Freelancers using OpenCV in RawalpindiFreelancers using OpenCV in Rawalpindi
ProjectsPeople
Shehzada Ammad Ali's avatar
Shehzada Ammad Ali
Islamabad, Pakistan
Full Stack Developer| n8n | Framer| Kajabee| Webflow Expert
1x
Hired
43
Followers
Full Stack Developer| n8n | Framer| Kajabee| Webflow Expert
Cover image for Rat Paw Detection with YOLOv8 + Gradio This project showcase...
Rat Paw Detection with YOLOv8 + Gradio This project showcases a lightweight and intuitive web interface for detecting rat paws in images using a custom-trained YOLOv8 model. Built with Gradio, it allows users to upload an image and receive instant visual feedback with detected paws highlighted. Key Features: YOLOv8 object detection fine-tuned specifically for rat paw recognition. Interactive web app for image uploads and real-time inference. Built with Gradio for fast prototyping and deployment. Clean interface with automatic annotation overlay.
2
189
Cover image for Contours Extraction & DXF Export from Images-AI-Based End-to...
Contours Extraction & DXF Export from Images-AI-Based End-to-end computer vision solution that automatically detects objects in an image, accurately measures in real-world units, &exports result as a scalable DXF file. Key Features Uses background subtraction & morphological operations, extract objects from image, even in cluttered or noisy backgrounds. Detects known reference object (coin) in image & computes precise scaling factor (mm/px) using OpenCV contours & geometric heuristics. Clean object edges are extracted & converted into vector contours with pixel-level precision. Object outlines are transformed into vector splines & exported as .dxf files, fully compatible with CAD tools like AutoCAD, LibreCAD, SolidWorks, & Fusion360. User-friendly frontend for non-technical users to upload images & receive DXF files .
2
181
Cover image for Image Stitcher – Seamless Panorama Creation Using OpenCV & G...
Image Stitcher – Seamless Panorama Creation Using OpenCV & Gradio This project is a web-based image stitching tool built with Python, OpenCV, and Gradio. It enables users to upload multiple overlapping images and generate a seamless panoramic output with enhanced exposure and automatic perspective correction. Key Features: Uses CLAHE (Contrast Limited Adaptive Histogram Equalization) to enhance the luminance channel and balance exposure across input images. Utilizes OpenCV’s Stitcher class to intelligently align and blend images into a panoramic output. Applies a bounding box and perspective transform to fix skew and crop black borders for a cleaner result. Built with Gradio for a simple, interactive web interface that supports: Multiple image uploads, Real-time stitching preview, One-click stitched image download
1
115
Cover image for 🚬 New Project: Migratory Story Excited to kick off a new Sh...
🚬 New Project: Migratory Story Excited to kick off a new Shopify project for Migratory Story, a premium cigar store. Services: Shopify setup, UI/UX design, Figma prototypes, ecommerce management, and sales-driven content. #Shopify #Ecommerce #PremiumCigars #UIUXDesign #Figma #DirectResponseMarketing
1
142
OpenCV(3)
Syed Asad Iftikhar's avatar
Syed Asad Iftikhar
Rawalpindi, Pakistan
AI Automation Engineer | n8n, Flutter & Voice AI Specialist.
New to Contra
AI Automation Engineer | n8n, Flutter & Voice AI Specialist.
Cover image for I developed a real-time Air
I developed a real-time Air Drawing Application that uses Computer Vision to transform hand gestures into digital input. By utilizing a standard webcam, the app allows users to draw, erase, and select colors in mid-air without any physical contact with the screen. Key Technical Features: Hand Tracking: Integrated MediaPipe to track 21 specific hand landmarks with high precision and near-zero latency. Gesture Logic: Programmed custom state-switching—using a single index finger for "Drawing Mode" and a two-finger gesture for "Selection Mode" to navigate the UI. Real-time Rendering: Leveraged OpenCV for video processing and to create a dynamic, responsive canvas overlay. This project demonstrates my ability to build Human-Computer Interaction (HCI) tools and implement real-time AI solutions using Python.
