## AI Developer Needed: Face Recognition + Subtitle Tagging for Movies (Python) ### Project Overview We are building a system that automatically identifies actors appearing in a movie and tags them in subtitle files. The goal is to process a full-length movie (2–3 hours) and output a subtitle CSV enriched with actor tags (and optionally emotions). --- ### Core Requirements #### 1. Face Detection & Recognition * Detect faces from video frames using **open-source libraries only** * Examples: InsightFace, FaceNet, DeepFace, OpenCV, etc. * Match detected faces with a provided **Actors Faces Library** (images per actor) * Identify **prominent actors per timestamp** --- #### 2. Subtitle Integration * Input: * Movie video file (MP4/MKV) * Subtitle file (CSV or SRT converted to CSV) * Output: * Same subtitle file with an added column: ```text hashtags → #actor1 #actor2 ``` * Tag actors appearing during each subtitle time window --- #### 3. Performance Constraints (Important) * Must handle **full movie (up to 3 hours)** * Application memory usage: * **Maximum: 100 GB RAM** * Efficient implementations preferred (lower RAM = better ranking) * Should not crash on long videos --- ### Bonus (Extra Payout) * Emotion detection per face: * Example output: ```text #actor1:happy #actor2:angry ``` * Higher accuracy in: * Face recognition * Multi-face scenes * Faster processing time --- ### Provided Data (Zip File) Participants will receive: * Movie file * Subtitle CSV file * Actors Faces Library (folder per actor with images) --- ### Expected Deliverables * Python script (or equivalent runnable code) * Instructions to run (README) * Output sample CSV * Requirements file (pip/conda) --- ### Evaluation Criteria | Criteria | Weight | | ------------------------------- | ------ | | Accuracy (actor identification) | Memory efficiency | Speed | Code quality & clarity | Bonus (emotion detection) --- ### Technical Expectations * Should work on CPU (GPU optional but not required) * Must use **open-source models only** * No paid APIs --- ### Important Notes * The solution should be robust to: * Different lighting conditions * Multiple faces in frame * Partial face visibility * Avoid loading entire video into memory * Streaming / sequential processing preferred --- ### Winner Selection The best solution will be selected based on: * Accuracy * Stability on long videos * Resource usage * Code usability --- ### Budget & Rewards * Base reward for working solution * Additional bonus for: * Emotion detection * High accuracy * Optimized performance --- ### Ideal Candidate * Experience with: * Computer Vision / Face Recognition * Python (OpenCV, PyTorch, ONNX, etc.) * Prior work in: * Video processing * ML pipelines --- If you have built similar systems or can optimize for performance at scale, this is a perfect challenge. Looking forward to your solutions! Please check the attached google drive for reference files. As the movie file is greater than 25MB (approved limit of freelancer, uploading drive link) https://drive.google.com/drive/folders/1Od45MgSYJe6N9TGBnzBND158ZONVSIEr?usp=sharing i have uploaded lot of actor faces into face library, but I want python or any file to narrow down required actors tagged in CSV file. Additional 30$ payout if it recognises emotions of tagged actors from the subtitle.