... , August 01, 2011, IP: 210.210.45.178] || Click here to download free Android application for this journal. 124 ...... papers and four books.
[Downloaded free from http://www.tr.ietejournals.org on Monday, August 01, 2011, IP: 210.210.45.178] || Click here to download free Android application for this jou
123
Corner Detection Algorithms for Digital Images in Last Three Decades AMBAR DUTTA, AVIJIT KAR
AND
B N CHATTERJI
ABSTRACT Corner detection is an important step in many computer vision applications. A large number of corner detection algorithms were already developed. An exhaustive review of the existing corner detection algorithms is, therefore, invaluable for the researchers working in this area. In the present literature, we have found a few reviews on this area. Most reviewers classified corner detectors into two categories – boundary-based and intensity-based. Some reviewers classified the algorithms into two groups – template-based and geometry-based. Though we follow the first classification, still we feel that there is a requirement of further subdivision. So, we subdivide each category into further two subcategories – spatial-domain and transform-domain. In this paper, we have reviewed a total of 114 corner detection algorithms developed from 1977 to 2006, classified them in each of the four categories and found that most of the works have been done in spatial domain only as compared to transform domain approaches.
1. INTRODUCTION Corner detection in images is an important step in many tasks in machine vision, including scene analysis, motion and structure from motion analysis, image registration, image matching, object recognition etc. A corner is an image point with high contrast along all the directions. Hence, it is well distinguished from neighboring points. A corner detection algorithm must satisfy the following criteria to be useful for feature point matching: (i) consistency, (ii) accuracy, and (iii) speed. The performance of corner detection algorithms is affected by the attributes, viz., corner angle, corner arm length, corner adjacency, corner sharpness, gray level distribution and noise level. Vision researchers have proposed a considerable number of corner detection algorithms. A Rosenfeld et al [1], A Heyden et al [2], Z Zheng et al [3], C Schmid et al [4], P I Rockett [5] and F Mokhtarian et al [6, 7] provided good literature survey on the existing corner detection algorithms. Corner detection algorithms can be broadly divided into two classes – boundary based and intensity based. Boundary based methods rely on extraction of contours of regions either by edge detection or by segmenting the image into regions followed by boundary finding. These methods, thus, largely depend on a segmentation process. On the other hand, the
Vol. 25, No. 3, May-June’08
intensity based methods estimate a measure to detect corners directly from the gray values of the original images without a prior segmentation. Each of these two above categories can further be subdivided into spatial domain and frequency domain methods. Spatial domain methods directly operate on the pixel values of the image. In transform domain methods, the image is first transformed to some other domain, which is then passed through a suitable filter and finally the filtered information is mapped back to the spatial domain with the help of an inverse transform operation. The remainder of the paper is structured as follows. In section 2, we discuss different performance measures of corner detectors. In the subsequent sections (section 3-6), we present a literature survey of 114 corner detection algorithms under different categories of corner detection algorithms. Finally, we conclude in section 7.
2.
PERFORMANCE MEASURES FOR CORNER DETECTORS
The exact number of corners in the image, the number of corners truly detected, the number of corners missed and the number of extra corners detected play very important role for the comparison of corner detection algorithms. To evaluate the performance of corner detection I E T E
T E C H N I C A L
R E V I E W
[Downloaded free from http://www.tr.ietejournals.org on Monday, August 01, 2011, IP: 210.210.45.178] || Click here to download free Android application for this jou
124
Corner Detection Algorithms
Boundary based
Spatial Domain
Transform Domain
Intensity based
Spatial Domain
Transform Domain
Fig 1 Classification of corner detection algorithms
algorithms, a few performance measures had already been proposed in the literature [6, 7, 108]. We have also proposed three performance measures – Detection Gradient, False Positive Ratio and False Negative Ratio, comparable with the existing measures, which are defined below. | NA – ND | + | NM + NF | DG = ⎯⎯⎯⎯⎯⎯⎯⎯⎯⎯⎯⎯ NA FPR =
NF ⎯⎯⎯ NA
FNR =
NM ⎯⎯⎯ NA
where NA, ND, NM and NF denote the total number of corners present in the image, the number of true corners detected, the number of missed (false negative) corners and number of extraneous (false positive) corners detected in the image, respectively. In the best case, the value of DG is zero, which signifies that all the corners are correctly detected without any missed or false corners; the same is true for FPR and FNR.
3.
