So, we come to the last section of the very first chapter. I will keep it short and to the point since you as a reader can safely skip it. The topic of our discussion is OpenCV 4.0.

OpenCV 4.0 is a result of three and a half years of hard work and bug fixes by OpenCV and was finally released in November 2018. In this section, we will look at some of the major changes and new features in OpenCV 4.0:

• With the OpenCV 4.0 release, OpenCV has officially become a C++11 library. This means that you have to make sure that a C++11 compliant compiler is present in your system when you are trying to compile OpenCV 4.0. 
• In continuation of the previous point, a lot of C APIs have been removed. Some of the modules that have been affected include Video IO module (videoio), Object Detection module (objdetect), and others. File IO for XML, YAML, and JSON have also removed the C API.
• OpenCV 4.0 also has a lot of improvements in the DNN module (the deep learning module). ONNX support has been added. Intel OpenVINO also marks its presence in the new OpenCV version. We will be looking into this in some more detail in our later chapters. 
• OpenCL acceleration has been fixed on AMD and NVIDIA GPUs. 
• OpenCV Graph API has also been added, which is a highly efficient engine for image processing and other operations.
• As in every OpenCV release, there have been a lot of changes with the purpose of improving the performance. Some new features such as QR Code Detection and Decoding have also been added.

In short, there have been a lot of changes in OpenCV 4.0 and they have their own uses. For example, ONNX support helps in the portability of models across various languages and frameworks, OpenCL reduces runtime for computer vision applications, Graph API helps in increasing the efficiency of the applications, and the OpenVINO toolkit uses Intel's processors and a model zoo to provide highly efficient deep learning models. We will be focusing primarily on OpenVINO toolkit and DLDT as well as accelerating computer vision applications in later chapters. But, I should also point out here that both OpenCV 3.4.4 and OpenCV 4.0.0 are being modified at a high speed to fix bugs. So, if you are going to use either of them in any application, be prepared to modify your code and installation to incorporate the changes made. On a similar note, OpenCV 4.0.1 and OpenCV 3.4.5 are also out within a few months of their predecessors.