The startup offers an open-source computer vision platform that provides state-of-the-art algorithms and a no-code interface for building workflows. This enables developers to create, test, and deploy computer vision applications efficiently without requiring specialized expertise.
Funding
$640K raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Developing and deploying computer vision applications often requires specialized expertise, dealing with complex installations, managing dependencies, and ensuring compatibility across different frameworks. This complexity can slow down the prototyping process and increase the time-to-market for AI solutions.
Solution
Ikomia offers an open-source computer vision platform designed to streamline the creation, testing, and deployment of AI solutions. The platform provides a comprehensive suite of tools, including a Python API, a desktop application (STUDIO), and a library of over 300 pre-packaged, state-of-the-art algorithms (HUB). These algorithms are encapsulated in modules with standardized input/output formats, ensuring interoperability across different frameworks such as OpenCV, Kornia, OpenMMlab, YOLO, Scikit, Detectron2, and HuggingFace. Ikomia simplifies the development process by automating installations, managing dependencies, and providing a no-code interface for building workflows, enabling users to focus on creating custom AI solutions without the need for extensive DevOps knowledge.
Target Audience
Ikomia is designed for computer vision engineers, data scientists, and AI developers who need a streamlined, open-source platform for building, testing, and deploying custom AI solutions.
Features
- Ikomia HUB: A curated library of over 300 ready-to-use, open-source computer vision algorithms with standardized Python commands.
- Ikomia API: A Python API that allows developers to prototype, train, test, and build computer vision workflows with a few lines of code, eliminating installation and compatibility issues.
- Ikomia STUDIO: A desktop application that provides a user-friendly, no-code interface for building inference and training pipelines using a drag-and-drop system.
- SCALE: An automated deployment SaaS platform that transforms computer vision workflows and models into ready-to-use endpoint APIs, deployable on cloud or on-premise infrastructure.
- Multi-framework support: Algorithms from various frameworks (OpenCV, OpenMMlab, Detectron2, YOLO, HuggingFace, etc.) are made interoperable through standardized input/output formats.
- Dataset loaders: Support for loading custom annotated data from various sources like Roboflow and CVAT.
- Workflow export: Workflows can be exported in JSON format for easy reuse and deployment on different machines.
- Integration with MLflow and TensorBoard for experiment monitoring.