Sketic: a machine learning-based digital circuit recognition platform

Authors: MOHAMAMD ABDEL MAJEED, TASNEEM ALMOUSA, MAYSAA ALSALMAN, ABEER YOSEF

Abstract: In digital system design, digital logic circuit diagrams are built using interconnects and symbolic representations of the basic logic gates. Constructing such diagrams using free sketches is the first step in the design process. After that the circuit schematic or code has to be generated before being able to simulate the design. While most of the mentioned steps are automated using design automation tools, drafting the schematic circuit and then converting it into a valid format that can be simulated are still done manually due to the lack of robust tools that can recognize the free sketches and incorporate them into end user simulators. Hence, the goal of this paper is to construct and deploy computer simulation tools capable of understanding free sketches and incorporate them into useful simulation tools. Such a tool will be useful at both the educational and the industrial levels. Moreover, while this tool is designed to deal with sketched logic circuits, it can be generalized and applied to many other fields to convert the sketched design into a digital format. To implement this tool, we relied on the emerging machine learning and image processing concepts to make sure that the designed system is robust and accurate. Our results show that our system is able to recognize all the gates in the digital circuit with more than 95% accuracy.

Keywords: Digital logic circuits, logic gates, machine learning, deep neural networks, detection, recognition, classification

Full Text: PDF