Adaptive Gaussian and Double Thresholding for Contour Detection and Character Recognition of Two-Dimensional Area Using Computer Vision
Contour detection with good accuracy is challenging in various computer-aided measurement applications. This paper evaluates the performance and comparison of thresholding and edge detection techniques for contour measurement along with character detection and recognition between images of high and...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Engineering Proceedings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4591/32/1/23 |
| _version_ | 1797594947266805760 |
|---|---|
| author | Nehal Abdul Rehman Farah Haroon |
| author_facet | Nehal Abdul Rehman Farah Haroon |
| author_sort | Nehal Abdul Rehman |
| collection | DOAJ |
| description | Contour detection with good accuracy is challenging in various computer-aided measurement applications. This paper evaluates the performance and comparison of thresholding and edge detection techniques for contour measurement along with character detection and recognition between images of high and low quality. Thresholding is one of the key techniques for pre-processing in computer vision. Adaptive Gaussian Thresholding (AGT) is applied to distinguish the foreground and background of an image, and Canny edge detection (CED) is used for spotting a wide range of edges. Adaptive Gaussian Thresholding works on a small set of neighboring pixels, while Canny Edge Detection takes high- and low-intensity pixels in the form of thresholds that are tested to find accurate contour measurements while retaining the maximum data contained within them. The results show that Adaptive Gaussian Thresholding outperforms Canny edge detection for both brightened sharp and blurry dull images. |
| first_indexed | 2024-03-11T02:30:56Z |
| format | Article |
| id | doaj.art-938c4dd1e3964dedba795de79365cf07 |
| institution | Directory Open Access Journal |
| issn | 2673-4591 |
| language | English |
| last_indexed | 2024-03-11T02:30:56Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Engineering Proceedings |
| spelling | doaj.art-938c4dd1e3964dedba795de79365cf072023-11-18T10:17:01ZengMDPI AGEngineering Proceedings2673-45912023-05-013212310.3390/engproc2023032023Adaptive Gaussian and Double Thresholding for Contour Detection and Character Recognition of Two-Dimensional Area Using Computer VisionNehal Abdul Rehman0Farah Haroon1Department of Industrial Electronics Engineering, Institute of Industrial Electronics Engineering, Karachi 75300, PakistanDepartment of Industrial Electronics Engineering, Institute of Industrial Electronics Engineering, Karachi 75300, PakistanContour detection with good accuracy is challenging in various computer-aided measurement applications. This paper evaluates the performance and comparison of thresholding and edge detection techniques for contour measurement along with character detection and recognition between images of high and low quality. Thresholding is one of the key techniques for pre-processing in computer vision. Adaptive Gaussian Thresholding (AGT) is applied to distinguish the foreground and background of an image, and Canny edge detection (CED) is used for spotting a wide range of edges. Adaptive Gaussian Thresholding works on a small set of neighboring pixels, while Canny Edge Detection takes high- and low-intensity pixels in the form of thresholds that are tested to find accurate contour measurements while retaining the maximum data contained within them. The results show that Adaptive Gaussian Thresholding outperforms Canny edge detection for both brightened sharp and blurry dull images.https://www.mdpi.com/2673-4591/32/1/23Adaptive Gaussian ThresholdingbinarizationCanny edge detectioncontour measurementcomputer visionimage segmentation |
| spellingShingle | Nehal Abdul Rehman Farah Haroon Adaptive Gaussian and Double Thresholding for Contour Detection and Character Recognition of Two-Dimensional Area Using Computer Vision Engineering Proceedings Adaptive Gaussian Thresholding binarization Canny edge detection contour measurement computer vision image segmentation |
| title | Adaptive Gaussian and Double Thresholding for Contour Detection and Character Recognition of Two-Dimensional Area Using Computer Vision |
| title_full | Adaptive Gaussian and Double Thresholding for Contour Detection and Character Recognition of Two-Dimensional Area Using Computer Vision |
| title_fullStr | Adaptive Gaussian and Double Thresholding for Contour Detection and Character Recognition of Two-Dimensional Area Using Computer Vision |
| title_full_unstemmed | Adaptive Gaussian and Double Thresholding for Contour Detection and Character Recognition of Two-Dimensional Area Using Computer Vision |
| title_short | Adaptive Gaussian and Double Thresholding for Contour Detection and Character Recognition of Two-Dimensional Area Using Computer Vision |
| title_sort | adaptive gaussian and double thresholding for contour detection and character recognition of two dimensional area using computer vision |
| topic | Adaptive Gaussian Thresholding binarization Canny edge detection contour measurement computer vision image segmentation |
| url | https://www.mdpi.com/2673-4591/32/1/23 |
| work_keys_str_mv | AT nehalabdulrehman adaptivegaussiananddoublethresholdingforcontourdetectionandcharacterrecognitionoftwodimensionalareausingcomputervision AT farahharoon adaptivegaussiananddoublethresholdingforcontourdetectionandcharacterrecognitionoftwodimensionalareausingcomputervision |