MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122481 A) filed by Neethi M V; and Atme College Of Engineering, Mysuru, Karnataka, on Dec. 5, 2025, for 'temporal analysis of mango fruit crop.'
Inventor(s) include Neethi M V; Vanitha G Naik; Madhu Nagaraj; Dr Vinod Kumar P; Dr. Anitha D B; J N Karthik; Ambika V; and Arpitha A.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a system for temporal analysis and yield estimation of mango fruit crops using deep learning techniques. The system integrates image processing, color segmentation, and neural network-based object detection to dynamically predict crop yield with high accuracy. An image capturing device, such as a mobile camera, periodically acquires mango tree images to form a temporal dataset. A flower detection module employs HSV color segmentation to determine flowering density, while a fruit detection module uses a pre-trained Faster R-CNN with ResNet-50 architecture for fruit identification and counting. A temporal correlation algorithm establishes a relationship between flowering and fruiting stages to predict yield, and a graphical user interface (GUI) displays the predicted results. The invention enables early-stage yield forecasting, reduces manual intervention, and offers a scalable, low-cost solution suitable for small- and medium-scale farmers."
Disclaimer: Curated by HT Syndication.
