diseases by the GoogLeNet detection speed of 23.13 FPS.
Convolutional Neural Networks," Inception structure and Rainbow
in IEEE Access. concatenation.
7 Benefits

 Farmers no longer have to apply water, fertilizers, and pesticides uniformly across entire
fields.
 Instead, they can use the minimum quantities required and target very specific areas, or
even treat individual plants differently [4]. Benefits include:
• Higher crop productivity
• Decreased use of water, fertilizer, and pesticides, which in turn keeps food prices down
• Reduced impact on natural ecosystems
• Less runoff of chemicals into rivers and groundwater
• Increased worker safety
8 Conclusion

 It’s evident that the importance of agriculture cannot be overstated.

 As scientists continue to discover new procedures to increase crop and livestock yields,
increase overall food quality, and reduce loss due to insects and diseases [1].
 We can safely say that agricultural research still has a long way to go and image processing
was the non destructive and effective tool that can be applied for the agriculture sector with
great accuracy for analysis of agronomic parameters [2].
 Through continued studies and research on agriculture using image processing, our
standard of living can improve significantly.
 The greatest benefactor to all this will be everyone and everything that relies on
agriculture, including economies [1].
 References
9
1. https://impoff.com/importance-of-agriculture/ (accessed on 24th Jan 2021).
2. Janwale, Asaram. (2015). Digital Image Processing Applications in Agriculture: A Survey. International Journal of Advanced
Research in Computer Science and Software Engineering. 5. 622.
3. https://ukdiss.com/examples/image-processing-for-agriculture-sector.php (accessed on 20th Jan 2021).
4. https://nifa.usda.gov/topic/agriculture-technology (accessed on 18th Jan 2021).
5. Prakash, K., et al. "A study of image processing in agriculture." International Journal of Advanced Networking and
Applications 9.1 (2017): 3311.
6. Zhu, J., Wu, A., Wang, X. et al. Identification of grape diseases using image analysis and BP neural networks. Multimed Tools
Appl 79, 14539–14551 (2020).
7. Cristin, R., Kumar, B.S., Priya, C. et al. Deep neural network based Rider-Cuckoo Search Algorithm for plant disease
detection. Artif Intell Rev 53, 4993–5018 (2020).
8. T. N. Pham, L. V. Tran and S. V. T. Dao, "Early Disease Classification of Mango Leaves Using Feed-Forward Neural Network
and Hybrid Metaheuristic Feature Selection," in IEEE Access, vol. 8, pp. 189960-189973, 2020.
9. Garg, Kanish, Swati Bhugra, and Brejesh Lall. "Automatic Quantification of Plant Disease from Field Image Data Using Deep
Learning." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2021.
10. Suma, V., Shetty, R.A., Tated, R.F., Rohan, S. and Pujar, T.S., 2019, June. CNN based Leaf Disease Identification and Remedy
Recommendation System. 3rdInternational conference IEEE.
11. P. Jiang, Y. Chen, B. Liu, D. He and C. Liang, 2019 "Real-Time Detection of Apple Leaf Diseases Using Deep Learning
Approach Based on Improved Convolutional Neural Networks," in IEEE Access.
10

Thank you