Intellectual Property India Publishes Patent Application for A Deep Learning Framework For Early Detection Of Guava Fruit Anthracnose And Fruit Fly Infestation

MUMBAI, India, Aug. 24 -- Intellectual Property India has published a patent application (202621080918 A) filed by Symbiosis International Deemed University on June 30, 2026, for A Deep Learning Framework For Early Detection Of Guava Fruit Anthracnose And Fruit Fly Infestation.

Inventors include Dr. Aniket K. Shahade; and Dr. Priyanka V. Deshmukh.

The application for the patent was published on August 21, 2026, under issue no. 34/2026.

Abstract: ABSTRACT A DEEP LEARNING FRAMEWORK FOR EARLY DETECTION OF GUAVA FRUIT ANTHRACNOSE AND FRUIT FLY INFESTATION The present invention discloses a deep learning framework (100) for early detection of guava fruit anthracnose and fruit fly infestation. The framework (100) comprises an image preprocessing module (110) employing unsharp masking (114) and CLAHE (116) for disease feature enhancement, a data augmentation module (120), a deep learning model module (130) evaluating ResNet50 (132), EfficientNetB3 (134), DenseNet121 (136), and Vision Transformer (138) classifiers, a transfer learning and classification head (140) with ImageNet pretrained weights (142) and a custom classification head (144), and a model evaluation module (150). EfficientNetB3 achieves 98.5 percent accuracy with minimal misclassification between anthracnose and fruit fly categories, enabling reliable early disease detection for sustainable guava agriculture. [

Disclaimer: Curated by HT Syndication.