Conference Paper

The generalized radial Hilbert transform and its applications to 2D edge detection (any direction or specified directions)

Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
DOI: 10.1109/ICASSP.2003.1199484 Conference: Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on, Volume: 3
Source: IEEE Xplore

ABSTRACT It is well-known that the Hilbert transform (HLT) is useful for generating analytic signals, and saving the bandwidth required, in communication. However, it is less known that the HLT is also a useful tool for edge detection. We introduce the generalized radiant Hilbert transform (GRHLT), and illustrate how to use it for edge detection. The GRHLT is the general form of the two-dimensional HLT. Together with some other techniques (such as section dividing and shorter impulse response modification), we can use the GRHLT to detect the edges of images exactly. The GRHLT used for edge detection has a higher capability for noise immunity than other edge detection algorithms. Besides, we can also use the GRHLT for directional edge detection, i.e., detecting edges with certain directions.

0 Followers
 · 
145 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: Edge enhancement is a key part of image processing in order to sharpen the edge and optimize the visual quality of the input image. This paper proposes novel edge-directed enhancement spatial phase filters based on the generalized radial Hilbert transform theory. The simulated results showed that the proposed spatial phase filters are more efficient and flexible for edge-directed enhancement than conventional mathematical morphological edge enhancement algorithms.
    Photonics and Optoelectronics (SOPO), 2012 Symposium on; 01/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we define the short-response Hilbert transform (SRHLT) and use it for edge detection. The SRHLT has a parameter b. When b = 0, it becomes the Hilbert transform (HLT). When b is infinite, it becomes differentiation. Many edge detection algorithms are based on differentiation. However, they are sensitive to noise. By contrast, when using the HLT for edge detection, the noise is reduced but the resolution is poor. The proposed SRHLT in this paper can compromise the advantages of differentiation and HLTs. It is robust to noise and can simultaneously distinguish edges from non-edge regions very successfully.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, the performance of image filtering using the Hilbert Matrix and its inverse is studied first and according to its results, a new edge enhancement and embossing algorithm is proposed. Most of the Laplacian and Sobel-based edge detection methods use small masks. The algorithm suggested here not only enhances and sharpens the edges of the image, but also makes it possible to use customized masks in Hilbert matrix and its inverse. Practical results show that this algorithm can be exploited in different fields such as angiography. The proposed method has been compared with sharpening method using Laplacin and Sobel operators.

Full-text (2 Sources)

Download
39 Downloads
Available from
Jun 3, 2014