2019 was an amazing year for community contributions from our Intel® DevMesh community portal. We are proud to announce 5 of the best AI projects submitted last year. These have been recognized for showcasing outstanding innovation and proof of concept development in the field of artificial intelligence.

As we get started in 2020, we are highly encourage and excited to see how this developer community will continue to develop and share work using our new Intel oneAPI Toolkits. Congratulations to the developer teams behind these amazing projects from 2019. Keep up the great work.

Identification of Pathological Disease in Plants - Powered by Intel® Distribution of OpenVINO™ Toolkit

Version 2.0 of the project "Identification of Pathological Disease in Plants Using Intel® Distribution of OpenVINO™ Toolkit". The system can now Identify 5 pathological diseases which are common not only in Indian agricultural lineup. This projects allows for untrained workers or automated systems to easily identify disease in crops using common smartphones or tablets, with the potential to save crops before they are ravished by disease. Created with Intel® DevCloud, Intel Opt ML/DL Framework, Intel Python, Movidius NCS, Multi-core, OpenVINO. Learn More

Peter Moss Acute Myeloid & Lymphoblastic Leukemia Detection System

The Peter Moss Acute Myeloid & Lymphoblastic Leukemia Detection System is an open source extension of the GeniSys AI Artificial Intelligence Network that allows you to upload AML/ALL test data and run classifications to detect positive and negative examples using Intel technologies. This project started as a family affair via the passion of developer to engage the research and academic community to create a faster more accurate means for early detection of this disease. Created using Intel OpenVINO, Intel® DevCloud, Movidius NCS Learn More

Flow-AI: Flow Dynamic based on Fujitsu AI-Solver technique

Fujitsu’s “AI-Solver” is a data-driven technique that can learn from physics-based simulation to instantly predict the principal field distribution of within a 3D space. It uses a deep learning framework to learn the response of a system from simulation data generated on arbitrarily-shaped geometries. The result is a new approach to flow dynamics, that can generate an accurate simulation in near real time. Created using Intel Python, MKL, and Movidius NCS Learn More

3D Printing Error Detection AI with Movidius and UP2

Using the power of AI to rescue 3D prints before they are unsalvageable. Popular 3D printer OctoPrint is deployed on an UP2 board and enhanced with the Movidius NCS to catch errors at the edge. This project started as a community project to assist large 3D print jobs in a local developer space. It has since become the basis for production grade quality assurance in manufacturing, reducing the time and need for human review. Created with Intel OpenVINO, Intel Opt ML/DL Framework, and Intel Movidius NCS Learn More

Cash Recognition for Visually Impaired

Powered by deep learning technology, a mobile app for visually impaired - that can recognize Nepalese bank notes using smartphone camera. Created using Intel Optimized Tensorflow/Keras, React Native (Android + iOS), Python Flask server, Intel DevCloud for training, Intel Movidius Neural Compute Stick, Intel NUC kit. Learn More