Computer Vision Jobs

Je souhaite extraire uniquement les questions visibles des images que je fournirai. Les livrables incluront un document texte (au format Word) où toutes les questions seront bien organisées et structurées. Idéalement, chaque question sera catégorisée si des indices sont visibles sur l'image. Par exemple : - Type des fichiers sources : contenu éducatif, formulaires officiels ou examens. - Résultat attendu : fichier texte lisible avec mise en page propre. Merci de me signaler tout problème potentiel avant de commencer.

I want to build a repeatable automation that plays the Solitaire game currently released only as a mobile app on both iOS and Android. The goal is for the script (or companion app) to mimic every tap and gesture a human would make—dealing, moving cards, undoing moves, and registering a win—so the game can be completed hands-free. I have not locked in a specific Solitaire variant yet, so please design the solution in a way that can adapt if we decide on Klondike, Spider, FreeCell, or another common mode. Screen-reading accuracy and gesture precision are more important to me than raw speed; the bot should respect the normal game tempo so its actions still look natural. Feel free to lean on frameworks such as Appium, XCTest, UIAutomator, or your preferred computer-vision app...

I need a production-ready AI application that ingests a user-supplied 2D floor plan (PDF, PNG, or DWG) plus any accompanying building-section notes, then automatically produces a full, permit-ready drawing set. Core output must include: • Foundation plan • Floor-framing plan • Building sections • Roof-framing plan • Exterior elevations The engine has to read the project’s geographic location, look up the corresponding climate and loading data, and embed all mandatory IRC 2018 clauses directly into the sheets (live references, snow/wind loads, footing depths, insulation R-values, etc.). Because the target audience is professional builders and code officials, the drawings must hit an advanced level of detail: framing member sizing, schedules, di...

I need a small, accurate program that accepts two medium-resolution JPEG photographs of a finished metal assembly and automatically presents them side-by-side, with every visual difference clearly highlighted on the right-hand image. The purpose is simple: help our fabrication team spot mis-welds, missing brackets, or other subtle manufacturing deviations without having to inspect the parts manually. Here is what matters most to me: 1. The tool must read standard JPEGs shot between 720p and 1080p—you can assume consistent lighting but plenty of reflections and shiny edges typical of stainless steel. 2. Output should be a single composite image (or screen) that shows both originals next to each other; regions that differ are accented visually so a technician can locate them in second...

Interactive 2D / 3D Children’s Game Development Needed Hello, We are looking for an experienced game developer or game development team to create high-quality interactive 2D and 3D games for children’s play areas, entertainment centers, shopping malls, and family entertainment venues. Our goal is to develop visually attractive, fun, and reliable games that can be integrated with our own computer vision, AI, camera, and sensor technologies. Important note: We do not need the developer to create camera systems, motion detection, AI, or sensor hardware. These technologies will be developed and integrated by our own engineering team. The game software must be designed in a way that allows easy integration with external systems. Our external software will handle player tracking...

Lead Engineer — Computer Vision & LLM Systems London (hybrid/in-office preferred) | Full-time** ## The company We are an AI-powered property intelligence platform. We turn a Rightmove or Zoopla listing into a full development appraisal — GDV, build costs, planning probability, extendable envelope — derived directly from floor plan geometry and plot data. Our browser extension and AI assistant, Otto, put this in front of UK estate agents at the point of instruction; a consumer-facing product is in build. We are mid-pilot with Glue Dog, a major UK independent estate agent network. If you need process, roadmap certainty, or a large team around you before you can ship, this isn't the role. ## The role You will own two things end to end: the computer vision pipeli...

I’m putting together a pick-and-drop mobile robot inside CoppeliaSim and I need a clean, well-commented Python script that handles two core tasks: • Closed-loop motion control: A PID controller should drive the differential wheels so the robot follows a straight or curved path accurately, with easy access to kp, ki and kd for later retuning. • Vision-based sorting: Using a simulated camera feed, the code must identify basic red, green and blue objects, command the gripper to collect the detected item, then deposit it at a defined drop zone. Everything happens in simulation, so feel free to make full use of CoppeliaSim’s remote-API calls, Python, OpenCV (or a similar vision library), and any helper utilities you find convenient. The scene already contains the robot...

Project Title: Develop ANPR / ALPR Engine for Qatar and GCC Number Plates Project Description: We are looking for an experienced AI/computer vision developer or team to develop a custom ANPR/ALPR engine for Qatar and GCC vehicle number plates. The engine must detect and recognize vehicle license plates from live CCTV/video streams and still images. It should support Qatar plates as the primary requirement, with future support for other GCC countries such as UAE, Saudi Arabia, Oman, Bahrain, and Kuwait. Required Scope: 1. License plate detection from images and video streams 2. OCR/recognition of Qatar number plates 3. Support for Arabic and English plate characters where applicable 4. Handling different plate types, colors, sizes, and formats 5. Vehicle image capture with plate crop 6....

I’m building a proof-of-concept that lets an ultra-low-power board—specifically an ESP32—capture image data and immediately flag early-stage oral cancer. Because the hardware budget is tiny, I need a novel, highly compressed AI architecture that still reaches clinically useful accuracy and inference speed at the edge. The device will ingest live image data from a camera module, run on-device preprocessing, then execute an AI-based model (think pattern-recognition and other machine-learning techniques rather than simple thresholding) fast enough to give instant feedback without off-loading to the cloud. Latency, memory footprint, and power draw must all stay within the ESP32’s limits. If you’re interested, send a detailed project proposal outlining: &bu...

