Shulou(Shulou.com)11/24 Report--

CTOnews.com December 29, the Intel open source computer vision library OpenCV 4.7 was officially released today. The new version brings a new ONNX layer, which greatly improves the convolution performance of DNN code.

OpenCV 4.7 supports OpenVINO 2022.1 QR code detection and improves decoding quality, supports FFmpeg 5.x branch version, NVIDIA CUDA 12.0, and provides SIMD acceleration for the self-built libjpeg-turbo library. The new version also supports H.264 / H.265 on Android, provides Huawei Teng CANN back-end support for DNN modules, and speeds up convolution processing in DNN modules.

The DNN module is introduced from OpenCV 3.3.The normal installation of OpenCV can use the model trained by the deep learning framework without any dependency, and the reasoning calculation can be realized by using the dnn interface of OpenCV.

CTOnews.com learned that Huawei Teng CANN, the abbreviation of Compute Architecture for Neural Networks, is a heterogeneous computing architecture launched by Huawei for AI scenarios. By providing multi-level programming interfaces, Huawei allows users to quickly build AI applications and businesses based on the Teng platform.

OpenCV, whose full name is Open Source Computer Vision Library, is a cross-platform computer vision library. OpenCV is sponsored and co-developed by Intel, issued under a BSD license, and can be used free of charge in the business and research fields. OpenCV can be used to develop real-time image processing, computer vision and pattern recognition programs.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.