Freelancers using OpenCV in LahoreFreelancers using OpenCV in Lahore
AI Solutions & Automation for Your Business
AI Solutions & Automation for Your Business
Cover image for ๐Ÿ‘‹ Hi, I'm Ahmad Yasin,
๐Ÿ‘‹ Hi, I'm Ahmad Yasin, Founder & CEO of Nexariza AI โ€” a global AI engineering and intelligent software company building AI agents, generative AI solutions, automation systems, computer vision applications, and custom SaaS products for businesses worldwide. In this short intro, I share who we are, what we do, and why we're passionate about helping businesses harness the power of AI to solve real problems. ๐Ÿš€ What Nexariza AI does: โœ… Custom AI Agents & Automation โœ… Generative AI Solutions โœ… Computer Vision Systems โœ… Custom Software & SaaS Development ๐ŸŒ Work with us / Partner with us: ๐Ÿ”— Website: https://nexariza.com (https://nexariza.com)๐Ÿ“ฉ Email: contact@nexariza.com (mailto:contact@nexariza.com)๐Ÿ’ฌ WhatsApp: +92 370 7348001 ๐Ÿ”— LinkedIn: linkedin.com/company/nexariza ๐Ÿ”— All links: linktr.ee/nexariza_ai ๐Ÿ“š Also check out Nexariza Learning Hub for free AI, ML & programming tutorials โ€” subscribe so you don't miss what's next! #NexarizaAI #AIAgency #ArtificialIntelligence #AIAutomation #FounderStory #TechEntrepreneur #AIAgents #GenerativeAI #SaaS #StartupJourney
0
29
Cover image for Project Title: Embedded Linux Face
Project Title: Embedded Linux Face Recognition Security System โ€” Dubai Client Category: Computer Vision ยท Edge AI ยท IoT Short Description: Production-grade 1:1 face verification system deployed on an industrial Linux PC in Dubai. Integrates SCRFD + AdaFace (ONNX Runtime) with ONVIF IP camera, Wiegand 48-bit access hardware, and GPIO alarm outputs. Supports 20,000-face offline database. Runs as a Linux daemon. Full offline deployment. Services Delivered: Computer Vision Engineering Embedded Linux Development Edge AI Deployment IoT Hardware Integration System Architecture Tech Stack: Python ยท SCRFD ยท AdaFace ยท ONNX Runtime ยท ONVIF ยท SQLite ยท Wiegand ยท GPIO ยท Ubuntu Linux Outcome: Live production system managing physical access control in Dubai. Client received a deployed, tested, auto-restarting daemon with full remote management capability. Links: nexariza.com (http://nexariza.com) | contact@nexariza.com (mailto:contact@nexariza.com)
1
243
AI Engineer and Machine Learning Expert
New to Contra
AI Engineer and Machine Learning Expert
Cover image for The system continuously monitors examination
The system continuously monitors examination halls through live camera feeds, analyzes student behavior, and flags suspicious activities such as mobile phone usage, abnormal head movements, gaze deviation, multiple faces, and unauthorized interactions.
0
37
Cover image for AI Surveillance & Activity Recognition
AI Surveillance & Activity Recognition System Built a real-time AI-powered surveillance platform for intelligent monitoring, object detection, and security analytics. The system leverages deep learning and computer vision to detect people, vehicles, unattended objects, and suspicious activities across multiple camera streams. Key Features Real-time person, vehicle, and object detection Automatic Number Plate Recognition (ANPR) Facial recognition and identity verification Multi-object tracking using ByteTrack Unattended baggage and boundary breach detection Crowd monitoring and suspicious activity recognition Real-time alerts and monitoring dashboard Optimized for high-performance GPU deployment
0
50
Cover image for Urdu News AI Summarization &
Urdu News AI Summarization & Search System Designed and developed an end-to-end AI platform for processing Urdu news from television broadcasts and digital media. The system automatically transcribes speech, extracts text from news tickers, generates concise summaries, and enables intelligent semantic search across large collections of Urdu news content.
0
30
Cover image for AI Chatbot with RAG &
AI Chatbot with RAG & Multi-Agent System
0
89
AI Developer & ML Engineer: Top-notch Expertise
AI Developer & ML Engineer: Top-notch Expertise
I build production-ready AI systems that actually ship
I build production-ready AI systems that actually ship
Cover image for Satellite imagery is the ultimate
Satellite imagery is the ultimate stress test for Computer Vision. It is not just about detection; it is about architecting precision across massive, high-resolution datasets where every pixel counts. I have been building AI pipeline to segment parking lots, walkways, and structures from aerial data. The challenge is not just the mode, it is the Infrastructure: - Tiling & Inference: Processing massive dimensions without losing small-object context. - Robust Pre-processing: Using OpenCV to handle varying lighting and atmospheric "noise." - Cloud Orchestration: Turning heavy segmentation models into responsive, scale-ready tools. It is about turning raw pixels into a reliable data layer for the business. Currently opening 20 hours/week for long-term partnerships in Computer Vision & AI Systems.
1
126
Cover image for I designed and delivered an
I designed and delivered an end-to-end MVP for a real-time AI talking avatar system, where live browser speech is converted into an AI-generated response and rendered through a lip-synced avatar video on GPU hardware. The objective was to validate technical feasibility, latency characteristics, and perceived real-time interaction before committing to production hardening. The system integrates speech-to-text, LLM-based reasoning, text-to-speech, and video synthesis into a single, runnable pipeline, deployed on an A100 GPU.
0
340
Cover image for At Formulatrix, I led the
At Formulatrix, I led the development of a computer vision pipeline for RockMaker, a biotech product used in crystallization experiments. I built and deployed object detection and image classification models that improved scoring accuracy by 13%, reducing manual effort for scientists and increasing customer satisfaction. The solution was productionized with Docker and CI/CD pipelines, ensuring scalability and reliability across client sites.