I need a small Python utility that can scan any PNG I feed it, detect every black-colored pixel that is connected to the outer frame of the image, and then erase those pixels while leaving every interior mark—text, boxes, circles, fine lines—fully intact. The files come in many sizes and there is no alpha channel to worry about, so you are free to work in a standard 24-bit space. Feel free to rely on OpenCV, Pillow, NumPy, scikit-image or any similar library as long as installation stays simple (pip install …). Command-line execution is ideal: point the script at a single file or an entire folder, have it generate a cleaned version in a chosen output directory, and log how many border pixels were removed for quick verification. A clip example image is provided that sho...

I’m building an AI-driven tool that can read structural drawings and instantly produce a clean, reliable steel material take-off. The core workflow I have in mind is: • Import: User drops a PDF or native CAD file into the app (both Windows desktop and a lightweight browser version). • Parse: Your algorithm identifies every structural-steel member, sizes and lengths included, and groups them automatically by section. • Visualise: A basic 3-D isometric of the framing appears so the user can sanity-check the extraction before pressing “approve.” • Cost: Once approved, the software outputs two figures—estimated raw material cost and fabrication cost—calculated from editable rate tables. I don’t need connection bolts, finishes or o...

I have a mobile robot prototype and I need an AI agent that will let it perceive its surroundings, decide on actions, and execute them safely in real time. Because the hardware stack is still flexible, I am open to ROS, a custom embedded setup, or a commercial SDK—whatever you feel will achieve the best balance between performance and maintainability. At a minimum the agent must: • Fuse camera and sensor data to detect obstacles and points of interest. • Plan a collision-free path and update it on the fly. • Expose a clean API so I can add higher-level skills later (object pickup, voice interaction, etc.). Please structure the code in well-documented modules, supply build instructions, and include a short demo video that shows the robot handling a simple naviga...

I have list of images, need to extract only questions in doc file, i have format available

I need an AI solution that takes product photos and sorts each image into fewer than five preset categories. The sole goal here is image classification—no detection or enhancement features are required. You will start from an existing dataset of labelled product images (I’ll supply a download link once we begin). A lightweight, production-ready model built in Python with either TensorFlow or PyTorch is preferred; transfer-learning from a well-known backbone (e.g., ResNet, EfficientNet, MobileNet) is perfectly acceptable so long as the final classifier is accurate and quick to infer on standard CPU hardware. Key deliverables: • Clean, commented source code for training and inference • The trained model weights (or exported SavedModel / .pt file) • A short ...

Project Title: Wanted: STEM Experts for 20 Original Advanced Problems (Robotics, CV, RL, STEM) Project Description: We are seeking highly skilled researchers, algorithm engineers, and mathematicians to author 20 highly complex, completely original STEM problems. These problems will be used to evaluate the reasoning capabilities of frontier AI models, so they need to be genuinely difficult. The Deliverables (Format depends on your domain): You will deliver 20 original problem tasks. The required format varies based on the subject: For General STEM (Mathematics, Physics): Deliver a clean LaTeX file containing one original, self-contained problem, the uniquely determined correct final answer, and a step-by-step rigorous proof/worked solution. For Computer Science Domains (Robotics/Control, ...

We are looking for a System Developer with experience in camera-based Advanced Driver Assistance Systems (ADAS) development and integration within complex automotive environments. Key Responsibilities Own and develop the system architecture for camera-based ADAS functions in collaboration with multiple stakeholders across the vehicle development process. Define, maintain, and manage system requirements, including the derivation and traceability of detailed technical requirements. Integrate and validate ADAS functionalities such as Intelligent Speed Assistance, Lane Keeping Assistance, Travel Assist, and related driver assistance features at vehicle level. Plan, execute, and document system-level testing activities, including performance evaluation, root-cause analysis, and optimization. M...

Je souhaite faire développer une application mobile centrée sur l’intelligence artificielle, inspirée d’Instagram mais offrant une expérience nettement plus poussée. L’idée est de proposer un réseau social orienté photo-vidéo où l’IA amplifie la créativité des utilisateurs tout en ouvrant de nouvelles possibilités de monétisation et de suivi de performance. Fonctionnalités clés attendues : • Filtres avancés pour photos et vidéos : génération et ajustement en temps réel grâce à des modèles de vision par ordinateur (style-transfer, correction d’éclairage, effets 3D, etc.). • Opt...

Egy hordozható, Raspberry Pi 5-re épített képfeldolgozó céleszközhöz keresek Python-ban, OpenCV-vel jártas fejlesztőt. A cél egy stabil, valós idejű alkalmazás, amely két CSI porton csatlakozó, 160°-os Waveshare halszem kamerák képét dolgozza fel. Feladat részletei • A zárt, kontrollált megvilágítású dobozban egy 3 mm átmérőjű, sárga, zöld vagy piros kör alakú foltot kell HSV-alapú színkereséssel felismerni. • A detektálásnak folyamatos, akadozásmentes FPS mellett kell futnia, headless módban is. • Találat eset...

Saya ingin meningkatkan efisiensi kerja di lini produksi manufaktur dengan membangun sistem AI untuk pengawasan kualitas. Fokusnya adalah mendeteksi cacat produk secara real-time agar proses sortir berlangsung otomatis dan akurat, sehingga downtime dan limbah dapat ditekan. Ruang lingkup pekerjaan: • Memetakan alur inspeksi yang ada dan mengidentifikasi titik pengambilan data (kamera, sensor, atau citra mikroskop). • Membersihkan dan menyeimbangkan dataset citra produk; jika data belum memadai, sertakan rencana augmentasi atau synthetic data generation. • Melatih model computer vision (mis. YOLO, EfficientDet, atau metode setara) yang mampu mengklasifikasikan cacat dengan presisi tinggi. • Menyiapkan pipeline inferensi low-latency—idealnya menggunakan Python, Ten...