Web Components Template Generation from Web Screenshot

Abstract

AI-driven automation is the game-changer in this decade. The one concept that belongs to this domain is to simulate human working processes by using machine learning. An adaptation of this knowledge in web development is popularized topic in the web developer society. Moreover, Web Components, the new paradigm in software engineering practices in web development, becomes the new standard defined by World Wide Web Consortium (W3C). It is an essential building block for modularizing large and complex web applications into smaller pieces and then presenting them via the web browser on the user's computer or mobile. We combine knowledge between Computer Vision (CV) with deep learning and Web Components developer framework together to train the machine to recognize bounding boxes and category labels for each object of interest in an image. This paper introduces the methodology to automatically generate a website by neuron network model composite with many small web components. Our work's best result has a validation loss of 1.873, which can recognize the web object and transform it into the Web Components Template by React web framework.