Visible to the public Edge Detection

SoS Newsletter- Advanced Book Block

Edge Detection

Edge detection is an important issue in image and signal processing. The work cited here includes an overview of the topic, several approaches, and applications for radar and sonar. These works were presented or published between January and August of 2014.

  • Waghule, D.R.; Ochawar, R.S., "Overview on Edge Detection Methods," Electronic Systems, Signal Processing and Computing Technologies (ICESC), 2014 International Conference on, pp.151,155, 9-11 Jan. 2014. doi: 10.1109/ICESC.2014.31 Edge in an image is a contour across which the brightness of the image changes abruptly. Edge detection plays a vital role in image processing. Edge detection is a process that detects the presence and location of edges constituted by sharp changes in intensity of the image. An important property of the edge detection method is its ability to extract the accurate edge line with good orientation. Different edge detectors work better under different conditions. Comparative evaluation of different methods of edge detection makes it easy to decide which edge detection method is appropriate for image segmentation. This paper presents an overview of the published work on edge detection.
    Keywords: edge detection; image segmentation; edge detection methods ;image intensity; image processing; image segmentation; sharp changes; Algorithm design and analysis; Detectors; Field programmable gate arrays; Image edge detection; Morphology; Wavelet transforms; Edge Detection; Edge Detectors; FPGA; Wavelets (ID#:14-2812)
  • Isik, S.; Ozkan, K., "A Novel Multi-Scale And Multi-Expert Edge Detection Method Based On Common Vector Approach," Signal Processing and Communications Applications Conference (SIU), 2014 22nd , vol., no., pp.1630,1633, 23-25 April 2014. doi: 10.1109/SIU.2014.6830558 Edge detection is most popular problem in image analysis. To develop an edge detection method that has efficient computation time, sensing to noise as minimum level and extracting meaningful edges from the image, so that many crowded edge detection algorithms have emerged in this area. The different derivative operators and possible different scales are needed in order to properly determine all meaningful edges in a processed image. In this work, we have combined the edge information obtained from each operators at different scales with the concept of common vector approach and obtained edge segments that connected, thin and robust to the noise.
    Keywords: edge detection; expert systems; common vector approach; crowded edge detection algorithms; edge information; image analysis; multiexpert edge detection method; multiscale edge detection method; Conferences; Image edge detection; Noise; Pattern recognition; Speech; Vectors; common vector approach; edge detection; multi-expert; multi-scale (ID#:14-2813)
  • Wenlong Fu; Johnston, M.; Mengjie Zhang, "Low-Level Feature Extraction for Edge Detection Using Genetic Programming," Cybernetics, IEEE Transactions on, vol.44, no.8, pp.1459,1472, Aug. 2014. doi: 10.1109/TCYB.2013.2286611 Edge detection is a subjective task. Traditionally, a moving window approach is used, but the window size in edge detection is a tradeoff between localization accuracy and noise rejection. An automatic technique for searching a discriminated pixel's neighbors to construct new edge detectors is appealing to satisfy different tasks. In this paper, we propose a genetic programming (GP) system to automatically search pixels (a discriminated pixel and its neighbors) to construct new low-level subjective edge detectors for detecting edges in natural images, and analyze the pixels selected by the GP edge detectors. Automatically searching pixels avoids the problem of blurring edges from a large window and noise influence from a small window. Linear and second-order filters are constructed from the pixels with high occurrences in these GP edge detectors. The experiment results show that the proposed GP system has good performance. A comparison between the filters with the pixels selected by GP and all pixels in a fixed window indicates that the set of pixels selected by GP is compact but sufficiently rich to construct good edge detectors.
    Keywords: edge detection; feature extraction; filtering theory; genetic algorithms; image denoising; GP system; edge detection; genetic programming; linear filters; localization accuracy; low-level feature extraction; natural images; noise rejection; second-order filters; Accuracy; Detectors; Educational institutions; Feature extraction; Image edge detection; Noise; Training; Edge detection; feature extraction; genetic programming (ID#:14-2814)
  • Naumenko, AV.; Lukin, V.V.; Vozel, B.; Chehdi, K.; Egiazarian, K., "Neural Network Based Edge Detection In Two-Look And Dual-Polarization Radar Images," Radar Symposium (IRS), 2014 15th International , vol., no., pp.1,4, 16-18 June 2014. doi: 10.1109/IRS.2014.6869302 Edge detection is a standard operation in image processing. It becomes problematic if noise is not additive, not Gaussian and not i.i.d. as this happens in images acquired by synthetic aperture radar (SAR). To perform edge detection better, it has been recently proposed to apply a trained neural network (NN) and SAR image pre-filtering for single-look mode. In this paper, we demonstrate that the proposed detector is, after certain modifications, applicable for edge detection in two-look and dual-polarization SAR images with and without pre-filtering. Moreover, we show that a recently introduced parameter AUC (Area Under the Curve) can be helpful in optimization of parameters for elementary edge detectors used as inputs of the NN edge detector. Quantitative analysis results confirming efficiency of the proposed detector are presented. Its performance is also studied for real-life TerraSAR-X data.
