This project will no longer be maintained by Intel. Intel has ceased development and contributions including, but not limited to, maintenance, bug fixes, new releases, or updates, to this project. Intel no longer accepts patches to this project.
This repository contains Python* code samples which us the Open Source Computer Vision (OpenCV) Library. These code samples are a good starting point for developers, across a wide range of markets, who wish to develop more robust computer vision and analytic solutions.
The code samples are mainly in two categories: Diagnostics and Application
Diagnostic Samples:
Sample 01 - Version information and environment variables
Sample 02 - OpenCV build information
Sample 03 - Basic image test - overlay text
Sample 04 - Basic video test - stream and overlay text
Sample 05 - Checks for OpenCL™ availability
Sample 07 - Checks for hardware extension support
Application Samples:
Sample 06 - Video steam and capture image
Sample 08 - Watermarking still image
Sample 09 - Watermarking display stream
Sample 10 - Still image face and eye detection
Sample 11 - Real-time video face detection and tracking
Sample 12 - Real-time people counter
The twelve computer vision code samples in this repository have been optimized using Intel® Integrated Performance Primitives (Intel® IPP) and the Intel® Math Kernel Library (Intel® MKL). By following these code samples with the optimized libraries, you will be able to see performance improvements over the basic installation of OpenCV.
Tested:
Intel® NUC NUC6i7KYK with Intel® Core™ i7 (codename Skylake)
C++
Microsoft Windows® 10 + Microsoft Visual Studio* 2015
Python*
Ubuntu* 16.04.2 + Anaconda + Intel® Distribution for Python*
Microsoft Windows 10 + Anaconda + Intel® Distribution for Python*
- Latest Integrated Windows 10 Drivers
- Intel® SDK for OpenCL™ applications for Windows* (*Registration Required)
- Intel® Media SDK (*Registration Required)
- OpenCV v3.2.0
- Intel® Distribution for Python* (*Registration Required)
- Intel® Integrated Performance Primitives (*Registration Required)
- Intel® Math Kernel Libraries (*Registration Required)
- Intel® Threading Building Blocks
Drivers:
Intel® SDK for OpenCL™ Applications:
- Intel® SDK for OpenCL™ Applications
- Getting Started with Intel® SDK for OpenCL™ Applications
- Developer Guide for Intel® SDK for OpenCL™ Applications
Intel® Media SDK:
OpenCV:
Important: OpenCV v3.2.0 release can use vendor-provided OpenVX* and LAPACK/BLAS including Intel® Math Kernel Libraries for acceleration. Do not refer to outdated Intel® INDE documentation but directly refer to OpenCV documentation within the OpenCV v3.2.0 release.