Mohit Angrish

Computer Vision : Sewer Defect Detection : Video Precessing and Object Detection

• Lead a team of 6 from to develop, train/test multiple Object detection models | classification models | OCR models identifying 74 visually separable defects occurring in the sewage pipes and Distance counter of the pipe respectively according to NASCO standards. Devised different strategies to verify existing marked defects and non detected defects.
• Closely Worked with the UI and Application team to optimize the workloads and add more product experience features to develop the feedback loop for model correction , maintenance and monitoring.
• Responsible for Designing entire AI roadmap for the project and helping fellow peers to improve their skills and competency in handling production grade machine learning systems.

Cost Optimization

• Developed optimization engine using differential evolution to calculate minimum cost while ensuring all the safety checks are performed.
• Devised and build the architecture for the application and deployed on the on-prem server.

Face Mask Detection

• Designed a two staged deep learning model consisting of MTCNN and a feed forward network to detect whether a person is wearing a mask or not. Abiding to the new rules due to spread of COVID.

Intrusion Detection

• Built a Deep Learning based intrusion detection system to detect people in unauthorized areas or unsafe areas using Faster RCNN model with inceptionV2 backend. Integrated the system with CCTV cameras using RTSP at construction sites all over India.

Invoice extraction using Deep leaning

• Design a deep learning model using Bi-directional LSTM to extract texts of a number of key fields from given receipts and save the texts for each invoice image, to extract key information from an un-structured or semi-structured data.

Auto Learning for ML on cloud

• Built a re-trainable machine learning pipeline on Azure.