LQ Visual Inspector
- 0 Collaborators
Leather Quality Visual Inspection: a purpose-built solution for faster, more accurate leather quality control ...learn more
Project status: Under Development
oneAPI, Robotics, RealSense™, Artificial Intelligence
Intel Technologies
oneAPI,
Intel Opt ML/DL Framework,
OpenVINO,
AI DevCloud / Xeon,
Intel Python
Overview / Usage
Manufacturing processes typically include one or more steps where the product is visually inspected for defects. Typically, visual inspection is a highly manual process that can be time consuming and prone to errors. The selection of leathers for car interiors is also done manually. This activity is therefore highly subjective and no technology is available to improve the quality/cost ratio and reduce human error.
Methodology / Approach
LQ Visual Inspector can help leather manufacturers for automobiles using a set of AI and computer vision technologies that enable manufacturers to transform quality control processes by automatically detecting leather product defects.
- Data Collection - Collect Image data set of different leather defects
- Data Annotation - Using the powerful and efficient OpenVINO Toolkit Computer Vision Annotation Tool (CVAT)
- Model Training - Train multiple Deep Learning models using Intel® oneAPI AI Analytics Toolkit (AI Kit) and TensorFlow Deep Learning framework
- Model Selection - Choose best performing Deep Learning architecture based on ROC/AUC, Accuracy and Precision.
- Inference - Perform model optimization and inference using Intel OpenVINO Toolkit
- Deployment - Integrate Intel Edge Software Hub for Edge to Cloud deployment environment
Technologies Used
- Computer Vision Annotation Tool (CVAT)
- Intel® oneAPI AI Analytics Toolkit (AI Kit)
- Intel OpenVINO Toolkit
- Intel Edge Software Hub