OpenCV Jobs

I’m building a cross-platform mobile app that acts as a personal styling and beauty assistant for both men and women. The core of the product is an AI engine that delivers highly-personalized outfit recommendations. Key functionality • The assistant studies three user-supplied inputs—body measurements, skin tone and face shape—and combines them with each person’s stated style preferences, their body type and real-time fashion trend data. • For every request it returns a clear set of outfit suggestions, indicating why each piece flatters the user’s proportions, complexion and current tastes. • A lightweight dashboard lets me update trend data, brand catalogs and style rules without redeploying the app. Technology expectations The re...

I want an app that scans the phone’s camera roll, recognises the same person across different shots, and then lets me decide exactly which images to forward. The core flow is simple: • First, the app analyses every photo, clusters faces that it believes belong to the same individual and shows me those groupings. • From there, I can pick pictures one-by-one or bulk-select them in three distinct ways: individually, by date range, or by geolocation. This mirrors the way I already think about my library, so the interface needs to surface those three filters prominently and let me combine them if I wish. • Once I have a final selection, the app should open the standard share sheet so I can send the chosen files through any installed channel (Messages, WhatsApp, AirDrop...

Quiero implementar en mi servidor Linux un sistema OMR escrito en Python que me permita elaborar, procesar y calificar hojas de respuesta de 1 a 100 preguntas. Necesito que desde la propia interfaz gráfica pueda: • Diseñar plantillas personalizadas: definir número de preguntas, incluir nombre de la institución y cargar el logo. • Reservar cuatro columnas de dígitos (0-9) que el alumno sombreará para generar su código interno; por ejemplo, 1101 identificará “PRIMERO A – Estudiante 01”. • Escanear la hoja PDF o imagen, identificar automáticamente al estudiante mediante esas columnas y leer cada burbuja para asignar la nota. • Guardar los resultados directamente en MySQL y permitirme co...

I need a fully-packaged proctoring add-on that plugs straight into Moodle quiz pages. Before the candidate even starts, the page must request camera permission, show a brief consent notice, then take and store an initial snapshot. While the quiz is running, the script should capture images at a configurable interval and run face-detection logic that immediately raises alerts for four specific situations: no face, multiple faces, noticeable face movement, and any visible gadgets. Each alert increments a violation counter; when the counter reaches a limit I set, the attempt should submit automatically. Inside Moodle’s admin area I want a settings screen where I can toggle the feature, choose snapshot frequency, set violation limits, and enable or disable each alert type. After each e...

I need a Python-based tool that can scan video files, detect Trees, Road, Infrastructure—and leave room for many more object classes as the project grows—then save every relevant frame straight into a MySQL database. Each stored image must be linked to the corresponding frame number and any detection metadata so I can later query, filter, and analyse the results. Once the data is stored, I want a lightweight viewer that steps through the saved frames in order, overlaying the detection boxes so I can visually confirm accuracy. OpenCV for frame extraction and display is acceptable; YOLO, TensorFlow, or another modern model is fine so long as the code is clean, well-commented, and easy for me to retrain with additional classes. To keep the hand-off smooth, please include: •...

1. CONTEXTO Y DESAFÍO REAL Proyecto del sector de la trefilería y el galvanizado con más de 40 líneas de producción activas. El 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, valide, estructure y democratice el conocimiento técnico que surge en el día a día, creando una infraestructura de inteligencia industrial sostenible a largo plazo. 2. LA SOLUCIÓN: "THE ...

I’m building a real-time AR application in Unity that puts user interactions at the center of the experience. The project already has a solid concept, but I now need the scene brought to life with responsive touch/gesture input through AR Foundation and polished 3D assets. Unity 3D (URP) will drive the core app, while MediaPipe or OpenCV will handle hand-tracking and gesture recognition. On the hardware side the code must remain portable to Raspberry Pi OS and Arduino-based prototypes, so a clean Python or Node.js bridge is essential. Here’s what I’d like you to deliver: • A Unity scene that compiles on Android and iOS, wired for AR Foundation with robust user interaction logic (tap, pinch, swipe, custom gestures). • Integration of MediaPipe/OpenCV scripts s...

