Guided Scale Space Radon Transform for linear structures detection
This addresses the challenge of automatic line detection in images with complex backgrounds, though it appears incremental as it builds on the existing SSRT framework.
The paper tackles the problem of detecting thick linear structures in images with complex backgrounds using the Scale Space Radon Transform (SSRT), which suffers from irrelevant peaks that obscure line detection. The proposed method incorporates Hessian orientations during SSRT computation to emphasize linear structures, resulting in robust detection across synthetic and real images with varying thickness, noise, and backgrounds.
Using integral transforms to the end of lines detection in images with complex background, makes the detection a hard task needing additional processing to manage the detection. As an integral transform, the Scale Space Radon Transform (SSRT) suffers from such drawbacks, even with its great abilities for thick lines detection. In this work, we propose a method to address this issue for automatic detection of thick linear structures in gray scale and binary images using the SSRT, whatever the image background content. This method involves the calculated Hessian orientations of the investigated image while computing its SSRT, in such a way that linear structures are emphasized in the SSRT space. As a consequence, the subsequent maxima detection in the SSRT space is done on a modified transform space freed from unwanted parts and, consequently, from irrelevant peaks that usually drown the peaks representing lines. Besides, highlighting the linear structure in the SSRT space permitting, thus, to efficiently detect lines of different thickness in synthetic and real images, the experiments show also the method robustness against noise and complex background.