Dr. Farshid Pirahansiah
AI research, computer vision, and model optimization for edge and cloud. A decade-plus of turning algorithms into production systems — from real-time vision and GPU acceleration to on-device LLMs.
About Me
I am an AI and computer vision expert with over a decade of experience collaborating with global organizations. My work spans research and development, machine learning, deep learning, IoT, and model optimization for edge and cloud solutions. I have led groundbreaking projects in generative AI, video analytics, and intelligent systems — proficient in C++, Python, OpenCV, and advanced GPU optimization, bridging the gap between cutting-edge research and commercially viable products.
What I Do
- Computer Vision & AI — image processing, deep learning, real-time systems
- Edge AI — Jetson, Coral TPU, Intel NCS2, Raspberry Pi, FPGA (Kria KV260)
- On-Device LLMs — local inference, model quantization (INT8/FP16), TensorRT, OpenVINO
- GPU Optimization — CUDA, RTX 1080→5090, Apple Silicon
- Full-Stack LLM — training, fine-tuning, deployment, API integration
Services
- Consulting & Engineering — end-to-end computer vision and AI systems for production
- Coaching & Tutoring — personalized curriculum from CV fundamentals to edge AI
- Model Optimization — quantization, pruning, deployment for edge and cloud
- Startup & Product — architecture, technical leadership, investor-ready solutions
Publications & Patents
21 publications (book chapters, journal & conference papers) and 3 patents. Full text below.
Book Chapters
- Mastering AI and Machine Learning: A Comprehensive Summary
- Mastering AI and Machine Learning: Essential Glossary, Resources, and References
- AI computer vision locally: LLMs on device
- Camera Calibration and Video Stabilization Framework for Robot Localization
- Computational Intelligence: From Theory to Application
- The New Developer Era: The Future of AI Agents
Journal Articles
- Ant Colony Optimization for Image Edge Detection
- Adaptive Image Thresholding Based on PSNR
- Character and Object Recognition Based on Global Feature Extraction
- GSFT-PSNR Global Single Fuzzy Threshold
- PSNR-based Threshold Method for Image Segmentation
- SLAM Trends and Humanoid Robot Linkages
Conference Papers
- Adaptive Image Segmentation Based on PSNR for License Plate Recognition
- Evaluation of Classification Techniques Using Enhanced Geometrical Topological Feature Analysis
- Camera Calibration for Multi-Modal Robot Vision
- Character Recognition Based on Global Feature Extraction
- Single Thresholding Method for Handwritten Images Segmentation
- License Plate Recognition with Multi-threshold based on Entropy
- Multi-threshold Approach for License Plate Recognition System
- 2D versus 3D Map for Environment Movement Objects
- Pattern Image Significance for Camera Calibration
- TafreshGrid: Grid Computing in Tafresh University
Patents
- A Method for Detecting a Moving Vehicle
- Patent Application WO 2020/141969 A2 — Digital Advertising System
- Face Augmentation
Browse the full Atlas for publications, courses, technical notes, talks, and projects. · Google Scholar · My podcast
Connect
Dr. Farshid Pirahansiah · Computer Vision & Edge AI Engineer · info@pirahansiah.com