Symbol Spotting in Electronic Images Using Morphological Filters and Hough Transform
Article Sidebar
-
Symbol spotting, Hough Transform, Electronic Symbols, Morphological filters
Abstract
In this paper, two algorithms (a preliminary and enhanced algorithm) to detect electronic symbols in document images are proposed. Morphological operations coupled with Hough transform are used in the proposed methodology. The objective of the proposed algorithms is to detect electronic symbols of open and closed shapes. The methods can successfully spot many complex types of electronic symbols such as Fixed Resistor; Zener Diode; Pn Junction Diode; NPN transistor; Not Gate; Input and Output Terminals; Ground; Single Cell Battery; Transformer; and LED symbols. The experimental results on the Systems Evaluation Synthetic Documents (SESYD) dataset show that the proposed preliminary method detects 86.2%, (12151 symbols out of 14100 symbols), precision of 0.94, recall of 0.91, and F-measure of 0.92. An enhanced algorithm that used line Hough transform is also demonstrated with accuracy of 91.2% (12864 symbols out of 14100 symbols), precision of 0.97, recall of 0.93, and F-measure of 0.95).
Full text article
Authors
Copyright (c) 2022 Dilovan S. Ramadhan, Hasan S. M. Al-Khaffaf
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License [CC BY-NC-SA 4.0] that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work, with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online.