Find OpenCV Projects on Upwork with Vollna

I’m looking for a developer to create an algorithm that integrates with my app’s existing technology. The app scans a person’s face and generates one of six lash maps, which act as a guide for where each lash should be placed.

The algorithm should:
• Read the lash map and determine the correct type of lashes to use (individual, fans, or spikes) based on the selected set.
• Place the lashes in the correct position (inner, outer, middle, or straight) with the correct length and curl.
• Work in real-time as an augmented reality (AR) filter, ensuring that as the user moves their head, the lashes stay in place and adjust naturally—similar to a Snapchat filter.

For example, if the lash map specifies a volume set with C curl and an 8mm length in the inner corner, the algorithm should:
• Select only fans (since it’s a volume set).
• Use C curl (as defined by the map).
• Place 8mm fans in the inner corner using the correct perspective.

This app is designed for eyelash technicians who specialize in beauty and eyelash extensions. The system has already been programmed to measure a person’s eyes and automatically generate the ideal lash map with the correct curl, lengths, and set based on those measurements. The app already knows what lashes to use—users do not input this information manually.

Additionally, you will not need to create any lash images or assets—I already have them ready to be used. Your job is strictly to integrate this existing system into the real-time lash try-on feature, allowing users to see the lashes applied to their eyes and moving naturally as they turn their head.

You don’t need prior knowledge of eyelash extensions—everything related to how lash sets work will be explained in a Google Doc. You’ll also be able to work with my developers to understand how the system generates lash mapping.

This project requires expertise in:
• Algorithm development for automated lash placement.
• Computer vision & facial tracking to ensure the lashes move naturally with the user’s face.
• AR development to create a real-time filter experience.

My current developers have tried to do this but they can’t seem to train a machine learning model that can properly place the individual lashes according to the given lash map. If you have experience with facial tracking, real-time AR filters, and algorithm development, I’d love to hear from you!

Skills: Machine Learning, Computer Vision, Augmented Reality, iOS, Android, OpenCV, Artificial Intelligence

Project Overview
We are seeking a skilled developer to build ApparelApp, a Shopify app that allows users to upload a full-body photo and visualize clothing items (starting with sweaters) overlaid on their image. The app will use AI to detect body parts (torso/arms for sweaters), remove existing clothing, apply a neutral base layer to avoid mismatching, and overlay the selected clothing item. The goal is to provide a personalized try-on experience, reducing returns (30-40% reported in Shopify 2024 studies) and boosting conversions (40% lift reported by CDS Visual). We’ll start with a proof-of-concept (PoC) to test feasibility, then proceed to the full app if successful.

Development Phases
Proof-of-Concept (PoC): Test the core functionality (AI detection, background removal, clothing overlay) on a small scale.
Full App (Sweaters Module): If the PoC succeeds, build the complete sweaters module with Shopify integration and additional features.
Future Modules: Expand to pants, dresses, etc., using a modular approach.

Please only bid if you're built similar visualizer tools before.

***** Please read the full attachment before bidding, with all details enclosed. *****

Skills: React, Node.js, OpenCV, YOLO

Build a python computer vision script and model to interpret two types of routes displayed on aviation maps.

Detect labeled points connected by lines, the direction of the route between them (sometimes labeled with arrows, sometimes inferred by the direction of connected routes), output each route segment and information labeled on each point and the segment line.

Script should take a similar map and output the routes as JSON structured similarly to the detailed examples in the attached PDF.

Skills: Computer Vision, Machine Learning, OpenCV, TensorFlow, Deep Learning, Neural Network, Python, Artificial Intelligence

I'm looking for a freelancer who can help me set up a mini project on my Raspberry Pi AIkit with Hailo8 and 8L. The project involves running zeroshot object detection using a live camera feed.

Key requirements:
- Experience with TensorFlow/OpenCV/pytorch for object detection is a must.
- Proficiency in using Raspberry Pi and setting up a live camera feed from RPI camera, USB and IP camera.
- Ability to implement zeroshot learning for object detection.
- Use a transformer model

The project should demonstrate the object detection capabilities in real time. The ideal candidate would have a solid understanding of both hardware and software components involved in this project. Please include in your proposal your experience with similar projects.

Skills: Python, Microcontroller, Artificial Intelligence, Raspberry Pi, Transformer Model

I'm looking for a skilled web developer with expertise in HTML, JavaScript, and libraries like OpenCV or TensorFlow. The project involves creating a website where I can upload an image onto a canvas. The JavaScript should be capable of identifying various types of Barton Charts (specifically 24 hour, 7 day, 8 day, 16 day, and 31 day).

Key Functions:
- The JavaScript needs to find the center of the chart (the center of the black circle), the 0% mark inner circle, and the 100% outer circle.
- After identifying these components, the script should compute one of the arc angles and draw a line from the center of the chart to the 100% mark along the arc.
- A draggable circle should be placed at the end of the line, allowing me to click and drag the arc around the circle, pivoting around the center of the chart.
- More chart example are available upon request.

