OpenCV Jobs

INGENIERO SENIOR DE IA: SISTEMA RAG MULTIMODAL ON-PREMISE CON APRENDIZAJE CONTINUO 1. CONTEXTO Y DESAFÍO REAL proyecto del sector de la trefilería y el galvanizado con más de 40 líneas de producción activas. desafío no es la falta de información, sino que el conocimiento crítico es volátil: reside en la experiencia de supervisores y operarios veteranos y se transmite de forma verbal. Cuando surge una solución técnica en planta, esta no se documenta y se pierde para el siguiente turno. Buscamos desarrollar un ecosistema de IA que no solo responda preguntas, sino que capture y democratice el conocimiento técnico que surge en el día a día. 2. LA SOLUCIÓN: "THE KNOWLEDGE LOOP" B...

Project Description We're looking for an experienced developer to build a fully automated poker bot that can play in free online poker tournaments (play-money / freerolls). This is a research and hobby project — not for real-money play. The system needs to combine game theory optimal (GTO) strategy with exploitative adjustments based on an expert human player's decision-making framework that we will provide. The bot should be able to join a table, read the game state visually, make decisions, and execute actions — all autonomously. What We're Building (3 Core Systems) 1. Poker Decision Engine (The Brain) Implement a GTO baseline strategy using frameworks like OpenSpiel, PokerRL, or equivalent Build an exploitative layer on top that adjusts based on opponent tend...

I need a complete Python application that runs on a Raspberry Pi 5 and identifies plant-leaf diseases in real time from the Pi camera. The same core model must also accept still-image uploads. All three disease categories—Fungal, Bacterial and Viral—have to be recognised with reliable accuracy. The user interface will be a Django web app. Within that app I want three role levels—Admin, Standard user and Guest—each with appropriate permissions for running detections, reviewing results and managing data. Please structure the code so that REST endpoints are cleanly separated; this will let me expose the following Android-ready APIs later on: live-video analysis, image-file analysis and retrieval of disease-history logs. Deliverables • Python inference engine (...

I need a clear, well-structured Python pipeline that ingests JPEG road images and their corresponding lane-segmentation masks (they sit in two separate folders sharing the same filenames) and returns one scalar per frame: a normalized lane-visibility score. The number is meant for relative comparison only, so internal units do not have to match any physical standard—just remain self-consistent frame to frame. The logic I have in mind revolves around four cues: • Brightness of the lane pixels themselves • Contrast between those pixels and adjacent pavement pixels • A distance weighting that values pixels closer to the camera more heavily than distant ones • A continuity penalty that reduces the score when the mask reveals breaks or flicker in the lane lin...

I’m ready to move from concept to working prototype on a home-security robot that focuses solely on emergency response—specifically, detecting break-ins and sending instant alerts. The core idea is a mobile unit that patrols designated zones, recognises unauthorised entry, and pushes real-time notifications (sound, SMS, or app-based) to my phone while triggering audible deterrents on-site. Here’s the shape of the work: • System architecture: advise on the right combination of sensors (camera, PIR, ultrasonic, mic), onboard processing (Raspberry Pi, Jetson, or similar), and wireless protocols so the robot can run edge-based computer-vision without relying on the cloud. • Detection pipeline: develop or integrate a lightweight model—OpenCV or TensorFlow-L...

This project aims to develop an AI-powered fitness assistant that provides real-time posture correction and feedback during physical workouts. With the growing popularity of home-based and remote fitness routines, there is a pressing need for intelligent systems that can guide users to perform exercises safely and effectively, minimizing the risk of injury and promoting consistent form. The proposed system leverages advanced computer vision and machine learning techniques to detect and analyze body posture using a live camera feed. By utilizing frameworks such as MediaPipe and OpenCV, the assistant accurately captures skeletal landmarks and evaluates the user’s movement patterns in real time. The AI model processes this posture data to identify deviations from the correct form and de...