0
25
Cover image for I engineered a high-performance, browser-based
I engineered a high-performance, browser-based 3D experience that allows users to manipulate a system of 15,000+ particles using real-time hand gestures. This project explores the intersection of Web Graphics and Computer Vision, turning a standard webcam into a spatial controller. The Technical Challenge The main hurdle was achieving a "haptic" feel ensuring the particles reacted instantly and smoothly to physical movements without lag. This required mapping 2D webcam coordinates into a 3D coordinate system and calculating volumetric transformations on the fly. The Solution & Workflow High-Performance Rendering: Used Three.js and WebGL with additive blending and custom color mapping to render a massive particle count at a consistent 60 FPS. Real-time Inference: Integrated Google MediaPipe to track 21 3D landmarks per hand directly in the client-side browser, eliminating the need for a backend. Dynamic Math: Implemented custom lerping (Linear Interpolation) and gesture thresholds to create fluid movements, such as a "fist-clench" collapsing the particles into a sphere and an "open-palm" expanding them into a galaxy. The Results Created a fully immersive, zero-latency interface that demonstrates the power of the modern web for interactive AI applications.
0
9
Cover image for I built a custom AI
I built a custom AI Voice Agent for a service-based business to automate their appointment booking process. The system handles inbound/outbound calls, qualifies customers, and manages scheduling without any human intervention. The Technical Challenge The goal was to create a "robust" agent that could handle natural human speech patterns including stammers or mid-sentence changes while maintaining the conversational flow. I needed to bridge the gap between high-fidelity voice synthesis and real-time database management. The Solution & Workflow Voice & Logic: Integrated ElevenLabs for realistic vocal performance and Retell AI (or similar) for low-latency conversational handling. Automation Engine: Built complex workflows in n8n to process the data gathered during the call. Real-time Integration: The system automatically cross-references and updates Google Calendar, sending instant confirmations to both the client and the customer. The Results 100% Automation: Successfully moved the client from manual phone bookings to a fully autonomous system. Error Handling: Programmed the agent to stay on track even when users provide vague or self-correcting input.
0
13
Cover image for I developed Chezify, a high-performance
I developed Chezify, a high-performance mobile application tailored for a local fast-food restaurant. The goal was to bridge the gap between a traditional physical storefront and a modern digital presence by providing a seamless, branded ordering interface. The Technical Challenge The focus was on creating a Modular Architecture that allows the business to scale its menu effortlessly. I designed a library of reusable Flutter widgets (FoodCards, DealCards) that ensure UI consistency across the entire app while maintaining a strict 60 FPS performance target for a premium user experience. The Results Optimized Performance: Achieved silky-smooth scrolling and transitions, even with high-resolution imagery. Scalable Design: Built a custom UI/UX from scratch using Dart, avoiding generic templates to ensure brand uniqueness. Business Integration: Developed an "Exclusive Deals" logic to drive higher order values through targeted combo offers.
0
16
OpenCV(1)
Arham Malik's avatar
Arham Malik
Rawalpindi, Pakistan
Backend & AI engineer who ships systems fast and scale.
New to Contra
Backend & AI engineer who ships systems fast and scale.