Ideal candidates should have a strong background in web development, specifically with HTML and JavaScript, and have experience with image processing libraries. The goal is to create an interactive, user-friendly chart manipulation tool.

Skills: JavaScript, HTML, Artificial Intelligence, OpenCV, Tensorflow

I need a tool to track student moods in distance learning by checking their faces and words in real-time. Here’s what I’m after:

Use Vision Transformers (ViT) to catch emotions from faces in video.
Use OpenCV to spot faces in those videos.
Add Speech-to-Text to turn student audio into text.
Use BERT to analyze if their text is positive, negative, or neutral (sentiment).
Build it with Python.
Make a simple frontend in Python (Flask preferred) to show mood results.
Store data in MySQL.

Skills: Python, Website Design, Matlab and Mathematica, Machine Learning (ML), Natural Language Processing

We are looking for a skilled software developer to create a program that processes PDF files containing QR codes and organizes a set of JPEG images based on specific rules. The ideal candidate must have experience in file manipulation, QR code processing, and image handling. If you have a strong understanding of programming and can efficiently combine these elements, we would love to hear from you. Please include examples of previous work related to file processing in your application.

----------------------------------------

Objective:
Develop software that processes a PDF file containing QR codes and a collection of JPEG photos, combining them according to the following rules. The output should be saved as JPEG files.
________________________________________
Input Data:
1. A PDF file with a variable number of A4 pages. Each page contains exactly one QR code.
2. A collection of JPEG photos in portrait and landscape format with a variable number of images.
________________________________________
Processing Rules:
1. First Step:
o Take the first QR code from the PDF file.
o Take the first photo from the collection.
2. Format Check for the Photo:
o Portrait Format: The photo is placed directly below the QR code.
o Landscape Format: The photo is not inserted but is saved separately in a list.
3. Continue Processing:
o Repeat the process with the next QR code and the next photo until no more photos are available.
o If QR codes remain but no more photos are available, stop the process and save the existing files in the output folder.
________________________________________
Additional Option: Detecting the Same Person in Multiple Portrait Photos
• If multiple consecutive portrait photos are present, automatic face recognition can be used to determine whether they show the same person.
• If two or more photos show the same person, the program can:
o Set the QR code only once and group the person's photos underneath.
o Maintain a separate assignment list for later arrangement.
• Face recognition can be implemented using OpenCV (dlib), Amazon Rekognition, or similar technologies.
• Alternatively, EXIF data (timestamps) and capture order can be used to determine the likelihood that the photos belong to the same person.
________________________________________
Output:
• The resulting images (QR code + photo) are saved as JPEG files.
• Landscape format photos are stored separately and not combined with QR codes.
• The original filenames of the photos and their metadata must be retained. The filename of the QR code images can be adjusted.
________________________________________
Additional Requirements:
• The order of the QR codes and photos must be preserved.
• If there are not enough QR codes or photos, the program should respond accordingly (e.g., by displaying a warning).
• A user-friendly Windows interface must be developed so that users without PC knowledge can use the software easily.
o User Interface Features:
 Option to upload the PDF file with QR codes.
 Option to upload the folder with photos.
 Start button to begin the process.
 Progress indicator and a notification upon completion.
 Option to set the output folder.

Skills: Graphic Design, Java, Adobe Photoshop, JavaScript, PHP

Impliment a sign language translation sytem that translate Indian sign language into english text in real time. Around 100-200 calsses in the dataset. Develop deep learning model with attention and/ or transfer learning methods . Test the model in realtime with openCV

Skills: Deep Learning, Deep Learning Modeling, Computer Vision, TensorFlow, Keras, OpenCV, NVIDIA AI Platform, Java

Crate a python function that would detect image orientation and then auto rotate it to correct orientation if needed. The issue is we can't use exif data as that is irrelevant. AI is also not much of help as it is lengthy and expensive solution. Any other solution is welcome.

Skills: Python, OpenCV, Image Editing, Python Pillow

We are looking for an AI/Machine Learning Developer and a Computer Vision Developer to help build an AI-driven graphic design platform.

AI/Machine Learning Developer
Skills Needed:

TensorFlow, PyTorch, GANs, StyleGAN, VAEs

NLP (OpenAI API, GPT-4, BERT)

Cloud Deployment (AWS, GCP), FastAPI, Flask

Experience in training and deploying deep learning models for real-time creative applications

Responsibilities:

Develop AI models for generating design elements

Integrate AI tools with the platform for enhanced user experience

Optimize models for cloud scalability

Computer Vision Developer
Skills Needed:

OpenCV, Image Processing, Object Detection, Segmentation

Expertise in Python for image manipulation

Responsibilities:

Implement image processing algorithms for separating and editing design layers (text, graphics, images)

Enable real-time image manipulation tools for users

Requirements:

Proven experience in AI and computer vision development

Ability to work collaboratively and independently

Strong problem-solving skills and experience with AI-driven creative projects

To Apply: Send your resume and portfolio showcasing relevant work.

