TAF PUBLISHING

Python software is one of the most popular languages for artificial intelligence applications, especially in the academic area, because of its easy syntax and ready-to-use libraries. But for industrial usage, due to the nature of the declarative languages, python is not the preferred language when it is needed to add more functionality to the application, like user interactions or other software abstractions, which needs more system resources and stability, especially in embedded systems. If there is not enough resource to build a new model for AI application for desired software language, it will be perfect to have the advantage of the ability of python in the AI field. Instead of creating one python application or more than one python layer in the system, it is efficient to abstract the AI application, which is written in python language, and handle all other activities with more efficient languages or frameworks. In this paper, we will see how we can use a visual python AI application, which communicates with another software layer written by C++ using the Qt framework for a user interface in an efficient way, running in the backend to handle only AI-related processes. In the example, the python application detects faces in the backend and sends related visual data to the frontend application using interprocess communication. The frontend application will be efficient from a memory usage perspective and flexible for customer usage in an industrial way. The whole working demo, consisting of a python face detection application and a C++ program, is available in the given GitHub link [1] and is explained in a detailed way for software design and the user interface, which will be written in QML language.