Custom Object detection and face recognition system using yolo

About this Gig
Are you struggling to get accurate detections or looking to automate a visual task? I am a Computer Vision engineer specializing in YOLO11 and State-of-the-Art Face Recognition. I don't just write code; I build robust systems that work in real-world conditions, handling occlusion, low light, and moving targets. My Core Services: - Custom Object Detection: I will train YOLO11/v8 to detect your specific objects (e.g., defects, vehicles, logos, weapons). - Object Tracking: Preventing "flickering" detections using DeepSort or ByteTrack for counting and trajectory analysis. - Face Recognition: Secure attendance systems, access control, or VIP identification using InsightFace or FaceNet (Liveness detection included). - Pose Estimation: Gym form analysis or gesture control. What You Get With Every Order: - Annotated Data Review: I check your data quality before training. - Training Metrics: Confusion matrix and mAP graphs to prove accuracy. - Inference Script: Clean Python code to run the model on images/video/webcam. Recent Projects: - Automated License Plate Recognition (ALPR) - Employee Face Attendance System with Anti-Spoofing - Construction Site Safety (PPE Detection)
Requirements
What exactly are we detecting? Will this run on a webcam, a pre-recorded video file, or a folder of images? Do you have labeled data? Where will this run?