Join us to build an innovative AI-powered creative tool for the design industry!

Skills: Computer Vision, OpenCV, Data Preprocessing, Deep Learning, PyTorch, Machine Learning, TensorFlow, TensorFlow Stack, StyleGAN

I’m working on a next-generation video AI tool aimed at creators and media companies. The tool combines audio, text, and visuals, and uses AI to automate a currently slow, manual process in video production.

I’m looking for a technical co-founder or strong AI/video developer to build the MVP with me and potentially grow into a long-term partnership.

⸻

What I’m building:

The tool solves a real pain point in video localization and repurposing. It combines several AI capabilities (speech, OCR, translation, video rendering) into one seamless product.

More details will be shared after a short intro call + NDA.
I’m happy to walk you through everything — I already validated the idea with creators and agencies.

⸻

Who I’m looking for:

You don’t need to know everything, but ideally you’re comfortable with:
• AI pipelines: Whisper, OCR (Tesseract / Google Vision), GPT / DeepL, etc.
• Text-to-Speech (like ElevenLabs / Play.ht)
• Video rendering tools: FFMPEG, OpenCV, or frameworks like Remotion
• Building APIs (FastAPI, Node.js, etc.)
• A basic frontend (React/Next.js is fine)
• Bonus: you’ve shipped an AI product or video tool before

⸻

About me:
• I’m a full-time entrepreneur with strong marketing, distribution & monetization skills.
• I’ve built audiences on multiple platforms and have early interest from potential users.
• I’m looking for someone to build, ship fast, and think long-term.

⸻

Structure:
• Open to paid MVP work (hourly or fixed)
• Open to equity if there’s a great fit
• I’ll handle product, vision, users, and go-to-market — you focus on the build

⸻

To apply:
• Share your experience with AI/video-related projects
• Link relevant repos, demos, or tools you’ve built
• Let me know your availability and rate (or interest in equity)

Let’s build something that genuinely solves a real need and scales fast.

Skills: AI Development, SaaS, Artificial Intelligence

I'm looking for an experienced AR web app developer to create an AR web app optimized for desktop browsers.

Scope of work:
User opens a browser URL/scan QR code.
Grants camera access.
Holds target image in front of the webcam.
Video plays automatically on recognition.


Scope of Work
1. Core Functionality
Image Recognition: Detect specific 2D images (e.g., cards, logos) using a laptop/webcam feed.
Video Activation: Play a pre-recorded video overlay when the target image is recognized.
Web-Based AR: No app installation required—runs directly in a browser.

2. Technical Components
Target Image Preparation:
High-contrast, unique imagery (e.g., logos, geometric patterns) for reliable tracking.
Optimized file formats: .jpg, .png, or .jpeg.

AR Tracking System:
Support for flat/curved surfaces (e.g., cards, bottles).

Video Integration:
Preloaded or streamed video triggered on target detection.


Skills & Experience:
- Previous work on AR projects is highly preferred.
- Strong knowledge of web development languages, AR libraries and frameworks.
- Excellent problem-solving skills and ability to work independently.
- Unity Skillset is not required

Skills: CSS, HTML, OpenCV, Three.js

C++ Developer for Video Effects Library (CLI & GUI)

We are looking for an expert C++ developer to create a high-performance video effects library that can be called via CLI. The library should include customizable video effect templates similar to those on Hypno.com . it must support CLI AND GUI from which we can give him source video with required assets like(intro/outro, overlays etc)

Responsibilities:

Develop a C++ library to process videos and apply video template effects.

Implement/Create similar attracted video effects templates similar to Hypno.com .

Provide a CLI interface to apply effects using input parameters (effect name, source video, intro/outro, overlays etc.).

Develop a GUI interface to allow customization of effect templates.

Optimize for performance and compatibility across platforms (Windows/macOS/Linux).

Deliver fully documented source code and assist in integration with our existing software.

Requirements:

Strong C++ programming skills with experience in video processing.

Expertise in OpenCV, OpenGL, Vulkan, FFmpeg, or similar video processing libraries.

Experience with GUI frameworks like Qt, ImGui, or custom OpenGL interfaces.

Knowledge of multithreading and GPU acceleration for real-time processing.

Prior experience with CLI-based applications and command-line argument parsing.

Ability to work independently and deliver a production-ready solution.

Nice to Have:

AI Imagery and videography skills

Experience with shader programming (GLSL, HLSL, or Vulkan shaders).

Familiarity with machine learning-based video effects.

If you believe that your skills and expertise align with the requirements of this position, please send us your resúme for review. Additionally, if you have a portfolio or examples of previous work, we would be interested in seeing them. We are eager to assess your qualifications and establish a cooperative relationship as soon as possible.

