MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202641064096 A) filed by Chennai Institute Of Technology on May 21, 2026, for Non Invasive Vein Detection System Using Image Processing And Deep Learning.
Inventors include N. Sudhandira Priya; Seetha Shri K; and Lithika R.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: Title: NON-lNVASlVE VEIN DETECTION SYSTEM USING IMAGE PROCESSING AND DEEP LEARNING The titled invention discloses a machine learning-based vein detection system using image processing techniques. The system utilizes images captured either through mage acquisition unit (1) comprising a USB camera or standard digital images. These images are used to create a training dataset for the machine learning model. Initially, the captured images undergo processing in the image preprocessing module (2) followed by the image enhancement module (3) to improve contrast and visibility. Subsequently, a deep learning segmentation module (4) is applied to learn vein patterns from the training images and accurately identify vein locations in new input images. The performance of the system is evaluated using both qualitative and quantitative methods. Visual inspection and histogram analysis are used for qualitative assessment, while quantitative evaluation is carried out using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM). The processed results are finally displayed through the output visualization module (5). The proposed approach demonstrates improved vein visibility and higher accuracy compared to conventional enhancement methods. The developed system is low-cost, portable, and non-invasive, making it suitable for real-time clinical applications. This machine learning-assisted vein detection solution has significant potential to reduce procedural errors, improve treatment accuracy, and enhance patient comfort in medical environments.
Disclaimer: Curated by HT Syndication.
