MUMBAI, India, Aug. 10 -- Intellectual Property India has published a patent application (202541006511 A) filed by Hindusthan Institute Of Technology on January 27, 2025, for Morphological Image Processing Operators On Fpga With Reconfigurable Architecture.
Inventors include Dr. C. Natarajan; Hakkem. B; Dr. B. Paulchamy; Dr. K. Kalpana; S. Brindha; and Chittaturi Karthik Virat.
The application for the patent was published on July 31, 2026, under issue no. 31/2026.
Abstract: RECONFIGURABLE ARCHITECTURE OF MORPHOLOGICAL IMAGE PROCESSING OPERATORS ON FPGA Morphological image processing is a critical technique in Image analysis, widely used in applications such as noise reduction, shape detection, feature extraction, and image segmentation. Efficient implementation of these operations is essential to meet the demands of real-time processing in various fields, including medical imaging, surveillance, and industrial automation. This project proposes a novel reconfigurable architecture for morphological image processing operators on FPGA (Field-ProgranJmable Gate Array) platforms. The reconfigurable design leverages the inherent parallelism of FPGAs to accelerate the computationally intensive morphological operations such as dilation, erosion, opening, and closing. By employing hardware optimization techniques and modular design principles, the architecture supports dynamic reconfiguration to adapt to varying image processing requirements without the need for significant hardware modifications. The proposed system ensures high throughput, reduced latency, and energy efficiency compared to traditional CPU or GPU-based implementations. Additionally, the design incorporates flexibility to handle different structuring elements and image resolutions, making it scalable and versatile. The project includes detailed performance analysis, comparing the FPGA-based implementation against conventional methods in terms of speed, resource utilization, and power consumption. This work contribute to the advancement of real-time image processing systems, particularly in domains requiring high reliability and low-latency solutions, thereby opening new avenues for adaptive and efficient morphological image processing ·applications.
Disclaimer: Curated by HT Syndication.