A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
A new curve detection method: randomized Hough transform (RHT)
Pattern Recognition Letters
Use of the Hough transformation to detect lines and curves in pictures
Communications of the ACM
Detection and Modeling of Buildings from Multiple Aerial Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
A New Approach for Line Recognition in Large-size Images Using Hough Transform
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Rectangle Detection based on a Windowed Hough Transform
SIBGRAPI '04 Proceedings of the Computer Graphics and Image Processing, XVII Brazilian Symposium
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Randomized Generalized Hough Transform for 2-D Grayscale Object Detection
ICPR '96 Proceedings of the 13th International Conference on Pattern Recognition - Volume 2
Diffusion tensors for processing sheared and rotated rectangles
IEEE Transactions on Image Processing
| Hi-index | 0.01 |
We present a new method for extracting rectangular shapes from images. It uses a windowed Hough transform and adds a new coordinate to store the precise pixel distribution of a line by means of a topological relation. By an early and rigorous check of each edge candidate, performed in the new expanded Hough space, the edge space is significantly reduced, thus simplifying further processing. Moreover, the edge checking algorithm provides flexibility in choosing the diameter of the circular search window. The method is robust, revealing a good recognition quality when applied to both synthetic and real images.