    Keywords: edge detection; neural nets; radar computing; radar imaging; radar polarimetry; synthetic aperture radar; NN edge detector; SAR image pre-filtering; area under the curve; dual-polarization radar images; image processing; neural network based edge detection; parameter optimization; real-life TerraSAR-X data;single-look mode; synthetic aperture radar; two-look radar images; Artificial neural networks; Detectors; Image edge detection; Noise; Speckle; Synthetic aperture radar; Training; Synthetic aperture radar; edge detection; neural network; polarimetric; speckle; two-look images (ID#:14-2815)
  • Tong Chunya; Teng Linlin; Zhou Jiaming; He Kejia; Zhong Qiubo, "A Novel Method Of Edge Detection With Gabor Wavelet Based On FFTW," Electronics, Computer and Applications, 2014 IEEE Workshop on, pp.625,628, 8-9 May 2014. doi: 10.1109/IWECA.2014.6845697 Since remote sensing images' features of substantial data and complex landmark, so it needs a higher requirement for edge detection operator. Using Gabor wavelet as the edge detection operator can get over the limitations of grads operator and Canny operator in edge detection. However, the method based on 2-D Gabor wavelet takes more time. In response to this lack of Gabor wavelet, this paper presents an edge detection method based on parallel processing of FFTW and Gabor wavelet and the experimental analysis shows this method can improve the processing speed of the algorithm greatly.
    Keywords: Gabor filters; discrete Fourier transforms; edge detection; geophysical image processing; remote sensing; wavelet transforms;2D Gabor wavelet; Canny operator; FFTW; complex landmark feature; discrete Fourier transformation; edge detection method; grads operator; parallel processing; remote sensing images ;substantial data feature; Image edge detection; Image resolution; Wavelet transforms; FFTW; Gabor wavelet; edge detection; parallel; processing; remote sensing images (ID#:14-2816)
  • Nai-Quei Chen; Jheng-Jyun Wang; Li-An Yu; Chung-Yen Su, "Sub-pixel Edge Detection of LED Probes Based on Canny Edge Detection and Iterative Curve Fitting," Computer, Consumer and Control (IS3C), 2014 International Symposium on , vol., no., pp.131,134, 10-12 June 2014. doi: 10.1109/IS3C.2014.45 In recent years, the demands of LED are increasing. In order to test the quality of LEDs, we need LED probes to detect it, so the accuracy and manufacturing methods are attracted more attention by companies. LED probes are ground by people so far. When processing, we often consider the angle and radius of a probe (the radius is between 0.015 mm and 0.03 mm), so it is hard to balance between precision and quality. In this study, we proposed an effective method to measure the angle and radius of a probe. The method is based on Canny edge detection and a curve fitting with iteration. Experimental results show the effectiveness of the proposed method.
    Keywords: curve fitting; edge detection; iterative methods; light emitting diodes; Canny edge detection; LED probes; LED quality test iterative curve fitting; probe angle; probe radius; subpixel edge detection; Computational modeling; Curve fitting; Equations; Image edge detection; Light emitting diodes; Mathematical model; Probes; Edge detection; LED; Probe; Sub-pixel edge detection (ID#:14-2817)
  • Nascimento, AD.C.; Horta, M.M.; Frery, AC.; Cintra, R.J., "Comparing Edge Detection Methods Based on Stochastic Entropies and Distances for PolSAR Imagery," Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of, vol.7, no.2, pp.648,663, Feb. 2014. doi: 10.1109/JSTARS.2013.2266319 Polarimetric synthetic aperture radar (PolSAR) has achieved a prominent position as a remote imaging method. However, PolSAR images are contaminated by speckle noise due to the coherent illumination employed during the data acquisition. This noise provides a granular aspect to the image, making its processing and analysis (such as in edge detection) hard tasks. This paper discusses seven methods for edge detection in multilook PolSAR images. In all methods, the basic idea consists in detecting transition points in the finest possible strip of data which spans two regions. The edge is contoured using the transitions points and a B-spline curve. Four stochastic distances, two differences of entropies, and the maximum likelihood criterion were used under the scaled complex Wishart distribution; the first six stem from the h-f class of measures. The performance of the discussed detection methods was quantified and analyzed by the computational time and probability of correct edge detection, with respect to the number of looks, the backscatter matrix as a whole, the SPAN, the covariance an the spatial resolution. The detection procedures were applied to three real PolSAR images. Results provide evidence that the methods based on the Bhattacharyya distance and the difference of Shannon entropies outperform the other techniques.