We look forward to hearing from you.

Skills: C++, FFmpeg

Job Description

Job Title: Blender API Engineer
Job Type: Full-time
Location: Remote



Job Summary:

Join our innovative team as a Blender API Engineer, where you will develop and refine 3D workflows using Blender's Python API. This pivotal role requires scripting expertise, automation skills, and tool development to elevate 3D content creation and production pipelines. We seek a candidate proficient in Python programming, Blender's API, and cutting-edge procedural modeling techniques.



Key Responsibilities:

Develop and maintain custom Blender scripts and plugins using Python.
Automate 3D modeling, rendering, and animation workflows in Blender.
Integrate Blender with external tools, game engines (Unity, Unreal), and other APIs.
Create procedural generation tools and automation scripts to enhance efficiency.
Optimize existing Blender scripts for performance, scalability, and usability.
Collaborate with artists, animators, and developers to improve asset pipelines.
Debug and troubleshoot issues in Blender scripting and automation.


Required Skills and Qualifications:

Strong expertise in Blender’s Python API and scripting for automation.
Proficiency in Python, with experience developing add-ons and custom tools.
Experience with procedural modeling, 3D geometry processing, and automation.
Understanding of rendering engines (Cycles, Eevee) and shader scripting.
Familiarity with game development pipelines and integrations (Unity, Unreal) (preferred).
Knowledge of PBR materials, shader scripting, and texture automation.
Strong debugging skills and familiarity with version control (Git, SVN).


Preferred Qualifications:

Prior experience in gaming, animation, or VFX industry.
Experience with machine learning for 3D applications.
Familiarity with OpenCV, NumPy, SciPy for 3D data manipulation.


Why Join Us?

Work on cutting-edge 3D automation and AI-driven procedural generation. Collaborate with a team of expert developers and artists. Opportunity to develop and implement innovative Blender tools. Flexible work environment with remote work options.

Skills: Blender, Python

FREELANCERS ONLY!

Hi, I am looking to hire a full-stack freelance AI developer immediately. You must be able to do a video interview and start right away.

Requirements:
• Availability to work 9 hours with a 1-hour break, at your preferred timezone Monday–Friday.
• Strong experience in Python and AI/ML frameworks (TensorFlow, PyTorch, Scikit-learn, OpenCV).
• Experience with Large Language Models (LLMs), NLP, or Computer Vision is a must.
• Backend development experience with Django/FastAPI/Flask.
• Proficiency in working with APIs (OpenAI, Hugging Face, etc.).
• Knowledge of cloud platforms like AWS, GCP, or Azure.
• Experience with Foundry and blockchain integration with AI is a plus.
• Experience with fine-tuning models and deploying AI applications.
• Ability to convert ideas or research papers into working AI models.
• Strong understanding of AI ethics and best practices.

What We Expect:
✅ Punctual and honest
✅ Understand UX/UI for AI applications
✅ Speak and write clear English
✅ Willingness to learn and try new techniques
✅ Freelancer only (must be looking for long-term work)

Job Description:
You will handle multiple AI projects at once, ranging from AI-powered web apps to LLM-based tools. The work includes:
• Developing AI models and integrating them into web or mobile applications.
• Building AI-powered chatbots, recommendation systems, and automation tools.
• Deploying AI models on cloud servers and optimizing performance.
• Working with datasets to clean, preprocess, and fine-tune models.
• Collaborating on innovative AI-driven solutions for various industries.

Salary:
The starting salary will be $600 per month, with an automatic raise after three months.

Interview Process:
You should be available for a video interview and ready to start immediately.

Write "I am an AI freelancer" in your cover letter and mention your 5 best AI projects.

Thanks!

Skills: Python, Artificial Intelligence, API, Machine Learning

I'm seeking a skilled Python developer with extensive experience in OpenCV to help debug my human body recognition code.

Key Requirements:
- Expertise in Python
- Proficient in using OpenCV
- Previous experience in debugging code
- Ability to identify and rectify issues leading to incorrect results

The code is currently producing incorrect results. I need someone who can quickly pinpoint the issues and provide a solution. Your ability to understand complex algorithms and work under pressure will be highly valued. Please provide examples of similar projects you've worked on in your proposal.

Skills: Python, Software Architecture, Machine Learning (ML)

The project has a goal of delivering an OCR solution using a Festo's Universal Sensor SBSC-U-AF-R2B hardware & Festo's SBS Vision Sensor Software. The OCR module has a task of detecting orthogonal sequence of arabic numerals. As the project is limited to the usage of SBS Vision Sensor Software & its readily available OCR modules, a freelancer that is experienced with it would be a preference. The project has a potential to develop into more subsequent projects.

