A New Weighted Region-based Hough Transform Algorithm for Robust Line Detection in Poor Quality Images of 2D Lattices of Rectangular Objects
In this work we present a novel kernel-based Hough Transform method for robust line detection in poor quality images of 2D lattices of rectangular objects. First, during a preprocessing stage, the connected regions of the image are determined. Then, a rectangularity score is computed for each region...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Computer Vision Center Press
2013-04-01
|
| Series: | ELCVIA Electronic Letters on Computer Vision and Image Analysis |
| Subjects: | |
| Online Access: | https://elcvia.cvc.uab.es/article/view/521 |
| _version_ | 1819107389719183360 |
|---|---|
| author | Theoharis Tsenoglou Nikolaos Vassilas Djamchid Ghazanfarpour |
| author_facet | Theoharis Tsenoglou Nikolaos Vassilas Djamchid Ghazanfarpour |
| author_sort | Theoharis Tsenoglou |
| collection | DOAJ |
| description | In this work we present a novel kernel-based Hough Transform method for robust line detection in poor quality images of 2D lattices of rectangular objects. First, during a preprocessing stage, the connected regions of the image are determined. Then, a rectangularity score is computed for each region in order to filter out non-rectangular regions. Finally, the proposed method uses a kernel to specify each region’s contribution to the accumulator array based on the following shape descriptors: a) its rectangularity, b) the orientation of the major side of its minimum area bounding rectangle (MBR), and c) the MBR’s geometrical center. The proposed kernel is designed as the product of Gaussians having as footstep shape in Hough space that of a sinusoidal ribbon. Experimental and theoretical analysis on the uncertainties associated with the geometrical center as well as the polar parameters of the MBR’s major axis line equation allows for automatic selection of the parameters used to specify the shape of the kernel’s footstep (e.g. length and width of the ribbon) on the accumulator array. Comparisons performed on images of building facades taken under impaired visual conditions or with low accuracy sensors (e.g. thermal images) between the proposed method and other Hough Transform algorithms, show an improved accuracy of our method in detecting lines and/or linear formations. Finally, the robustness of the proposed method is shown in two other application domains those of, façade image rectification and skew detection and correction in rotated scanned documents. |
| first_indexed | 2024-12-22T02:53:16Z |
| format | Article |
| id | doaj.art-9d848857427e4878affa1485de6e21a8 |
| institution | Directory Open Access Journal |
| issn | 1577-5097 |
| language | English |
| last_indexed | 2024-12-22T02:53:16Z |
| publishDate | 2013-04-01 |
| publisher | Computer Vision Center Press |
| record_format | Article |
| series | ELCVIA Electronic Letters on Computer Vision and Image Analysis |
| spelling | doaj.art-9d848857427e4878affa1485de6e21a82022-12-21T18:41:19ZengComputer Vision Center PressELCVIA Electronic Letters on Computer Vision and Image Analysis1577-50972013-04-0112210.5565/rev/elcvia.521201A New Weighted Region-based Hough Transform Algorithm for Robust Line Detection in Poor Quality Images of 2D Lattices of Rectangular ObjectsTheoharis Tsenoglou0Nikolaos Vassilas1Djamchid Ghazanfarpour2Technological Educational Institute (T.E.I.) of AthensTechnological Educational Institute (T.E.I.) of AthensUniversity of LimogesIn this work we present a novel kernel-based Hough Transform method for robust line detection in poor quality images of 2D lattices of rectangular objects. First, during a preprocessing stage, the connected regions of the image are determined. Then, a rectangularity score is computed for each region in order to filter out non-rectangular regions. Finally, the proposed method uses a kernel to specify each region’s contribution to the accumulator array based on the following shape descriptors: a) its rectangularity, b) the orientation of the major side of its minimum area bounding rectangle (MBR), and c) the MBR’s geometrical center. The proposed kernel is designed as the product of Gaussians having as footstep shape in Hough space that of a sinusoidal ribbon. Experimental and theoretical analysis on the uncertainties associated with the geometrical center as well as the polar parameters of the MBR’s major axis line equation allows for automatic selection of the parameters used to specify the shape of the kernel’s footstep (e.g. length and width of the ribbon) on the accumulator array. Comparisons performed on images of building facades taken under impaired visual conditions or with low accuracy sensors (e.g. thermal images) between the proposed method and other Hough Transform algorithms, show an improved accuracy of our method in detecting lines and/or linear formations. Finally, the robustness of the proposed method is shown in two other application domains those of, façade image rectification and skew detection and correction in rotated scanned documents.https://elcvia.cvc.uab.es/article/view/521Hough TransformRectangularityBuilding FacadesSkew Correction |
| spellingShingle | Theoharis Tsenoglou Nikolaos Vassilas Djamchid Ghazanfarpour A New Weighted Region-based Hough Transform Algorithm for Robust Line Detection in Poor Quality Images of 2D Lattices of Rectangular Objects ELCVIA Electronic Letters on Computer Vision and Image Analysis Hough Transform Rectangularity Building Facades Skew Correction |
| title | A New Weighted Region-based Hough Transform Algorithm for Robust Line Detection in Poor Quality Images of 2D Lattices of Rectangular Objects |
| title_full | A New Weighted Region-based Hough Transform Algorithm for Robust Line Detection in Poor Quality Images of 2D Lattices of Rectangular Objects |
| title_fullStr | A New Weighted Region-based Hough Transform Algorithm for Robust Line Detection in Poor Quality Images of 2D Lattices of Rectangular Objects |
| title_full_unstemmed | A New Weighted Region-based Hough Transform Algorithm for Robust Line Detection in Poor Quality Images of 2D Lattices of Rectangular Objects |
| title_short | A New Weighted Region-based Hough Transform Algorithm for Robust Line Detection in Poor Quality Images of 2D Lattices of Rectangular Objects |
| title_sort | new weighted region based hough transform algorithm for robust line detection in poor quality images of 2d lattices of rectangular objects |
| topic | Hough Transform Rectangularity Building Facades Skew Correction |
| url | https://elcvia.cvc.uab.es/article/view/521 |
| work_keys_str_mv | AT theoharistsenoglou anewweightedregionbasedhoughtransformalgorithmforrobustlinedetectioninpoorqualityimagesof2dlatticesofrectangularobjects AT nikolaosvassilas anewweightedregionbasedhoughtransformalgorithmforrobustlinedetectioninpoorqualityimagesof2dlatticesofrectangularobjects AT djamchidghazanfarpour anewweightedregionbasedhoughtransformalgorithmforrobustlinedetectioninpoorqualityimagesof2dlatticesofrectangularobjects AT theoharistsenoglou newweightedregionbasedhoughtransformalgorithmforrobustlinedetectioninpoorqualityimagesof2dlatticesofrectangularobjects AT nikolaosvassilas newweightedregionbasedhoughtransformalgorithmforrobustlinedetectioninpoorqualityimagesof2dlatticesofrectangularobjects AT djamchidghazanfarpour newweightedregionbasedhoughtransformalgorithmforrobustlinedetectioninpoorqualityimagesof2dlatticesofrectangularobjects |