A robust edge detection method with sub-pixel accuracy

Sun, Qiucheng; Hou, Yuexian; Tan, Qing; Li, Chunjing; Liu, Ming

doi:10.1016/j.ijleo.2014.02.001

Cited by 40 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results are usually examined either by visual inspection as a qualitative measure [1,26] or quantitatively by di erent indexes [27][28][29][30][31][32][33][34][35]. Some of these algorithms utilize a linking technique collecting pixels that belong to a set of edges [36][37][38].…”

Section: Related Workmentioning

confidence: 99%

“…Recently, many papers have been published in the area of image edge detection [27][28][29][30][31][32][33][34][35] that tests its importance as follows: Lopez-Molina et al [27] presented a study that focuses on the improvements of edge detection by using Anisotropic Di usion (AD) instead of Gaussian Linear Filtering (GLF); in [28], the modi ed scheme is presented to improve the performance of traditional Canny edge detection through an adaptive lter based on bi-dimensional general auto-regression model; in [29], Lopez-Molina et al presented a novel edge detection framework based on the measurement of grey level changes using a new class of functions called relief functions; in [30], a new edge detection method that combines smoothing spline algorithm and gray- Figure 1. Schematic overview of the proposed algorithm where di erent steps can be observed.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A generalized entropy-based two-phase threshold algorithm for noisy medical image edge detection

Elaraby

Moratal

2017

Scientia Iranica

View full text Add to dashboard Cite

Abstract. Edge detection in medical imaging is a signi cant task for object recognition of human organs and is considered a pre-processing step in medical image segmentation and reconstruction. This article proposes an e cient approach based on generalized Hill entropy to nd a good solution for detecting edges under noisy conditions in medical images. The proposed algorithm uses a two-phase thresholding: rstly, a global threshold calculated by means of generalized Hill entropy is used to separate the image into object and background. Afterwards, a local threshold value is determined for each part of the image. The nal edge map image is a combination of these two separate images based on the three calculated thresholds. The performance of the proposed algorithm is compared to Canny and Tsallis entropy using sets of medical images corrupted by various types of noise. We used Pratt's Figure Of Merit (PFOM) as a quantitative measure for an objective comparison. Experimental results indicated that the proposed algorithm displayed superior noise resilience and better edge detection than Canny and Tsallis entropy methods for the four di erent types of noise analyzed, and thus it can be considered as a very interesting edge detection algorithm on noisy medical images.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A generalized entropy-based two-phase threshold algorithm for noisy medical image edge detection

Elaraby

Moratal

2017

Scientia Iranica

View full text Add to dashboard Cite

show abstract

“…In this study, a Sobel operator [27][28][29] was used to detect the edge pixels of each circle, and the results of a circle edge extracted from a camera image are shown in Section 5. Using a Sobel operator, all the pixels of the circle edge on the camera image can be obtained.…”

Section: A Improved Mapping Relationshipmentioning

confidence: 99%

Accurate projector calibration based on a new point-to-point mapping relationship between the camera and projector images

Huang

et al. 2015

Appl. Opt.

View full text Add to dashboard Cite

The mapping relationship between the charge-coupled device (CCD) of a camera and the digital micro-mirror device (DMD) of a projector, together with the algorithm to estimate the parameters of the projector, determines the accuracy of projector calibration. In this paper, a new method is presented to achieve sub-pixel-level mapping between the camera and projector images. Instead of directly mapping the circle centers from the CCD to the DMD, which is pixel-precision-based, a set of pixels on the circle edge are extracted on the CCD and mapped onto the DMD. The locations of the circle centers are extracted on the DMD by the least-squares fitting technique, thus achieving sub-pixel precision. Compared with existing approaches based on the direct mapping of the circle centers on the camera image to the projector image, the proposed method is characterized by higher accuracy in mapping the points and thus the projector calibration. The experimental results are presented to show the effectiveness of the proposed method in the improvement of the accuracy of the projector calibration.

show abstract

“…Edge detection is an essential preprocessing operation in many machine vision industrial applications [1][2][3], such as shape recognition, 3D reconstruction, defect detection on mechanical parts, etc. Edges are sets of pixels in the image regions with sharp intensity changes and correspond to visible contour features of objects in an image.…”

Section: Introductionmentioning

confidence: 99%