I have a single-page TIFF that contains image data, and I need a small, well-structured Python project that will read that file, compute its colour histogram (or any other standard colour-profile information we agree on), and write the numeric results to a clean CSV file. I care as much about the code organisation as the actual extraction: classes, clear method separation, doc-strings and a simple command-line entry point are expected so I can drop the module straight into a larger .gal-based workflow. Feel free to rely on Pillow, OpenCV, NumPy or similar mainstream libraries as long as dependencies are listed in a requirements.txt. Deliverable • A self-contained Python package (Git repo or zip) with class-based implementation • One example script showing how to point it at a...

The file in question is a single screenshot whose text is now so heavily blurred that it is impossible to read. My only goal is to recover that text with enough clarity that every character can be copied or transcribed without guesswork. Because the blur is severe, I expect advanced de-blurring techniques—whether that means frequency-domain restoration in Photoshop, AI-powered tools such as Topaz Sharpen AI/Gigapixel, or custom Python/OpenCV scripting. Feel free to combine multiple passes or layer-based masking if that gives the best result; I just need the cleanest, most legible outcome you can achieve. Deliverable: a high-resolution image (PNG or TIFF) where the text is crisp and readable. If the restored file must remain at its original dimensions, please provide a second upsc...

I’m building a production-grade image-enhancement pipeline and want an AI engineer who lives and breathes Python and computer vision. The goal is to take raw mobile photos and automatically clean noise, sharpen details, fix color and convert them to 3d printable files. You’ll choose or design the model, train or fine-tune it, then wrap everything in a lightweight API that my mobile team can call in real time (on-device when feasible, cloud fallback when not). You should be completely comfortable with OpenCV plus deep-learning frameworks such as PyTorch or TensorFlow, and you know the trade-offs between traditional filters, GAN-based approaches, and modern super-resolution networks. Experience packaging models for CoreML, TensorFlow Lite or similar mobile runtimes will set you ...

I am building a CNC pen plotter that draws people on paper using a single pen. Before investing in a full pipeline, I want to run a paid validation phase to test feasibility and output quality. I am looking for a freelancer who can convert 1–2 images of people into clean, recognisable, CNC-ready vector line drawings. This is a finite, well-defined task, not open-ended research. Scope of Work (Validation Phase) - You will: - Take 1–2 photographs of people (provided by me) - Remove or ignore the background - Generate a vector line drawing that: ( Is recognisable when drawn with a pen Uses only strokes / paths Contains no dots, no shading fills, no raster data Looks like a human sketch Is suitable for CNC pen plotting ) Input Images: - May be colored - May include background...

I have a growing catalogue of raw video assets that need to be delivered in several sizes, bit-rates, and formats, and I want the entire pipeline handled through FFmpeg. In parallel, I’m exploring AI-driven animation—think taking existing footage or image sequences and adding character motion, stylised effects, or scene enhancements powered by a modern deep-learning model. Here’s what I need from you: • Design and script an FFmpeg workflow that ingests source files and outputs clean, artifact-free H.264/H.265 versions at multiple resolutions. It should be efficient enough for batch processing on a single workstation but scale to a GPU server when required. • Recommend (and set up) an AI model suited to my animation goals, then wire it into the pipeline so...

I need a piece of software that plugs straight into the video stream coming from existing, off-the-shelf CCTV cameras and immediately adds deep-learning smarts. The core must deliver three capabilities with high accuracy: object detection, facial recognition and motion tracking and more Whenever the system identifies a configured event it should push an alert to me by email, SMS, an in-app popup and, for operators in the control room, an on-screen monitor notification. Ideally the alert payload will include a timestamp, camera ID and a cropped snapshot or short clip of the trigger moment. Please build the solution so it can run on a local server (GPU-enabled Windows or Linux) but remain flexible enough to shift to a cloud instance later if needed. A clean, web-based dashboard to review...