Publication Date: 2022/08/03
Abstract: As of now decade, many researchers have worked in the tomato plant disease detection field. It’s not easy for farmers to identify tomato leaf diseases detect is difficult, for farmers challenging for them to discover other plant illnesses, such as tomato plant disease. So, the ongoing development with the help of machine-learning and deep-learning has greatly helped in identifying tomato plant disease detection by operating various methods along with tools. Precise the outcome but the accuracy of models depends on the volume as well as the quality of labeled data for training. In this article, for the detection of the disease convert the image into RBG and then identify the region-based image along with the help of segmentation by using the k-mean method. Then extract the image together with gray level co-occurrence matrix (GLCM) features used to identify a diseased infected part. Performance-based, classify images with respect to improving the efficiency of the overall model. The final output indicates that the proposed method achieved an accuracy of 95% through resnet50 for ten classes, nine disease classes, and one class that is healthy.
Keywords: Grey Level Co-Occurrence Matrix (GLCM), Convolution Neural Network (CNN)
DOI: https://doi.org/10.5281/zenodo.6957844
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT22JUL676.pdf
REFERENCES