Ing. Rijo Roy

Scientific Employee for Research and Teaching at Lehrstuhl für Bildverarbeitung • Research and development of deep learning models for the track- ing of human cells to detect cancerous cell behaviors. • Combining the tracking and the classification methods. • Supervising masters students in seminar course - "Current Trends in 3D Image Analysis". Used: Python, MATLAB, PyTorch, CUDA, Machine Learning, Deep Learning, Image Processing and Visualization

• Co-author of survey paper on transformers used for object detection in medical imaging. • Research and study on the state-of-the-art approaches used for cell tracking. • Classification of the individual cells which are found using cell tracking approaches. Used: Python, Git, PyTorch, Deep Learning, Image Processing

• In association with Uniklinik Aachen, created state-of-the-art methods for segmentation nnUNet, feature extraction Autoencoder, and classification of breast cancer lesions. • The noisy ultrasound images are refined with image processing techniques to improve the segmentation AUC for the nnUNet model. • Used self-attention methods to try to improve the performances. Technologies used: Python, MATLAB, Pytorch, Deep Learning, Machine Learning, Image Processing

• Python code for feature extraction and clustering of HeLa cells images using image processing techniques and mathematical modelling.

• Developed end to end pipeline for detection (UNet model) and classification (DenseNet model) of different classes of bone marrow cells to detect whether the patient is suffering from Leukemia. • Created user interface for the visualization of the results for an uploaded test image. Technologies used: Python, Git, Pytorch, Cuda, Deep Learning, Machine Learning, Image Processing

• Software development of test automation scripts using Python and C++ for telematics connectivity projects. • Increased the coverage of test automation to 94% thereby reducing manual work. • Active participation in gathering and understanding customer expectations and requirements. • Experienced in agile model. • Good exposure to complete project development model

• Designed, developed, documented, executed, and maintained test automation systems. • Worked with Python, Linux shell, MATLAB, and C++ on embedded-based systems. • HIL and SIL system development and execution. • Test ownership of connectivity modules. • Supported cross-functional teams for the design and development of automation scripts

• Worked in automotive telematics connectivity for Daimler truck projects. • Test planning, development, and automation using Python and C++. • Developed Python-based software tools with UI. • Exposure to V-type project model with CI/CD. Tools: Git, JIRA, Jenkins, TML, Canoe

• Field of study: Computer Engineering • Major Courses: Image Data Analysis, Pattern Recognition in Image Data, Computer Vision, Machine Learning. • Thesis: Automatic Identification of Cell-cycle Stages using Artificial Neural Networks • Grade 1.9

• Machine Vision • Systems and Software Engineering

• Major Courses: Electrical Machines, Digital Systems, Signals and Systems, Object-Oriented Programming