Skills: Computer Vision, OpenCV, Python, OCR Algorithm, Artificial Intelligence, Machine Learning

Overview:
Build a face-tracking AR filter that uses image recognition to measure eyes for lash application. The filter draws lines on the user’s face, identifies eye shape (almond, round, slim), plane (ascending, descending, even), set (wide, close, proportionate), and eyelid type, then recommends lash styles.
Responsibilities:

- **Filter Creation:** Implement real-time face tracking and overlay lines for eye measurements.
- **Image Recognition:** Detect eye landmarks, measure distances/angles, classify shapes, and eyelid types.
- **User Interface:** Design a clear, intuitive AR experience aligned with brand colors and fonts.
- **Optimization & Testing:** Ensure smooth performance on various devices and in different lighting.
- **Iteration:** Update features based on user feedback and maintain compatibility with AR platforms.
**Requirements:**
- Proficiency in AR development (Spark AR, Lens Studio, Unity) and computer vision (e.g., OpenCV).
- Experience translating facial measurements into on-screen overlays.
- Strong collaboration skills with design and beauty teams.

To apply, submit your resume and samples of relevant AR/computer vision working

Skills: Augmented Reality, Facial Recognition

Project Title:
Cloud-Based AI Pipeline (YOLO + OCR) for Extracting Data from Dynamic Screens via Image Input

Description:
We are developing a system that captures images of dashboards/screens and extracts key labeled values (e.g., “Label AB,” “Label XY”) using a camera.
Our internal team handles the hardware/camera system and uploads images to the cloud.

We are looking for an experienced AI/ML + Azure cloud developer to build the cloud-side inference pipeline using computer vision + OCR techniques. The entire system must be Dockerized and deployed on Azure.

Scope of Work:
☁️ 1. AI/ML Inference Pipeline on Azure
Receive uploaded screen images from Azure Blob or an API

Preprocess images for:

Blur detection

Glare/reflection handling

Shadow correction

Screen cutoff validation

Use object detection (e.g., YOLO) to detect key screen regions ("Label AB", "Label CD", etc.)

Use OCR to extract numeric or alphanumeric values next to those labels

Match labels → values dynamically (layout agnostic)

Return structured JSON output including:

Detected values

Confidence scores

Any errors or quality issues flagged

? 2. Error & Validation Handling
Flag and tag issues such as:

Image is too blurry

Value not detected

Label missing

Low OCR confidence

Screen not fully visible

Provide this metadata in a clean JSON format

Example:

json
Copy
Edit
{
"label_ab": {
"value": "97",
"confidence": 0.91
},
"label_cd": {
"value": null,
"error": "Label not detected"
},
"image_quality": {
"sharpness_score": 28.5,
"glare_detected": true,
"issues": ["Blurry", "Cutoff at top"]
}
}
? 3. API Development (for mobile app integration)
REST API endpoints to:

Receive an image from the device

Return extracted values + validation flags

(Optional) retrieve previous results by ID or timestamp

API must include image error feedback that our mobile app team can consume and display to users during or after upload.

? 4. Dockerization & Deployment
Package the full pipeline into a Docker container

Deploy to Azure Container Instance or similar

Provide documentation for:

Building and running the container

Updating the model or logic

Environment variables and settings

? 5. Feedback Loop + Retraining Folder Setup
Save flagged/failed cases in a retraining-friendly folder structure

bash
Copy
Edit
/flagged_cases/
/retrain_data/
(Optional) provide a script or structure for retraining the model with new labeled data later

Support manual model upgrading (drop-in new model + rebuild Docker)

?️ Tech Stack Required:
Python (preferred)

OpenCV, PyTorch or TensorFlow

YOLOv5/YOLOv8 or similar detection model

OCR: EasyOCR, Tesseract, or PaddleOCR

Azure Blob Storage, Azure Functions or HTTP Trigger

Azure Container Instance (ACI) or App Service

REST API: FastAPI or Flask

Docker

✅ What We Provide:
Sample labeled screen images (2 dashboard layouts)

Base model checkpoint (if needed)

Azure environment + access

Input/output format specs

Our team handles image capture and uploads

? Deliverables:
Dockerized AI pipeline

Deployed on Azure (ACI preferred)

REST API with:

JSON outputs for detected labels + values

Error tagging + image quality flags

Folder structure + simple script for future retraining

Clear deployment + update documentation

✨ Nice to Have (Bonus):
Experience with model versioning

CI/CD familiarity (Docker push → deploy flow)

Ability to collaborate on feedback-based model improvement

Skills: Machine Learning (ML), Docker, OpenCV, Computer Vision, Microsoft Azure

I'm building a tool that auto-generates short videos from a user-written script. Here's the basic flow:

User selects a video dimension (1:1, 9:16, 4:5, or 16:9).
→ All uploaded video clips should be automatically trimmed/resized to this format.

User writes a script and highlights words or phrases.
→ They then assign a video clip to each highlighted word (from their local device or a pre-uploaded media library).

Voiceover is generated using the ElevenLabs API based on the full script.

Aeneas is used to sync the voiceover audio with the highlighted words (word-level or phrase-level alignment).