Cover image for Yeah, this one is a
Yeah, this one is a bit out there, but it was super fun. I built an AI that actually understands memes. It looks at the image and the text together using PyTorch, TensorFlow, and GPT 4. I used early and late fusion techniques to combine vision and language, plus Tesseract OCR to grab text from the image itself. The model hits over 95% accuracy on meme classification. It’s not your typical corporate project, but it shows how multimodal AI can understand humor, culture, and context. Definitely one of my favorite experiments. For more details, please visit: https://arham-nexus.vercel.app/work/memechecker
0
43
Cover image for This was a really cool
This was a really cool EdTech project. The goal was to automate grading and student verification. I built a Flask backend that hooks into NLP models, speech to text, text to speech, and even computer vision with OpenCV. Students can give live demos, and the system checks their face, asks them questions out loud, and grades everything automatically. No more manual grading or worrying about cheating. It’s 100% automated, and teachers love how transparent it is. The AI responds in under a second, so it feels almost magical. For more details, please visit: https://arham-nexus.vercel.app/work/evaluasysai
0
38
Cover image for This is a classic enterprise
This is a classic enterprise academic portal, but built solid. It uses  Web Forms, ASP.NET, C#, and SQL Server. The main challenge was role based access control because you have admins, faculty, TAs, and lab demonstrators all needing different permissions. I designed a three tier architecture with stored procedures and optimistic concurrency control so data doesn’t get messed up when people edit at the same time. Over 200 users per semester use it for task assignments and progress tracking. It’s not flashy, but it works perfectly. For more details, please visit: https://arham-nexus.vercel.app/work/talabportal
0
21
Cover image for Skill Swap is a peer
Skill Swap is a peer to peer learning platform where you can be both a student and a teacher. I built the backend with Java Spring Boot, real time chat with WebSockets, and video calls with WebRTC. The matching algorithm finds people based on skills, ratings, and availability. You can switch roles anytime. It also has a trust based review system so fake reviews don’t ruin it. This was an MVP, but it proved that real time learning communities can work really well. For more details, please visit: https://arham-nexus.vercel.app/work/skillswap
0
34
OpenCV(2)
Shaheer Zafar's avatar
Shaheer Zafar
Islamabad, Pakistan
ML Engineer + AI Expert: Precision Python Solutions
ML Engineer + AI Expert: Precision Python Solutions
Cover image for Shaheerzafar5/YOLOv8-Classification-On-Custom-Dataset-Recipe-In…
Shaheerzafar5/YOLOv8-Classification-On-Custom-Dataset-Recipe-In…
0
11
Cover image for Shaheerzafar5/News_Head-Line-Sarcasm-Detection
Shaheerzafar5/News_Head-Line-Sarcasm-Detection
0
2
Cover image for Shaheerzafar5/Recipe-llama-2-7b-custom-2k
Shaheerzafar5/Recipe-llama-2-7b-custom-2k
0
17
Placeholder project card media
View more →
OpenCV(1)
Pervaiz Ahmad's avatar
Pervaiz Ahmad
Rawalpindi, Pakistan
AI & Deep Learning Engineer |Comp Vision, RAG, Agentic AI
AI & Deep Learning Engineer |Comp Vision, RAG, Agentic AI
Cover image for Automated Traffic Control and Management System
Automated Traffic Control and Management System
0
3
Cover image for Advanced Face Recognition System for Enhanced Security
Advanced Face Recognition System for Enhanced Security
0
1
Cover image for AI-Driven Retail Store Automation System
AI-Driven Retail Store Automation System
0
2
Cover image for AI-Powered Line Art Poster Generator
AI-Powered Line Art Poster Generator
0
0
OpenCV(4)
Syed Asad's avatar
Syed Asad
Islamabad, Pakistan
AI Consultancy & ML Engineering Expert
AI Consultancy & ML Engineering Expert
Cover image for Clothes Segmentation
Clothes Segmentation
0
24
Cover image for Gemma Finetuned on Architecture dataset
Gemma Finetuned on Architecture dataset
0
10
Cover image for Generative AI for Content Creation
Generative AI for Content Creation
0
5
Placeholder project card media
View more →
OpenCV(1)
Faraz Ahmad's avatar
Faraz Ahmad
Islamabad, Pakistan
Dedicated ML & AI Dev: Vision to Reality
Dedicated ML & AI Dev: Vision to Reality
Cover image for Video surveillance for Shop lifting
Video surveillance for Shop lifting
0
1
Cover image for Human Body Measurement using Computer Vision
Human Body Measurement using Computer Vision
0
1
Cover image for Human Activity Classification Using IMU Sensor Data
Human Activity Classification Using IMU Sensor Data
0
1
Placeholder project card media
View more →
OpenCV(2)