Intellectual Property India Publishes Patent Application for 'A Framework Using Deep Learning For Predicting Germination And Evaluating The Quality Of Maize Seeds' Filed by Nri Institute Of Technology; Ms. S. Sanjana; Mr. T. Vijaya Krishna; Mr. G. Sai Kumar; Mr. T. Kumareswar; Mr. P. Venu Gopal; and Mr. B. Phanindra Kumar

MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641061607 A) filed by Nri Institute Of Technology; Ms. S. Sanjana; Mr. T. Vijaya Krishna; Mr. G. Sai Kumar; Mr. T. Kumareswar; Mr. P. Venu Gopal; and Mr. B. Phanindra Kumar, Eluru, Andhra Pradesh, on May 14, for 'a framework using deep learning for predicting germination and evaluating the quality of maize seeds.'

Inventor(s) include Ms. S. Sanjana; Mr. T. Vijaya Krishna; Mr. G. Sai Kumar; Mr. T. Kumareswar; Mr. P. Venu Gopal; and Mr. B. Phanindra Kumar.

The application for the patent was published on May 29, under issue no. 22/2026.

According to the abstract released by the Intellectual Property India: "This new technique evaluates maize seeds, assesses their quality, and looks at how likely they are to sprout using deep learning. An autoencoder verifies that a seed image uploaded by a user is indeed maize, eliminating those that don't match. The system only proceeds with appropriately recognised users following identity verification. A CNN then takes over, carefully examining each authorised seed by examining its shape, size, colour, and texture. Visual data patterns immediately inform condition selections based on these findings. The seed advances if the data indicate significant characteristics associated with health. Next are timing projections, which predict whether growth will occur at all or how soon it will start. This step is handled by an LSTM, which makes inferences from previously processed data over time. One consistent chain of analysis is formed as each stage seamlessly transitions into the next. Furthermore, changes in temperature and moisture content replicate actual agricultural circumstances in the simulation, each of which influences how seeds begin to grow. This approach eliminates the need for physical handling, operates instantly, and provides unambiguous readings on seed performance. It gradually shapes more intelligent planting routine decisions while firmly establishing forecasts in real-time feedback loops."

Disclaimer: Curated by HT Syndication.