Machine Learning Based User Interface Generation

Every product development starts with idea conceptualization and design. The ideators and designers first choice is sketching the idea to conceptualize the product. After a few iterations of product design, mockups/prototypes are passed to developers who have the job of converting these designs into a functional product by grasping the design concepts and using their coding skills. Utilizing the advancements in deep learning and computer vision technologies, gap between designers and developers is bridged by simplifying the product development process. This will also help people with little or no knowledge of web development to bring their design ideas into reality. The service will consist of two stages firstly accepting images of web mockups including hand-drawn sketches and identifying the various HTML components in the sketch using Convolutional Neural Networks and tag them appropriately, secondly, the identified components will be converted to structured JSON files which will be converted to code based on HTML5, Flexbox and Bootstrap.

[1]  Tony Beltramelli,et al.  pix2code: Generating Code from a Graphical User Interface Screenshot , 2017, EICS.

[2]  Ray Smith An Overview of the Tesseract OCR Engine , 2007 .

[3]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Imran Sarwar Bajwa,et al.  Web Layout Mining (WLM): A New Paradigm for Intelligent Web Layout Design , 2006, 2006 ITI 4th International Conference on Information & Communications Technology.

[5]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[6]  Premanand K. Kadbe,et al.  Real time finger tracking and contour detection for gesture recognition using OpenCV , 2015, 2015 International Conference on Industrial Instrumentation and Control (ICIC).

[7]  Shin'ichi Koike Adaptive threshold nonlinear algorithm for adaptive filters with robustness against impulse noise , 1997, IEEE Trans. Signal Process..

[8]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[10]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.