BOUNDARY BASED DOMAIN METHODS
SPATIAL
Freeman and Davis [8] and Rutkowski and Rosenfeld [1] detected corners by using chaincode values. Medioni and Yasumoto [9] used B-
Vol. 25, No. 3, May-June’08
Splines to develop a technique for corner detection and curve representation. Beus and Tiu [10] developed an algorithm based on chain-coded plane curves that eliminates the detection of spurious corners using a maximum cut-off value to determine the length of the forward and backward arms of each point. Davies [11] proposed corner detector based on generalized Hough transform. Ogowa [12] computed a symmetry measure at every point on a digital curve and then extracted corners at the local maxima of the measure. Rangarajan, Shah and Brackle [13] proposed an optimal gray level corner detector based on Canny’s optimal one-dimensional edge detector [14]. Rattarangsi and Chin [15] presented scale-based corner detection algorithm on planar curves. Mehrotra, Nichani and Ranganathan [16] described two methods for corner detection, one was based on the first directional derivative of Gaussian and the other was based on the second directional derivative of Gaussian. The detector also computed corner angle and orientation. Bell and Pau [17] developed a corner detector based on Freeman’s chain-code. Liu and Tsai [18] proposed a method based on the principle of preserving gray and mass moments. Cooper, Venkatesh and Kitchen [19] used two different approaches to detect corners in an image – one, by using dissimilarity along the contour direction to detect curves in the image contour, and the other by estimating image curvature along contour direction. Orange and Greon [20] proposed segmentation model for the detection of corners
I E T E
T E C H N I C A L
R E V I E W
[Downloaded free from http://www.tr.ietejournals.org on Monday, August 01, 2011, IP: 210.210.45.178] || Click here to download free Android application for this jou
125
based on a geometrical model. Xie, Sudhakar and Zhuang [21] presented a cost minimization approach to corner detection in which they associated a corner with different cost factors capturing desirable characteristics of a corner. Pei and Horng [22] extracted corners from curvature local maxima of the shape resulting from the nest moving average of the original image. Seeger and Seeger [23] detected corners from a gray-level image by a real-time parameter-free algorithm. Sugimoto and Tomita [24] proposed an algorithm for the detection of various feature points (corner, inflection and transition). Zhang, Haralick and Ramesh [25] described a maximum a posteriori (MAP) probability technique for corner detection. Pikaz and Dinstein [26] proposed an approach based on a simple decomposition of the curve into the minimal number of concave and convex sections to detect feature points and to smooth noisy digital curves. Sohn, Alexander, Kim and Snyder [27] presented a constraint regularization approach to detect corners that overcome the problem of determining the unique smoothing factor. Koplowitz and Plante [28] proposed a scheme for chain-coded curves by measuring the number of links to either side of a point that can produce the largest digital straight line. Ray and Ray [29] presented a corner detection algorithm using an iterative Gaussian convolution with constant window size. Dias, Kassim and Srinivasan [30] presented an artificial neural network based corner detection algorithm in a 2-D image. Wang, Wu, Huang and Wang [31] proposed a modified contour tracking and efficient corner detection algorithm using bending value. Lai, Paul and Wu [32] presented an edge-corner detection algorithm, called Cellular Vectorization Method. Sheu and Hu [33] proposed a rotationally invariant two-phase scheme for corner detection where the candidate corners are detected first and then these corners are reinvestigated for the global trend. Arrebola, Camacho, Bandera and Sandoval developed techniques which are based on local [34] and circular [35] histograms of the contour chain code. Ji and Haralick [36] applied statistical techniques to detect corners from chain-encoded digital arcs. Ray and Ray [37] used a discrete scale-space kernel to detect corners on a digital arc. Tsai [38] proposed a boundary based corner detection algorithm by developing two artificial neural networks, one for detecting corners with high curvature, and the other for detecting points of Vol. 25, No. 3, May-June’08
tangency and inflection. Zheng and Zhao [39] implemented a parallel algorithm for detecting dominant points on multiple digital curves. Shilat, Werman and Gdalyahu [40] presented a method for the detection of corners along ridges/troughs and local minima points. Mokhtarian and Soumela [41] presented a corner detection algorithm based curvature scale space representation in which first the edges are extracted from the original image using Canny edge detector [14], and then corners are found from the edge image where there is a local maxima of absolute curvature. Sohn, Kim and Alexander [42] presented a mean field annealing approach to boundary smoothing for curvature estimation to improve the capability of detecting corners. Li and Chen [43] described a corner detection algorithm on planar curves as a fuzzy classification problem containing three stages – evaluation, classification and