Pseudoinverse learning autoencoder with DCGAN for plant diseases classification

Pest infestation of crops and plants impacts agricultural development. Generally, farmers or specialist observe the plants with the naked eye to recognise and diagnose ailments. However, this technique can be time-consuming, costly and inexact. In contrast, auto-detection using image processing methods gives fast and precise results. This paper introduces a new plant disease identification model predicated on leaf image classification that employs a deep convolutional generative adversarial network (DCGAN) along with a classifier identified by multilayer perceptron (MLP) neural networks trained with a pseudoinverse learning autoencoder (PILAE) algorithm. The DCGAN performes two tasks: (1) synthesis of the minor class images to overcome the issue of imbalance in the dataset and (2) extracting deep features of all images within the dataset. The PILAE training procedure is not required to identify the learning control variables or indicate the number of hidden layers. Consequently, the PILAE classifier can fulfil exceptional execution with regard to training efficiency and reliability. Empirical results from PlantVillage dataset possess demonstrated how the presented method yields positive results with other models and reasonably minimal complexly.