Motivation:
The aim of developing Imgcook is largely due to the heavy business code (duplicate view development). Honestly, most of the requirement and codes are redundant work which stimulates the demanding of directly generating codes based on the screenshot to free the labor that invests in redundant work.
Approaches:
In terms of the approaches, the Imgcook works in a way where transfers the sketch/screenshot to the middle structure and maps the middle structure into certain code paradigm like React or Vue.
Thus, the core part is to recognize components and patterns from a sketch and translates them into the middle representation. In this part, a bunch of technologies like OpenCV, edge detection, SSD and RNN are applied to ensure the outcome.
Current:
Right now, the Imgcook has involved in real production. And it has dramatically increased the efficiency of converting the sketch to real code. Normally, a sketch that needs 6 hours to implement will be reduced to 1 or .5 hour. And they are trying to continuously develop it comprehensively for more functionalities like a logic generation and customized code style.