Academic

A microplate well segmentation pipeline for real-time colorimetric analysis of microplate wells.

Project Goals Cost-effective and portable ELISA reader with AI-aided diagnosis for adaptive calibration Image processing based qualitative and quantitative real-time analysis for improved sensitivity and specificity Current Progress Completed precise micro-plate well localization Well localization utilizes bit plane slicing, masking and contouring, and shape appropriation Extracts basic color information, measuring light intensity in RBG colorspace, for each well Provides normalized measure of intenstity Note Uses standard well-reference: A-H for rows, 1 to 12 for columns ‘00’ for base/reference well Sample: Segmented Microplate-wells (Pic shows a zoomed section of the microplate) Sample: Segmented Microplate-wells (Pic shows a zoomed section of the microplate) Locations of Segmented Wells Locations of Segmented Wells A cropped Well filled with a solution A cropped empty Well Well boundary colored has been colored for reference in the above figures.

Intelligent Digital Inline Holographic Micrograph (DIHM) Cell-Enhancement and Characterization Project Intro Developing a novel and efficient neural model for detecting and classifying cells such as RBC, WBC, and cancer cells, etc.

Project Goals IoT project to simulate a smart university for resource usage optimization, funded by ORSP-PDPU. Annual financial grant of ₹ 1,45,000 sanctioned by the university for the project development Prototype modules installed in Computer Lab: Light Control, Lab Temperature Control, Authorized Personnel Access.

IoT project to simulate a smart university for resource usage optimization with prototype deployed modules installed in Computer Lab.

Cell-line segmentation from DIH micrograph. Signal enhancement using CNN-based Autoencoder. Cell-line characterization using CNNs. Easy accommodation of newer cell-lines using transfer learning.