0
338
Full Stack Developer and AI Automation Developer
Full Stack Developer and AI Automation Developer
Placeholder project card media
View more โ†’
AI Systems & Backend Engineer | RAG & Agent
New to Contra
AI Systems & Backend Engineer | RAG & Agent
Cover image for Beyond the Naked Eye โ€” Automated Delivery Analysis in Cricket
Beyond the Naked Eye โ€” Automated Delivery Analysis in Cricket
0
72
Cover image for Project Title
NeuroNLP โ€” Cognitive &
Project Title NeuroNLP โ€” Cognitive & Emotional Text Analysis Engine Project Link https://github.com/shoaib1522/NeuroNLP-Brain-Cognition-Scoring-from-Natural-Language-Text - Overview: NeuroNLP is a full-stack, microservice-based text analysis platform engineered to evaluate human written communication across cognitive, emotional, and structural dimensions. The system processes user text in real-time through an asynchronous Python backend to compute a composite "Brain Cognition Score" alongside multi-faceted analytics visualized in an interactive Next.js chat interface. - Coherence & Logical Flow Engine: Converts sentences into dense vector embeddings using all-MiniLM-L6-v2 (Sentence-Transformers) and evaluates sentence-to-sentence topical continuity via pairwise cosine similarity matrices. - Granular Emotion Classifier: Utilizes a fine-tuned roberta-base-go_emotions transformer model running on PyTorch to detect probability distributions across 27 distinct emotional states. - Lexical Diversity Pipeline: Computes a normalized Type-Token Ratio (TTR) using spaCy tokenization pipelines to evaluate vocabulary richness and prevent stylistic redundancy. - Automated Grammar Scoring: Integrates language-tool-python to identify syntactic errors and derive an inverted error-rate metric normalized to a 100-point scale. - Backend Microservice: Developed with Python and FastAPI (running Uvicorn) to execute asynchronous ML inference and return structured JSON analytics payloads. - Frontend Application: Built with Next.js 14 (App Router), React 18, and TypeScript, styled via Tailwind CSS, and rendering real-time analytical charts using Recharts. - ML Infrastructure: Powered by PyTorch, Hugging Face Transformers, Sentence-Transformers, and spaCy.
0
88
AI Engineer building AI agents, LLM apps, RAG systems
New to Contra
AI Engineer building AI agents, LLM apps, RAG systems
Cover image for Developed an AI-powered KYC verification
Developed an AI-powered KYC verification feature that compares a user's National ID/CNIC photo with their selfie using facial embeddings. The system detects and processes both images, generates face embeddings, compares facial similarity, and automatically determines whether the identity match meets the verification criteria.
0
126
Cover image for Developed a custom AI assistant
Developed a custom AI assistant integrated with Telegram using the OpenAI SDK. The agent was connected to private business data and designed to provide context-aware, personalized responses through a simple Telegram chat interface. The solution focused on private knowledge integration, custom AI behavior, and automated conversational assistance.
0
76
Cover image for AI Organization & Business Automation
We
AI Organization & Business Automation We developed and tested a complete AI-powered business organization designed to automate customer communication, sales, operations, marketing, and business management. The system uses multiple specialized AI agents coordinated through a central Chief of Staff AI. The workflow can handle customer conversations, qualify leads, manage CRM records, schedule meetings, generate Google Meet links, understand voice messages, and escalate important matters to the business owner. The core AI platform has already been built and tested successfully. The remaining phase focuses mainly on official API integrations, production infrastructure, security, and deployment to make the system reliable and scalable for real-world business operations.
0
69
Cover image for A Python pipeline that reads
A Python pipeline that reads incoming payment documents PDFs, scans, spreadsheets, even phone photos and turns them into database-ready JSON for a logistics company's accounting system. The hard part wasn't extraction, it was trust. In accounting, a wrong number is worse than no number, so the pipeline never guesses: anything ambiguous comes back as null with a note, and every run reconciles sums and counts to the exact cent before it returns anything.
0
68
AI/ML & Full-Stack Developer
New to Contra
AI/ML & Full-Stack Developer
Cover image for An AI-powered fake medicine detection
An AI-powered fake medicine detection system built with Python, PyTorch, NumPy, and OpenCV. The system processes medicine package images, extracts medicine names using OCR, and verifies them against a dataset of registered medicines to help classify products as real or fake.
1
36
Cover image for Zwitter is a Flutter-based e-commerce
Zwitter is a Flutter-based e-commerce app for a clothing brand featuring an AI-powered virtual try-on experience. I built the shopping flow including product browsing, search, filters, product details, cart, checkout, and order management. The app also integrates 3D body scanning and an avatar-based fitting system that lets users preview clothing on a personalized virtual avatar, along with a virtual wardrobe for managing try-on outfits.
0
28
Cover image for Restomatic is a full-stack restaurant
Restomatic is a full-stack restaurant management system I built and deployed for managing menus, branches, orders, carts, table reservations, and customer interactions. I developed the Flutter web frontend with a Flask/Gunicorn backend and MySQL database, then configured Nginx for HTTPS, API reverse proxying, and SPA routing. I also handled deployment, backups, and rollback.
0
29
Cover image for HairGenie is an AI-powered haircare
HairGenie is an AI-powered haircare platform designed to provide personalized haircare recommendations. I built the full-stack application with Next.js and TypeScript, using Supabase, PostgreSQL, MongoDB, and Redis for the data layer. The platform includes a 7-step onboarding experience, image-based hair analysis, and a rule-based recommendation engine designed for future ML integration.
0
41