Deep neural network features fusion and selection based on PLS regression with an application for crops diseases classification

• Published in: Applied soft computing Vol. 103; p. 107164
• Main Authors: Saeed, Farah, Khan, Muhammad Attique, Sharif, Muhammad, Mittal, Mamta, Goyal, Lalit Mohan, Roy, Sudipta
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.05.2021
• Subjects: CNN; Crops diseases; Feature extraction; Feature fusion; PLS based selection; Feature extraction; CNN; Feature fusion; PLS based selection; Crops diseases
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2021.107164

The plants diseases affect both the production and quality of food in the agriculture sector. Computer vision techniques can contribute significantly by detecting the plant’s diseases at very early stages with more accuracy. In this work, we proposed an automated crop disease recognition system using partial least squares (PLS) regression for feature selection from an extracted deep feature set. The presented framework incorporates three primary phases: First, the deep features are extracted using a pre-trained Visual Geometry Group (VGG19) convolutional neural networks (CNN) model; Second, a PLS-based parallel fusion method combines the features extracted from the fully connected layers 6 and 7; Third, the best features are selected using a PLS projection method. The most discriminant features are finally plugged into the ensemble baggage tree classifier for final recognition. Three different crops (tomato, corn and potato) are selected from the Plant Village dataset for the algorithm’s evaluation. The average accuracy achieved using the proposed method is approximately 90.1%. The proposed PLS based fusion and selection methods not only improve recognition accuracy but also reduce computational time. Further, based on the achieved results, we are confident that the proposed plan will work even under light variations and texture constraints. •Automatic identification of crop diseases can contribute to more sustainable agricultural in practices and food production security.•Partial least square (PLS) regression-based deep neural network (DNN) feature fusion and selection.•Transfer Learning based deep features are extracted from last two layers.•The overall achieve accuracy of the proposed method is 90.1% on the ensemble classifier.