Enhanced Plant Leaf Disease Identification by Integrating 2DCNN and Transfer Learning for a Content-Based Image Retrieval System

Efficiently managing plant leaf conditions in large agricultural areas requires automated detection of leaf diseases. This research presents an integrated approach utilizing Content-Based Image Retrieval (CBIR) systems for the automatic identification of plant leaf diseases. The CBIR system employs preprocessing, segmentation using the graph cut superpixel method and feature extraction via 2D Convolutional Neural Network (CNN) models, which is focused primarily on detecting colorful plant flake complaints prevalent in blueberry, cherry and apple crops. Additionally, Gradient Boosting Trees (GBT) serve as classifiers to point to database stores of class predictions made by the classifiers for plant leaf images. Comparable deep learning models such as InceptionV3 and ResNet50 in the proposed CBIR system extract high-level features from images, predict leaf classes and store them in the database. Euclidean similarity measures between feature representations further assess the CBIR system's overall performance, with deep learning models successfully supporting retrieval and image classification tasks when compared with 2D CNN models.