Each assigned video clip is trimmed to match the word's timestamp range and should be processed in parallel for speed (FFmpeg).

The final video is assembled using FFmpeg, combining the clips, subtitles, and audio.

Skills: FFmpeg, Video Stream, Python, API, C++, Python Script, Linux, JavaScript, MySQL, OpenCV

We are seeking a highly experienced Lead Data Scientist to join our team on Upwork. The ideal candidate is a hands-on expert in machine learning and data engineering with strong leadership skills and the ability to drive end-to-end ML solutions.

Tech Stack:

- Languages & Libraries: Python, TensorFlow, PyTorch, Scikit-learn, XGBoost, OpenCV, NLTK, Pandas, NumPy, SciPy

- Data & ML Engineering: Apache Kafka, Apache Spark, Airflow, MLflow, Docker, Kubernetes

- Databases: PostgreSQL, BigQuery, Neo4j

- Cloud: AWS

Requirements:

- Proven experience leading ML projects from prototype to production

- Fluent in English with excellent communication skills

- Available to work US business hours

- Strong problem-solving skills and ability to mentor junior team members

Nice to Have: Graph databases (Neo4j), MLOps experience, real-time data pipelines

Skills: Natural Language Processing, TensorFlow, PyTorch, pandas, Python

I'm looking for a skilled AI developer or machine learning engineer to help build a tool that can analyze a photo of an item and identify what it is.

The goal is to create an AI system that can take an image (uploaded by a user or captured via camera) and return a description, category, or even a specific product name. This could be something like:

User uploads a picture of a sneaker → Tool returns: "Nike Air Max 90" or "Running Shoe"

Picture of a mug → Tool returns: "Ceramic Coffee Mug" or "Drinkware"

🛠️ Skills & Experience Required:
Strong experience in Computer Vision and Image Recognition
Familiar with object detection and image classification
Proficiency in TensorFlow, PyTorch, or similar ML frameworks

Experience with pre-trained models (e.g. YOLO, ResNet, EfficientNet) and/or building custom models
Knowledge of OpenCV and image preprocessing techniques

Ability to work with labeled datasets or guide data collection/labeling

Bonus: Experience deploying models to the cloud or on mobile apps

🔍 What I Need Help With:
Consulting on the best approach for this tool

Model development (using existing models or training a custom one)

Model evaluation and refinement

(Optional) Basic prototype or UI to test the model

💬 To Apply:
Please share:

Relevant past projects (especially anything involving image classification or object detection)

Your preferred tech stack

Any thoughts on how you'd approach a project like this

Your availability and rough estimate of how long something like this might take

Looking forward to hearing from you!

Skills: AI Model Training, AI Model Development, Computer Vision, Machine Learning

Description:
We are looking for an experienced AI developer to help us integrate a real-time object recognition system using Meta Ray-Ban Smart Glasses. The goal is to livestream to Instagram while analyzing the feed to recognize and identify objects in real-time, displaying the results on a connected mobile phone.

Key Requirements:
- Experience with computer vision and real-time object recognition
- Proficiency in Python, OpenCV, TensorFlow, or similar AI/ML frameworks
- Familiarity with Meta Ray-Ban Glasses SDK and Instagram Live API
- Ability to process live video streams and overlay recognized objects
- Experience with API integration for real-time data transfer to mobile

Project Scope:
- Enable Instagram Live streaming from the Meta Ray-Ban Glasses
- Process the live video feed to detect and recognize objects
- Stream real-time object recognition results to a mobile app or overlay on the video

Skills: API, Computer Vision, Real Time Stream Processing

About Us:

We are an innovative team passionate about creating cutting-edge augmented reality experiences. We're developing a groundbreaking AR application that will revolutionize how users interact with their environment. Our app will utilize smartphone camera input to detect and recognize real-world objects, providing dynamic visual overlays and interactive information. We are seeking a talented and driven AR App Developer to bring this vision to life.

Our project involves developing an AR application that:

Uses the smartphone's camera feed to detect and recognize objects in real-time.

Employs computer vision and machine learning techniques for accurate object identification. (Knowing how to train or pull from YOLO websockets will be a plus)

Generates and displays dynamic visual overlays based on the detected objects.

Potentially integrates interactive elements and user input.

Optimizes performance for smooth and responsive AR experiences on mobile devices, with specific emphasis on Android.

Required Skills and Qualifications:

Proven experience in developing AR applications for mobile platforms (Android).

Strong proficiency in Unity (or other relevant game engine) and C# (or similar).

Experience with AR SDKs such as ARKit, ARCore, or Vuforia.

Understanding of computer vision and machine learning concepts.

Experience with object detection and recognition libraries (e.g., TensorFlow Lite, OpenCV).

Experience with the Android SDK, including configuration, building, and deployment.

Strong understanding of mobile app development principles and best practices.

Excellent problem-solving and debugging skills.

