**PROJECT DOCUMENT: FREELANCER REQUIREMENT – ANPR SDK DEVELOPMENT** Development of Offline ANPR (Automatic Number Plate Recognition) SDK Project Objective: To develop a high-performance, offline ANPR SDK capable of real-time license plate detection and recognition from IP camera streams, optimized for Indian road conditions. **Project Scope:** The selected freelancer/team will be responsible for designing and developing a modular ANPR SDK that can be integrated into edge devices or local servers. The SDK must process live RTSP streams and provide structured outputs via APIs. **Functional Requirements:** 1. Real-time video stream processing (RTSP / IP cameras) 2. Vehicle and number plate detection 3. Character segmentation and OCR 4. Output structured data: * Vehicle number * Timestamp * Image snapshot 5. Support for: * Day and night conditions * Motion blur handling * Non-standard Indian number plates 6. Offline operation (no cloud dependency) Technical Requirements:** * Strong experience in Computer Vision and Deep Learning * Hands-on experience with: * YOLO / SSD (object detection) * OCR models (CRNN, LPRNet, Tesseract improvements) * Experience with: * OpenCV * PyTorch / TensorFlow * RTSP stream handling (FFmpeg / GStreamer preferred) * Experience deploying models on: * Linux systems * Edge devices (Jetson preferred) --- **SDK Requirements:** * Deliverable must be a reusable SDK (not just an application) * Provide APIs in: * Python and/or C++ * Documentation for integration * Sample application for testing --- **Performance Expectations:** * Recognition latency: < 500 ms per frame * Accuracy target: * ≥ 95% (day conditions) * ≥ 90% (night conditions) --- **Deliverables:** 1. Working ANPR SDK (Linux-based) 2. API documentation 3. Demo application 4. Test results (accuracy benchmarks) 5. Deployment guide **Project Duration:** 4–8 weeks (flexible based on approach) --- **Eligibility Criteria:** Applicants must have: * Prior experience in ANPR / OCR / Computer Vision * Demonstrated projects (GitHub / portfolio required) * Ability to explain technical approach clearly --- **Application Requirements:** Interested candidates must submit: 1. Relevant project experience (links mandatory) 2. Proposed technical approach for ANPR in Indian conditions 3. Expected timeline 4. Tech stack to be used --- **Screening Questions (Mandatory):** 1. Which model architecture will you use for plate detection and why? 2. How will you handle non-standard Indian license plates? 3. How will you optimize performance for edge devices? --- **Selection Criteria:** * Depth of technical understanding * Relevant project experience * Practical implementation approach (not theoretical) **Note:** This is a product-oriented development project. Preference will be given to candidates who have built deployable systems rather than academic prototypes. ---