    Keywords: data acquisition; edge detection; entropy; geophysical techniques; image resolution; maximum likelihood estimation; radar imaging; radar polarimetry; remote sensing by radar; speckle; splines (mathematics);statistical distributions; stochastic processes; synthetic aperture radar; B-spline curve; Bhattacharyya distance; SPAN; Shannon entropies; backscatter matrix; coherent illumination; computational time; data acquisition; detection methods; detection procedures; edge detection methods; image analysis; image processing; look number; maximum likelihood criterion; multilook PolSAR images; polarimetric synthetic aperture radar; probability; real PolSAR images; remote imaging method; scaled complex Wishart distribution; spatial resolution; speckle noise; stochastic distances; stochastic entropies; transition points; Edge detection; image analysis; information theory; polarimetric SAR (ID#:14-2818)
  • Weibin Rong; Zhanjing Li; Wei Zhang; Lining Sun, "An Improved Canny Edge Detection Algorithm," Mechatronics and Automation (ICMA), 2014 IEEE International Conference on , vol., no., pp.577,582, 3-6 Aug. 2014. doi: 10.1109/ICMA.2014.6885761The traditional Canny edge detection algorithm is sensitive to noise, therefore, it's easy to lose weak edge information when filtering out the noise, and its fixed parameters show poor adaptability. In response to these problems, this paper proposed an improved algorithm based on Canny algorithm. This algorithm introduced the concept of gravitational field intensity to replace image gradient, and obtained the gravitational field intensity operator. Two adaptive threshold selection methods based on the mean of image gradient magnitude and standard deviation were put forward for two kinds of typical images (one has less edge information, and the other has rich edge information) respectively. The improved Canny algorithm is simple and easy to realize. Experimental results show that the algorithm can preserve more useful edge information and more robust to noise.
    Keywords: edge detection; adaptive threshold selection methods; gravitational field intensity operator; image gradient magnitude; improved Canny edge detection algorithm; standard deviation; Algorithm design and analysis; Histograms; Image edge detection; Noise; Robustness; Standards; Tires; Adaptive threshold; Canny algorithm; Edge detection; Gravitational field intensity operator (ID#:14-2819)
  • Catak, M.; Duran, N., "2-Dimensional Auto-Regressive Process Applied To Edge Detection," Signal Processing and Communications Applications Conference (SIU), 2014 22nd , vol., no., pp.1442,1445, 23-25 April 2014. doi: 10.1109/SIU.2014.6830511Edge detection has important applications in image processing area. In addition to well-known deterministic approaches, stochastic models have been developed and validated on edge detection. In this study, a stochastic auto-regressive process method has been presented and this method applied to gray scale and color scale images. Results have been compared to other well-recognized edge detectors, then applicability of the developed method is pointed out.
    Keywords: {edge detection; image colour analysis; stochastic processes; autoregressive process; color scale images; edge detection; edge detectors; gray scale images; image processing; stochastic autoregressive process method; stochastic models; Art; Conferences; Feature extraction; Image edge detection; MATLAB; Signal processing; Stochastic processes; auto-regressive process; color image processing; edge detection (ID#:14-2820)
  • Wang, Xingmei; Liu, Guangyu; Li, Lin; Liu, Zhipeng, "A Novel Quantum-Inspired Algorithm For Edge Detection Of Sonar Image," Control Conference (CCC), 2014 33rd Chinese, pp.4836,4841, 28-30 July 2014. doi: 10.1109/ChiCC.2014.6895759 In order to extract the underwater object contours of sonar image accurately, a novel quantum-inspired edge detection algorithm is proposed. This algorithm use parameters of anisotropic second-order distribution characteristics MRF (Markov Random Field, MRF) model to describe the texture feature of original sonar image to smooth noise. Based on the conditions mentioned above, sonar image is represented by quantum bit on quantum theory, structure edge detection operator of sonar image by establishing a quantum superposition relationship between pixels. Evaluation the results of quantum-inspired edge detection by PSNR (Peak Signal to Noise Ratio, PSNR), and then complete the quantum-inspired edge detection of sonar image. The comparison different experiments demonstrate that the proposed algorithm get good smoothing result of original sonar image and underwater object contours can be extracted accurately. And it has better adaptability.
