Enhanced Field-Based Detection of Potato Blight in Complex Backgrounds Using Deep Learning

Abstract

Rapid and automated identification of blight disease in potato will help farmers to apply timely remedies to protect their produce. Manual detection of blight disease can be cumbersome and may require trained experts. To overcome these issues, we present an automated system using the Mask Region-based convolutional neural network (Mask R-CNN) architecture, with residual network as the backbone network for detecting blight disease patches on potato leaves in field conditions. The approach uses transfer learning, which can generate good results even with small datasets. The model was trained on a dataset of 1423 images of potato leaves obtained from fields in different geographical locations and at different times of the day. The images were manually annotated to create over 6200 labeled patches covering diseased and healthy portions of the leaf. The Mask R-CNN model was able to correctly differentiate between the diseased patch on the potato leaf and the similar-looking background soil patches, which can confound the outcome of binary classification. To improve the detection performance, the original RGB dataset was then converted to HSL, HSV, LAB, XYZ, and YCrCb color spaces. A separate model was created for each color space and tested on 417 field-based test images. This yielded 81.4% mean average precision on the LAB model and 56.9% mean average recall on the HSL model, slightly outperforming the original RGB color space model. Manual analysis of the detection performance indicates an overall precision of 98% on leaf images in a field environment containing complex backgrounds.

High-throughput field crop phenotyping: current status and challenges

“…Furthermore, an accurate and qualitative assessment of disease at the leaf level can help in the identification of efficient resistant genes, as was done for Septoria tritici blotch (STB) in wheat ( Yates et al 2019 ). Technologies that utilize intact leaf images taken under natural conditions have also seen advances for use in the accurate recognition of diseases ( Fuentes et al 2017 , 2018 , Johnson et al 2021 ).…”

Potato Plant Leaf Diseases Identification Using Transfer Learning

“…Potato is an important food source across the world, and it can be stored to provide food security as a result it is a commercial and existence agriculture (1) . In developing countries like Ethiopian, plant diseases are detected manually by trained experts scouting in cultivation field and inspecting potato foliage (2) (3) . This task is very monotonous, in some cases it is impractical due to the unavailability of professionals in remote regions (2) .…”

“…In developing countries like Ethiopian, plant diseases are detected manually by trained experts scouting in cultivation field and inspecting potato foliage (2) (3) . This task is very monotonous, in some cases it is impractical due to the unavailability of professionals in remote regions (2) . However, advancements in image processing, and deep learning https://www.indjst.org/ in disease recognition of plant leaves using images can make the process far effective and timely.…”

A Color Space Blending With Deep Learning Networks in the Identification of Plant Leaves

“…The Vein images are extracted similarly to color space conversions, which is another preprocessing technique In deep learning convolutional networks (DCNN), a good accuracy rate and lower error rate have been achieved in computer vision-based applications such as leaf detection, plant disease identification, etc. Here, each layer of the network is able to learn discriminant features of the input samples such as color, shape, texture, etc, Johnson et al (2021). During the training process, parameters in the network are optimized and trained.…”

“…They also have successfully implemented HSV color space in plant disease detection. Johnson et al (2021) explain that XYZ color space is similar to RGB color space with the reasoning that the distribution of RGB color space is overlapping with nearby regions and there is a larger distribution of intensity values in XYZ color space. They also have explained that HSL color space is similar to HSV color space, with the reasoning that the distribution of HSL color space overlaps with adjacent regions and there is a wide distribution of pixel intensity values in HSV color space.…”