Offline hand-drawn circuit component recognition using texture and shape-based features

Abstract

Circuit diagram is the very foundation of electrical and electronic sciences. A circuit diagram consists of various symbols called circuit components that specify the functionality of that circuit. Every day-today gadgets that we use are made up with a number of electrical/electronic circuits to play out their particular tasks. Till date circuit designers have to physically enter all data from the hand-drawn circuits into computers, and this procedure requires some investment in terms of time and carries mistakes with high likelihood. To this end, in this paper, we propose a method that relaxes this constraint by introducing a method for recognition of hand-drawn electrical and electronic circuit components, with both analog and digital components included. In the proposed method, the pre-processed images of circuit components are used for training and testing a recognition model using a feature set consisting of a texture based feature descriptor, called histogram of oriented gradients (HOG), and shape based features that include centroid distance, tangent angle, and chain code histogram. In addition, the texture based feature, being large in number compared to others is optimized using a feature selection algorithm called ReliefF. Classification of components is done by using sequential minimal optimization (SMO) classifier. The proposed method has been evaluated on a dataset of 20 different circuit components with 150 samples in each class. The experimental outcome shows that the proposed approach provides average 93.83% accuracy on the present database. We also compare our method with some of the state-of-the-art methods and we see that our method outperforms these methods.

Handwritten Logic Circuits Analysis Using the YOLO Network and a New Boundary Tracking Algorithm

“…Comparison of the proposed hand-drawn circuit component recognition method with some state-of-the-art methods is shown in Figure 13. It should be noted that the accuracy of the proposed method has been calculated using the sample images of logic gates provided by ROY et al [2], and the accuracy of the other methods is obtained from [2]. Table 5 shows the class-level and also average values of precision in comparison with an RCNN-based method [10].…”

“…This study has investigated statistical, structural, syntactic, and hybrid methods, but it does not mention new methods based on deep learning networks. Another work [2] has provided a method for identifying components of manual electrical and electronic circuits, including analog and digital components. In this method, after performing the desired preprocessing, a set of texture-describing features and shape-based features including the histogram of oriented gradients (HOG), centroid distance, tangent angle, and chain code histogram, are extracted.…”

ElectroNet: An Enhanced Model for Small-Scale Object Detection in Electrical Schematic Diagrams

“…Techniques to extract features from circuit diagrams include shape-based features, texture-based features, Histogram of Oriented Gradients (HOG) features, and moments. In the study by Roy et al [3], for instance, the authors employed shape and texturebased features to classify elements, using centroid, tangent angle, and chain code as shape-based features. They also used the ReliefF feature selection algorithm to extract texture-based features, which were then fed into an SMO classifier.…”

“…The recognition of hand-drawn circuit schematic elements represents a significant area of research interest [1][2][3][4][5][6][7], with an ongoing necessity for a comprehensive approach that can interpret entire circuits, including associated textual labels. The aim is to facilitate automatic label assignment and the simulation of a full circuit, devoid of human intervention.…”

“…While numerous researchers have applied empirical techniques, these methods offer limited flexibility with respect to the freehand drawing of circuits and often impose constraints on factors such as line thickness and drawing style [1][2][3][4][5][6][7]. An additional issue has been the localization of elements and labels, an aspect overlooked by many of these strategies [1][2][3][5][6][7][8]. Even recent object-detection approaches have generally disregarded the integration of textual labels and the interpretation of labels featuring decimal points and metric prefixes.…”