    Keywords: Histograms; Image edge detection; PSNR; Quantum mechanics; Sonar detection; Edge Detection; Peak Signal to Noise Ratio; Quantum-inspired; Sonar image (ID#:14-2821)
  • Baselice, F.; Ferraioli, G.; Reale, D., "Edge Detection Using Real and Imaginary Decomposition of SAR Data," Geoscience and Remote Sensing, IEEE Transactions on, vol.52, no.7, pp.3833,3842, July 2014 doi: 10.1109/TGRS.2013.2276917 The objective of synthetic aperture radar (SAR) edge detection is the identification of contours across the investigated scene, exploiting SAR complex data. Edge detectors available in the literature exploit singularly amplitude and interferometric phase information, looking for reflectivity or height difference between neighboring pixels, respectively. Recently, more performing detectors based on the joint processing of amplitude and interferometric phase data have been presented. In this paper, we propose a novel approach based on the exploitation of real and imaginary parts of single-look complex acquired data. The technique is developed in the framework of stochastic estimation theory, exploiting Markov random fields. Compared to available edge detectors, the technique proposed in this paper shows useful advantages in terms of model complexity, phase artifact robustness, and scenario applicability. Experimental results on both simulated and real TerraSAR-X and COSMO-SkyMed data show the interesting performances and the overall effectiveness of the proposed method.
    Keywords: edge detection; geophysical image processing; remote sensing by radar; synthetic aperture radar; COSMO-SkyMed data; Markov random fields; SAR complex data; SAR data imaginary decomposition; SAR data real decomposition; TerraSAR-X data; amplitude phase information; contour identification; edge detection; interferometric phase data; interferometric phase information; single-look complex acquired data; stochastic estimation theory; synthetic aperture radar; Buildings; Detectors; Estimation; Image edge detection; Joints; Shape; Synthetic aperture radar; Edge detection; Markov random fields (MRFs); synthetic aperture radar (SAR) (ID#:14-2822)
  • Byungjin Chung; Joohyeok Kim; Changhoon Yim, "Fast Rough Mode Decision Method Based On Edge Detection For Intra Coding in HEVC," Consumer Electronics (ISCE 2014), The 18th IEEE International Symposium on, pp.1,2, 22-25 June 2014. doi: 10.1109/ISCE.2014.6884419 In this paper, we propose a fast rough mode decision method based on edge detection for intra coding in HEVC. It performs edge detection using Sobel operator and estimates the angular direction using gradient values. Histogram mapping is used to reduce the number of prediction modes for full rate-distortion optimization (RDO). The proposed method can achieve processing speed improvement through RDO computation reduction. Simulation results shows that encoding time is reduced significantly compared to HM-13.0 with acceptable BD-PSNR and BD-rate.
    Keywords: edge detection; video coding;BD-rate;HEVC;HM-13.0;RDO computation reduction; Sobel operator; acceptable BD-PSNR; angular direction estimation; edge detection; encoding time; fast rough mode decision method; full RDO; full rate-distortion optimization; gradient values; histogram mapping; intracoding; prediction mode number reduction; processing speed improvement; Encoding; Histograms; Image edge detection; Rate-distortion ; Simulation; Standards; Video coding; HEVC; edge detection; intra prediction; prediction mode (ID#:14-2823)
  • Muhammad, A; Bala, I; Salman, M.S.; Eleyan, A, "DWT Subbands Fusion Using Ant Colony Optimization For Edge Detection," Signal Processing and Communications Applications Conference (SIU), 2014 22nd, pp.1351,1354, 23-25 April 2014. doi: 10.1109/SIU.2014.6830488 In this paper, a new approach for image edge detection using wavelet based ant colony optimization (ACO) is proposed. The proposed approach applies discrete wavelet transform (DWT) on the image. ACO is applied to the generated four subbands (Approximation, horizontal, vertical, and diagonal) separately for edge detection. After obtaining edges from the 4 subbands, inverse DWT is applied to fuse the results into one image with same size as the original one. The proposed approach outperforms the conventional ACO approach.
    Keywords: ant colony optimisation; discrete wavelet transforms; edge detection; image fusion; ACO; DWT subbands fusion; ant colony optimization; discrete wavelet transform; image edge detection; inverse DWT; Ant colony optimization; Conferences; Discrete wavelet transforms; Image edge detection; Image reconstruction; Signal processing algorithms; ant colony optimization; discrete wavelet transform; edge detection (ID#:14-2824)


Articles listed on these pages have been found on publicly available internet pages and are cited with links to those pages. Some of the information included herein has been reprinted with permission from the authors or data repositories. Direct any requests via Email to SoS.Project (at) for removal of the links or modifications to specific citations. Please include the ID# of the specific citation in your correspondence.