Ability to work independently and collaboratively with non-technical stakeholders to understand their requirements from a more layman perspective.

Experience with optimizing mobile applications, writing code with the ability to be cross-platform down the line and code reusability by coding onto standardised languages.

Preferred Skills:

Knowledge of cloud-based services for data storage and processing.

Experience with cross-platform development.

Experience with machine learning model creation.

Experience in creating AR app that was focused for Education and Training purposes

Experience in creating customised 3D art to be used in AR

Communication of technical terms and code to provide an efficient and lean coding solution, providing layman explanations on how to reconfigure app and putting in brand new plugins down the line on what was built.


Disclaimer: "All code, assets, and deliverables created by the developer as part of this project will be the sole and exclusive property of us. The developer agrees not to use, distribute, or reproduce any of the code or assets created for this project for any other purpose, including personal or commercial projects, without the express written consent from us. This includes any algorithms, machine learning models, UI elements, or other software components developed during the term of this contract."

Skills: Artificial Intelligence, Machine Learning, Augmented Reality, TensorFlow, Virtual Reality

I have a C application that interacts with a specific website. The app currently uses a hybrid approach of manual and auto solving for text-based captchas. I want to transition to a fully automated, unlimited captcha solver using Machine Learning/AI. Your task would be to integrate this into my existing source code.

Ideal candidates should have:
- Proficiency in C/C++ programming
- Extensive experience with Machine Learning/AI
- Familiarity with captcha solving methodologies

Skills in OpenCV and TensorFlow would be beneficial as these libraries are used in my source code. As a freelancer, your understanding of captcha systems and ability to implement a seamless solution is crucial. The goal is to enhance the app's efficiency and effectiveness in bypassing captcha challenges without manual intervention. Please provide examples of similar projects you've completed in your bid.

Skills: C Programming, Java, Matlab and Mathematica, C# Programming, C++ Programming

These are acceptance criteria for backend code

1) Run 30+ cameras on one t4 instance
2) Make real-time streaming stable, without flickering and delays
3) Check mongoDB usage and optimize it
4) Fix bottlenecks
5) These changes cannot affect current system functions and should work as it was but with improvements (so nothing breaks in functionalities when implementing updates)
6) Launchable tool after improvements

Skills: Artificial Intelligence, Machine Learning, Python, Computer Vision, Natural Language Processing, Large Language Model, Generative AI, Digital Signal Processing, Deep Learning, Time Series Analysis, Chatbot Development, OpenCV, PyTorch, TensorFlow, Data Preprocessing

I need a Python expert with OpenCV experience to review my system that tracks people entering and exiting a designated zone. Using a pre-trained machine learning model, which I've uploaded on a server, you'll review a program that logs each person's entry and exit. I’ve already done everything but need someone to check why it’s producing errors with video decoding. I’ll share my screen and we can work together. It’ll include cpu core optimization and live video streaming.

Key Requirements:
- Proficiency in Python
- Experience with OpenCV
- Familiarity with machine learning models
- video streaming

Please include in your application:
- How you think you can solve it

Skills: Python, Software Architecture, Machine Learning (ML)

I'm building a tool that auto-generates short videos for tiktok, so I am am working it with FFmpeg C++ library and for now I need to customize FFmpeg C library for AV1 and H.265 Encoding/Decoding.

Responsibilities
Develop a GUI interface to allow customization of effect templates.
Develop a C++ library to process videos and apply video template effects.
Implement/Create similar attracted video effects templates

Requirements
Strong C++ programming skills with experience in video processing.
Expertise in OpenCV, OpenGL, Vulkan, FFmpeg, or similar video processing libraries.
Experience with GUI frameworks like Qt, ImGui, or custom OpenGL interfaces.
Knowledge of multithreading and GPU acceleration for real-time processing.
Prior experience with CLI-based applications and command-line argument parsing.

We look forward to hearing from you.

Skills: C++, FFmpeg, C, C#, Desktop Application, .NET Framework, Qt Framework, OpenGL, Video Stream, API

Job Overview:
We are seeking a skilled Raspberry Pi Developer to join our team and contribute to the development of innovative embedded systems and IoT solutions. The ideal candidate will have extensive experience with Raspberry Pi hardware, software development, and interfacing with peripherals and sensors.

Key Responsibilities:
Develop and implement applications on Raspberry Pi for embedded and IoT projects.
Design and optimize software for performance and power efficiency.
Interface Raspberry Pi with various peripherals, including sensors, cameras, displays, and other hardware modules.
Develop and test Python, C, or C++ applications for real-time data processing.
Work with communication protocols such as SPI, I2C, UART, MQTT, and HTTP for device integration.
Configure and manage Raspberry Pi OS (Linux-based) and related software stacks.
Develop and integrate cloud-based services with Raspberry Pi devices.
Collaborate with cross-functional teams, including hardware engineers, software developers, and project managers.
Troubleshoot and debug software and hardware issues.
Document designs, code, and testing procedures for future reference and scalability.

