Penglihatan Komputer Jobs

I have a sizeable batch of raw photographs that must be turned into a clean, AI-ready image-classification dataset. Every file simply needs a single or multi-label tag that tells my model whether it contains Vehicles, People, or both. No bounding boxes or pixel-perfect masks are required—just accurate whole-image labels. You’ll work in the annotation tool of your choice (LabelImg, CVAT, VoTT, Roboflow, etc.) as long as the final export is compatible with standard machine-learning pipelines. A comma-separated CSV or JSON with filename-to-label mapping is perfect. Selected classes • Vehicles • People Deliverables • Completed project file or export (CSV/JSON) listing each image and its assigned class(es) • The original images left unaltered in thei...

I am building a single cloud-based platform that can ingest electronic medical records and financial transaction streams, run advanced analytics on them, and surface clear, actionable insights. The core purpose is data analysis, and the feature set revolves around three pillars: Natural Language Processing to understand free-text notes and statements, Computer Vision to read scans or receipts, and Predictive Analytics to flag risk, forecast trends, and recommend next steps. You would take the lead across the full stack: designing ingestion pipelines, structuring secure databases, crafting and training the models, and exposing everything through clean REST/GraphQL APIs and a lightweight web dashboard. Experience weaving together healthcare and fintech data in a HIPAA- and PCI-aware manner ...

I need an end-to-end, browser-based MVP that lets kindergarteners learn Mandarin through printed word cards that “come alive.” The web app should use the device camera to recognise each card—individually or in sentence pairs—and immediately launch an animation on top of it via WebAR. Children then speak the word or sentence; the system listens, judges it in Mandarin and, when a syllable is off, gives an instant correction suggestion verbally the child can imitate before moving on. Four themed learning scenes must be interconnected so a class can start anywhere and cycle until all four are finished. When a new card is recognised inside a scene, its matching video should autoplay without extra taps. Every interaction, score and completion tick feeds a simple teacher ...

I'm seeking an expert to analyze infrared images of animals. The goal is to identify unique skin patterns, assign unique identification numbers, and track individual animals for population estimation. Key Tasks: - Analyze IR images to identify animals. - Recognize and document unique skin patterns. - Assign unique identification numbers. - Collaborate on integrating with image analysis software and a database for storing information. Ideal Skills and Experience: - Experience with image analysis, particularly in animal identification. - Familiarity with IR imaging technology. - Strong database management skills. - Ability to integrate multiple software components. Looking for someone who can provide accurate, reliable data to help in tracking animal populations.

I need a license-plate recognition engine that can reliably read Qatar, UAE, and Saudi Arabia plates when they appear in either still images or live video streams. High accuracy is non-negotiable—I am targeting production-level performance suitable for enforcement and analytics, so false positives must be minimal and confidence scores exposed. To succeed you will design, train, and package a full ANPR pipeline that: • detects the plate region in diverse lighting and angles, • recognises Arabic and Latin characters as well as the specific colour codes and icons used across the three countries, and • delivers results fast enough for real-time video (traffic-camera frame rates) while also accepting batch image inputs. Please outline your preferred tech stack (Open...

Project Overview We are seeking an experienced US Registered Patent Attorney (or USPTO-registered patent agent) to review, refine, and file a Provisional Patent Application (PPA) for a medical robotics and Quality Assurance system. Key Responsibilities Drafting & Claim Seeding: Review our technical dossier, system architecture diagrams, and enablement specs to draft an attorney-ready Provisional Patent Application with initial claim seeding (Method, System, Software, and Safety Framework). USPTO Filing: Handle the formal USPTO PPA submission, including Micro-Entity status certification (Form SB/16). Inventorship & Assignment Review: Verify invention assignment documentation and inventorship logs. Required Qualifications USPTO Registration: Must be a licensed attorney registe...

I need to fine-tune an existing computer-vision model for object detection so it performs reliably on my custom dataset. The base architecture is already selected; the task now is to prepare the data, set up transfer-learning, run hyper-parameter sweeps, and deliver a set of weights that reach an agreed-upon mAP on a held-out validation split. You may use PyTorch, TensorFlow, or another mainstream framework as long as the final model can be exported to ONNX. Please share examples of past work where you have successfully fine-tuned or trained object-detection networks—links to repos, papers, or short demos are ideal. Once we decide on the starting checkpoint and training environment, I’ll supply labeled images, class definitions, and any additional annotations you need. Delive...

I’m looking for someone who can help me find relevant projects on Freelancer.com, write targeted proposals, and manage/improve my existing portfolio. The Freelancer.com account is new, so there is no previous client history or completed projects on the account yet. The goal is to build the profile gradually by finding genuine projects that match my actual skills and getting the first few successful clients. Main areas: * AI & Data Science * Python * Machine Learning / Deep Learning * AI Automation * Chatbots * Computer Vision * Web Development * Graphic Design What I need: * Find relevant projects * Write customized proposals * Avoid wasting bids on irrelevant projects * Track bids and client responses * Help organize and present my existing projects professionally * Help bu...

I’m assembling a fresh video dataset focused on activity recognition and I need original footage of real-world daily routines. The goal is to train computer-vision models, so every clip must clearly show the action and end with enough “idle” frames for clean labeling. What I’m looking for • General actions such as walking through a hallway, sitting down, eating, opening doors, using a phone. • Specific tasks like brushing teeth, cooking a meal, tying shoelaces, folding laundry, making coffee, watering plants. Feel free to capture these moments indoors or outdoors, in different lighting conditions, camera angles, and with varied backgrounds. Diversity of age, gender, and setting is strongly encouraged. Recording guidelines • Shoot in 1080p o...

I’m looking for someone who can help me find relevant projects on Freelancer.com, write targeted proposals, and manage/improve my existing portfolio. The Freelancer.com account is new, so there is no previous client history or completed projects on the account yet. The goal is to build the profile gradually by finding genuine projects that match my actual skills and getting the first few successful clients. Main areas: * AI & Data Science * Python * Machine Learning / Deep Learning * AI Automation * Chatbots * Computer Vision * Web Development * Graphic Design What I need: * Find relevant projects * Write customized proposals * Avoid wasting bids on irrelevant projects * Track bids and client responses * Help organize and present my existing projects professionally * Help bu...

I’m preparing a postgraduate research paper in Computer Vision based on an existing university Capstone project titled “A Vision-Based Sleep Posture Recognition System.” I will provide the original project, university assessment requirements, formatting template, and supporting materials. I need a highly experienced academic researcher, not a general content writer. The work requires a rigorous literature review, critical analysis of the existing project and its results, and high-quality academic writing and editing suitable for a conference-style paper. All references must be genuine, verifiable, peer-reviewed academic sources, preferably recent IEEE, Elsevier, Springer, or reputable conference/journal publications, with proper IEEE referencing. Requirements: • S...