Intellectual Property India Publishes Patent Application for 'System/Method To Detect Tomato Leaf Disease Using An Enhanced Xception Model With Deep Convolutional Neural Networks' Filed by MLR Institute of Technology

MUMBAI, India, July 11 -- Intellectual Property India has published a patent application (202541060948 A) filed by MLR Institute of Technology, Hyderabad, India, on June 26, for 'system/method to detect tomato leaf disease using an enhanced xception model with deep convolutional neural networks.'

Inventor(s) include Mr. B. Veerasekharreddy; Dr. Venkata Nagaraju Thatha; Mrs. S. Viharika; and Mrs. J. Adilakshmi.

The application for the patent was published on July 11, under issue no. 28/2025.

According to the abstract released by the Intellectual Property India: "In agriculture, plant diseases are the major problem since they drastically lower crop yields and cost a lot of money. Because of its many health advantages and high nutrient content, the tomato has become the most widely grown vegetable crop in the world. In the opinion of many specialists, a disease poses a serious threat to tomato farming. Agriculturalists and the economy suffer greatly as a result of the widespread crop damage caused by several diseases. One of the most well-known approaches to deep learning is the Convolution Neural Network (CNN). Several agricultural challenges, like as weed detection, insect identification, fruit classification, and plant/crop disease recognition, have recently seen the most widespread application of CNN models. When it comes to disease diagnosis using a large amount of photos of plant leaves, CNN is crucial. Nevertheless, employing deep learning techniques to identify diseases from limited datasets is no easy feat. The current challenge is addressed by utilising the Transfer Learning (TL) technique. One of the most well-known deep learning techniques for disease detection in plants with very little plant image data is TL. The idea behind transfer learning is to take what you've learnt and apply it to new, similar problems. Reusing and adapting a pre-trained CNN model for use with a different dataset is the goal of TL. The core focus of the innovation is to introduce the MX-MLF2 model for disease detection in tomato leaves, which is based on Modified Xception. Classification of tomato leaf diseases is accomplished by the use of feature fusion and multi-level feature extraction. By including the transfer learning and fine-tuning approach alongside the MX-MLF2 model, the accuracy of tomato leaf disease detection is enhanced."

Disclaimer: Curated by HT Syndication.