Required Skills & Qualifications:
Bachelor’s degree in Computer Science, Electrical Engineering, or a related field (or equivalent experience).
Strong programming skills in Python, C, and/or C++.
Hands-on experience working with Raspberry Pi and embedded Linux systems.
Knowledge of IoT frameworks and cloud integration (AWS IoT, Azure IoT, Google Cloud IoT).
Experience with GPIO programming and interfacing with external hardware components.
Familiarity with networking protocols, including Wi-Fi, Bluetooth, and Ethernet.
Ability to read and understand electronic schematics and datasheets.
Strong debugging and problem-solving skills.
Experience with version control systems (Git, GitHub, GitLab).
Knowledge of containerization tools such as Docker is a plus.
Familiarity with AI/ML frameworks on Raspberry Pi (TensorFlow Lite, OpenCV) is an advantage.

Preferred Qualifications:
Experience developing industrial automation or home automation solutions using Raspberry Pi.
Knowledge of edge computing and real-time processing techniques.
Understanding of cybersecurity best practices for IoT applications.
Previous experience contributing to open-source Raspberry Pi projects.

Skills: Raspberry Pi, Raspberry Pi Firmware, Python, Linux, PHP, C++, Node.js

Job Overview:
We are seeking a skilled Raspberry Pi Developer to join our team and contribute to the development of innovative embedded systems and IoT solutions. The ideal candidate will have extensive experience with Raspberry Pi hardware, software development, and interfacing with peripherals and sensors.

Key Responsibilities:
Develop and implement applications on Raspberry Pi for embedded and IoT projects.
Design and optimize software for performance and power efficiency.
Interface Raspberry Pi with various peripherals, including sensors, cameras, displays, and other hardware modules.
Develop and test Python, C, or C++ applications for real-time data processing.
Work with communication protocols such as SPI, I2C, UART, MQTT, and HTTP for device integration.
Configure and manage Raspberry Pi OS (Linux-based) and related software stacks.
Develop and integrate cloud-based services with Raspberry Pi devices.
Collaborate with cross-functional teams, including hardware engineers, software developers, and project managers.
Troubleshoot and debug software and hardware issues.
Document designs, code, and testing procedures for future reference and scalability.

Required Skills & Qualifications:
Bachelor’s degree in Computer Science, Electrical Engineering, or a related field (or equivalent experience).
Strong programming skills in Python, C, and/or C++.
Hands-on experience working with Raspberry Pi and embedded Linux systems.
Knowledge of IoT frameworks and cloud integration (AWS IoT, Azure IoT, Google Cloud IoT).
Experience with GPIO programming and interfacing with external hardware components.
Familiarity with networking protocols, including Wi-Fi, Bluetooth, and Ethernet.
Ability to read and understand electronic schematics and datasheets.
Strong debugging and problem-solving skills.
Experience with version control systems (Git, GitHub, GitLab).
Knowledge of containerization tools such as Docker is a plus.
Familiarity with AI/ML frameworks on Raspberry Pi (TensorFlow Lite, OpenCV) is an advantage.

Preferred Qualifications:
Experience developing industrial automation or home automation solutions using Raspberry Pi.
Knowledge of edge computing and real-time processing techniques.
Understanding of cybersecurity best practices for IoT applications.
Previous experience contributing to open-source Raspberry Pi projects.

Skills: Raspberry Pi, Raspberry Pi Firmware, Python, Linux, PHP, C++, Node.js

We are looking for an experienced developer (or team) to build an AI-powered video analytics software similar to [Veesion](https://veesion.com/).

The software should use computer vision and deep learning to detect anomalies and suspicious activities in real-time video streams.

**Key Responsibilities:**
- Develop and train AI models for real-time object detection and anomaly recognition.
- Integrate machine learning models with a video processing pipeline.
- Optimize performance for real-time analysis with minimal latency.
- Implement a web-based dashboard for monitoring and alerts.
- Ensure scalability and compatibility with multiple camera feeds.
- Maintain security and data privacy best practices.

**Required Skills & Experience:**
- Strong experience in AI/ML, particularly in computer vision (YOLO, OpenCV, TensorFlow, PyTorch).
- Proficiency in programming languages like Python and C++.
- Experience in handling real-time video processing.
- Knowledge of cloud computing (AWS, GCP, or Azure) for AI model deployment.
- Frontend/backend development skills for web-based monitoring tools (React, Node.js, Django, or Flask).
- Prior experience working on video analytics or surveillance systems is a plus.

**Additional Information:**
- The project may evolve into a long-term collaboration.
- Developers with past experience in anomaly detection or similar projects will be preferred.
- Please share links to your previous work or relevant case studies.

Looking forward to working with talented developers who can bring this vision to life!

Skills: Artificial Intelligence, Machine Learning, TensorFlow