Edge detection for illumination varying images using wavelet similarity

Swaminathan, Anand; Kumari, R. Shantha Selva

doi:10.1049/iet-ipr.2012.0460

Cited by 12 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the image intensity is an integer value, we choose thresh = 15 as the experimental parameter. Moreover, we compared the average technique for thresh selection with an adaptive thresh calculation according to (6). Line detection results under the two thresh calculations show that both methods produce robust thresh values and their line detection results are similar.…”

Section: Estimation Of Threshmentioning

confidence: 99%

“…In the literature, line segment detection has been classified into four categories [1], namely statistical-based models, gradient-based models, pixel connectivity-edge linkingbased models, and Hough transform (HT)-based models. Significant progress has been made in each of these classes [2][3][4][5][6][7]. Furthermore, a comprehensive review has been given by Guerreiro and Aguiar [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Step‐by‐step pipeline processing approach for line segment detection

Shao

Ding

Luo

et al. 2017

IET Image Processing

View full text Add to dashboard Cite

This study proposes a line segment detection that can efficiently and effectively handle non-linear uniform intensity changes. The presented sketching algorithm applies the resistant to affine transformation and monotonic intensity change (RATMIC) descriptor to conduct binary translation in the image pre-processing step, which can remove the unwanted smoothing of the Canny detector in most line detections. The Harris corner detector is applied to catch regions of line segments for the purpose of simulating the composition of sketching and achieving a sense of unity within the picture. Furthermore, the RATMIC descriptor is employed to obtain binary images of the regions of interest (ROIs). Finally, small eigenvalue analysis is implemented to detect straight lines in the ROIs. The experiments conducted on various images with image rotation, scaling, and translation validate the effectiveness of the proposed method. The experimental results also demonstrate that about 30% in the overall coverage of major lines and 20% in the coverage per major line are increased compared with the state-of-the-art line detectors. Moreover, the performance of the proposed method produces a combined advantage of ∼17% in the coverage of line segments over the line segment detector with noisy images.

show abstract

Section: Estimation Of Threshmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Step‐by‐step pipeline processing approach for line segment detection

Shao

Ding

Luo

et al. 2017

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Image processing and edge detection in in images have variety of applications [1], [2] [3], [4], [5]. Automatic OD Detection (ODD) from retinal images is essential to detect various types of eye diseases.…”

Section: Introductionmentioning

confidence: 99%

Correlation Coefficient Based Automatic Optic Disc Detection from Retinal Images

Anand¹,

Prabhadevi²,

Rini³

2020

Preprint

View full text Add to dashboard Cite

In this paper an algorithm to detect the optic disc (OD) automatically is described. The proposed method is based on the circular brightness of the OD and its correlation coefficient. At first the peak intensity points are taken, a mask is generated for the given image which gives the circular bright regions of the image. To locate the OD accurately, a pattern is generated which is similar to the OD. By correlating the retinal image with the pattern generated, the maximum correlation of the pattern with the OD is obtained. On locating the coordinates of maximum correlation, the exact location of the OD is detected. The proposed algorithm has been tested with DRIVE database images and an average OD detection accuracy of 95% was obtained for healthy and pathological retinas respectively.

show abstract

“…The heights and approximation techniques are used for defuzzification, and the method exhibited comparable results. The problem caused due to uneven illumination in edge detection from digital images was solved by a method introduced by Anand Swaminathan and Santha Ramapachiyam [6], incorporating weighted least square regularization with the wavelet filter directional responses, and the method performed better than many existing techniques.…”

Section: Introductionmentioning

confidence: 99%

An Enhanced Block Based Edge Detection Technique Using Hysteresis Thresholding

Jayasree¹,

Narayanan²,

Kabeer³

et al. 2018

SIPIJ

View full text Add to dashboard Cite

Edge detection is a crucial step in various image processing systems like computer vision , pattern recognition and feature extraction. The Canny edge detection algorithm even though exhibits high accuracy, is computationally more complex compared to other edge detection techniques. A block based distributed edge detection technique is presented in this paper, which adaptively finds the thresholds for edge detection depending on block type and the distribution of gradients in each block. A novel method of computation of high threshold has been proposed in this paper. Block-based hysteresis thresholds are computed using a non uniform gradient magnitude histogram. The algorithm exhibits remarkably high edge detection accuracy, scalability and significantly reduced computational time. Pratt's Figure of Merit quantifies the accuracy of the edge detector, which showed better values than that of original Canny and distributed Canny edge detector for benchmark dataset. The method detected all visually prominent edges for diverse block size.

show abstract

Edge detection for illumination varying images using wavelet similarity

Cited by 12 publications

References 23 publications

Step‐by‐step pipeline processing approach for line segment detection

Step‐by‐step pipeline processing approach for line segment detection

Correlation Coefficient Based Automatic Optic Disc Detection from Retinal Images

An Enhanced Block Based Edge Detection Technique Using Hysteresis Thresholding

Contact Info

Product

Resources

About