EAI Endorsed Transactions on Scalable Information Systems 18(16): e12

Research Article

Segmentation and Recognition of Electronic Components in Hand-Drawn Circuit Diagrams

Download27 downloads
  • @ARTICLE{10.4108/eai.13-4-2018.154478,
        author={Momina  Moetesum and Syed  Waqar Younus and  Muhammad  Ali Warsi  and Imran  Siddiqi},
        title={Segmentation and Recognition of Electronic Components in Hand-Drawn Circuit Diagrams},
        journal={EAI Endorsed Transactions on Scalable Information Systems},
        volume={18},
        number={16},
        publisher={EAI},
        journal_a={SIS},
        year={2018},
        month={4},
        keywords={Hand-Drawn Circuit Diagrams, HOG Descriptor, SVM.},
        doi={10.4108/eai.13-4-2018.154478}
    }
    
  • Momina Moetesum
    Syed Waqar Younus
    Muhammad Ali Warsi
    Imran Siddiqi
    Year: 2018
    Segmentation and Recognition of Electronic Components in Hand-Drawn Circuit Diagrams
    SIS
    EAI
    DOI: 10.4108/eai.13-4-2018.154478
Momina Moetesum1,*, Syed Waqar Younus1, Muhammad Ali Warsi 1, Imran Siddiqi1,*
  • 1: Bahria University, Islamabad, Pakistan
*Contact email: momina.moetesum@bui.edu.pk , imran.siddiqi@bahria.edu.pk

Abstract

This paper presents an effective technique for segmentation and recognition of electronic components from hand-drawn circuit diagrams. Segmentation is carried out by using a series of morphological operations on the binarized images of circuits and discriminating between three categories of components (closed shape, components with connected lines, disconnected components). Each segmented component is characterized by computing the Histogram of Oriented Gradients (HOG) descriptor while classification is carried out using Support Vector Machine (SVM). The system is evaluated on 100 hand-drawn circuit diagrams with a total of 350 components. A segmentation accuracy of 87.7% while a classification rate of 92% is realized demonstrating the effectiveness of the proposed technique.