Computer Vision Prototype Needed — Head Tracking & Auto Zoom (R&D Phase) I’m building a product and am currently in the early R&D phase before final hardware and SDK delivery. We are looking for an experienced computer vision / mobile vision developer to help us prototype and validate: Core Features • Real-time head/face detection • Automatic head tracking (keeping the head centered) • Auto zoom / smart cropping (keeping head size consistent) • Smooth motion and transition logic At this stage, we do not yet have final hardware or SDK access, so we are asking the freelancer to: Phase 1 – Prototype (on your own hardware) • Build a working demo using your own Android device / webcam / test camera • Use open-source tools (MediaPi...

I need an AI-driven workflow that takes raw footage and automatically turns it into polished short-form content ready for TikTok, Reels, and Shorts. The focus is exclusively on clips under a minute; no long-form or course material will be involved. Here’s what I expect the system to do: ingest a batch of source videos, detect the strongest moments, trim away the rest, merge the highlights, and export a seamless final cut. While doing so it should apply modern, clean-looking filters and subtle visual effects—think gentle color grading, light motion graphics, and smooth transitions that feel current rather than retro or flashy. I’m open to the underlying tech stack as long as the result is reproducible. If you prefer Python with OpenCV and FFmpeg, or would rather leve...

I want to build a Windows-only application that watches the live screen, detects people—including stylised in-game characters—in real time, and immediately drives a game controller so the crosshair locks onto and tracks that target as it moves. The workflow I picture is straightforward: the program captures frames, an AI model spots the person, and a virtual stick signal (XInput, vJoy or a comparable driver) nudges the aim every frame so it stays centred. Smoothness and speed are critical. On a 1080p feed I’m aiming for roughly 60 fps with no more than 40–50 ms end-to-end latency, so techniques such as YOLOv8, TensorRT or a lightweight custom network combined with OpenCV screen capture should fit. You’re free to choose Python, C++, or another language as long...

We are building an AI-powered livestream production platform that can fully automate the broadcasting of sports competitions, starting with dog agility. The goal is to eliminate the need for camera operators and directors, while still delivering a professional, TV-like livestream using one or multiple cameras. This is not a theoretical idea – similar systems exist (Pixellot, PlaySight), but none are specialized for agility sports nor integrated with timing systems and live graphics. Our project focuses on rule- based AI direction + computer vision, not generative AI. MVP Scope Video & Livestream: - Capture video from 1–2 cameras (USB / IP / phone stream) - Output live RTMP stream (YouTube / test server) - Automatically switch cameras based on AI decisions AI Director Logi...

I already have a working object-detection pipeline written in Python, and I now need that same logic moved into a cleaner, better-structured Python codebase that’s easy to maintain and integrate into a larger application. Think of it as a conversion/refactor: exact same model, exact same results, but with modern syntax, clear separation of concerns, and thorough inline comments. You’ll start from my original scripts and checkpoints, preserve every bit of accuracy, and hand back a fully functioning module (including a simple demo script) that can be installed with pip-installable requirements. Feel free to streamline library calls—TensorFlow, PyTorch, OpenCV, or whatever is currently in place—so long as the final inference output matches the reference I provide. De...

I need a single piece of software that controls my dimension-weight-scanning workflow from start to finish. The application must talk directly to three devices on the line—scale, volumetric camera and scanner—capture the dimension and weight data, then trigger a photo of the package label. From that image the program should reliably pull out the text, barcode and any QR code in one pass. Once each package is processed, all results have to be written to an XML file structured by date, with an auto-incremented package ID embedded in the node. The same data set should immediately feed two more actions: 1. Generate a ready-to-print shipping label (standard 4x6 thermal format). 2. Push the full XML payload to our in-house system through a REST-style API. I expect the software t...

I have apk files and panel files and example app. I need the new app edited wkth the old apps pictures and logos and then panel files uploaded to hosting stite and app tested. Ibo iptv and panel

I already have a working Python script that identifies stripe-like patterns in still images, but it needs to move from “proof-of-concept” to a polished, deployable module. The current model does a reasonable job on simple samples, yet its accuracy drops with noisy backgrounds, it only understands a handful of stripe geometries, and it processes large batches slower than I’d like. The brief is straightforward: • Improve accuracy: fine-tune the existing algorithm—or replace it—so it handles challenging lighting and mixed-texture scenes without a spike in false positives. • Add more pattern types: extend recognition beyond the basic horizontal/vertical stripes to oblique, curved, or irregular banding the current code ignores. • Optimize perfor...