I will build robust computer vision solutions

Need to automate what humans see and do in front of a screen or camera? As a Computer Vision & Machine Learning Engineer, I design, train, and deploy end-to-end CV pipelines that turn raw images and videos into reliable, actionable insights for your business.

What can I do for you

Image classification and detection

• Product/defect detection for e-commerce and manufacturing
• Face and pedestrian detection for security and analytics
• Multiclass object detection using YOLO, Faster RCNN, SSD, etc.

Video analytics and tracking

• People/vehicle tracking, counting, heatmaps
• Activity or event detection in surveillance/retail/sports
• Real-time inference from CCTV, IP cameras, or recorded footage

Document and OCR automation

• Document scanning and perspective correction
• Text detection and recognition (OCR) for invoices, forms, and IDs
• Keyfield extraction and validation workflows

Image segmentation and enhancement

• Semantic / instance segmentation (e.g., medical, satellite, retail)
• Background removal, quality enhancement, noise removal
• Custom preprocessing pipelines for downstream ML models

Custom deep learning models

• Finetuning pretrained models
• Model optimization