Year: 2025
Type: article
Abstract: Crop diseases significantly diminish agricultural production, resulting in economic losses. Early detection and species identification remain major challenges. This paper introduces a lightweight Convolutional Neural Network (LCNet) designed for the detection of corn diseases, including blight, common rust, and gray leaf spot, using an efficient, low-latency model. The suggested architecture consists of three convolutional layers, three pooling layers, and one fully linked layer. Experimental findings indicate that LCNet surpasses the pretrained architecture MobileNetV2, DenseNet201, and ResNet50, with an average accuracy of 94.65%. This method enables prompt disease identification, assisting farmers in averting significant crop losses while minimizing human labour in oversight and administration.
Source: INMATEH Agricultural Engineering
Authors: Vimal SINGH, Anuradha CHUG, Amit Prakash SINGH
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: diamond
OpenAlex ID: W7077050491