location. Luo, Cross and Hancock [44] described a corner detection algorithm based on the topographic analysis of a vector potential image representation. Tsai, Hou and Su [45] presented a quantitative measure of corners based on the smaller eigen value of the covariance matrix of boundary points over a small region of support. Guest and Fairhurst [46] described a clustering approach to corner point analysis in hand-drawn images. Ludtke, Luo, Hancock and Wilson [47] proposed a corner detection algorithm using mixture model of edge orientation. Oh and Chien [48] described a corner detection algorithm by combining the generalized symmetry transform (GST) operator with the parametric corner equation. Shen and Wang [49] proposed a fast corner detector using modified Hough transform. Ray and Pandyan [50] presented an adaptive corner detector for planar curves. Marji and Siy [51] proposed an algorithm for detecting dominant points and polygonal approximation of digitized closed curves. Wu [52] proposed an efficient method for dominant point detection using adaptive bending value. Urdiales, Trazegnies, Bandera and Sandoval [53] presented a fast algorithm for corner detection defined at different scales by estimating the curvature of a contour in a local adaptive way. Banerjee, Kundu and Mitra [54] presented a support vector machine based algorithm for corner detection. Guru, Dinesh and Nagabhushan [55] presented a fast and efficient corner detection algorithm by introducing a new measure “cornerity index” for the quantification of the prominence of a corner point. Arrebola and I E T E
T E C H N I C A L
R E V I E W
[Downloaded free from http://www.tr.ietejournals.org on Monday, August 01, 2011, IP: 210.210.45.178] || Click here to download free Android application for this jou
126
Sandoval [56] detected corners by means of the hierarchical computation of a multi-resolution structure. Sarfraj, Rasheed and Muzaffer [57] presented a simple, robust and efficient real-time corner detection algorithm based on the change of sign of slope of the curve along the contour. Olague and Hernandez [58] proposed an accurate and flexible model-based multi-corner detector. Poyato, Garcia, Carnicer and Cuevas [59] described an efficient algorithm for detecting dominant points on the boundaries of digital planar curves. Sobania and Evans [60] proposed a morphological corner detector using paired triangular structuring element. The detector operated on the boundaries of a segmented image in a binary format and detected only interior or concave corners. Mokhtarian and Mohanna [7] presented a nice literature survey on the existing corner detection algorithms, provided two performance measure, accuracy and consistency, for corner detection algorithms and gave an enhanced version of original CSS corner detection algorithm [41], which worked on multiple scales also.
4.
BOUNDARY BASED TRANSFORM DOMAIN METHODS
Chen, Lee and Sun [61-63] proposed multiscale gray-level corner detection algorithms based on the modulus and orientation information of the wavelet transform which are used to detect edges and localize corners respectively. They also provided a multi-scale corner detection algorithm based on the wavelet transform of contour orientation. Kohlmann [64] derived a feature detection algorithm with 2-D intensity changes using 2-D Hilbert transform. Quddus and Falmy [65, 66] proposed a wavelet-based corner detection algorithm on planar curves. Peng, Zhou and Ding [67] proposed a boundary-based corner detection using wavelet transform. Gao, Sattar, Quddus and Venkateswarlu [68] proposed a multi-scale corner detection algorithm based on continuous wavelet transform on contour images. Yeh [69] proposed a robust, rotation- and scale-invariant wavelet-based corner detection algorithm on circular arcs by using the eigen vectors of the covariance matrices. Sun, Tang and You [70] proposed a wavelet-based corner detection algorithm by estimating the curvature of a contour in an adaptive way. Vol. 25, No. 3, May-June’08
5.
INTENSITY BASED DOMAIN METHODS
SPATIAL
Moravec [71] gave the concept of “points of interest” as points where a significantly high intensity variation occurs in every direction. Beaudet [72] presented a determinant operator, which has large values near the corners. Kitchen and Rosenfeld [73] were the first to apply the differential operators that consists of first and second order partial derivatives of the image to detect corners. They proposed a cornerness measure based on the product of the gradient magnitude and the change of the gradient direction along an edge contour. The local maxima of the measure isolated corner points. The detector is very sensitive to noise. Wu and Rosenfeld [74] detected corner points by a filter projection method. Zuniga and Haralick [75] proposed a facet model based corner detector. Paler, Foglein, Illingworth and Kittler [76] extracted corners from the local distribution of gray level values. Harris and Stephens [77] estimated the measure of local autocorrelation using first-order derivatives that is suggested by performing an analytic expansion of the Moravec [71] operator. At each pixel location a 2X2 autocorrelation matrix is computed and if both the eigen values are large, the pixel is considered to be a corner. The algorithm is computationally expensive. Forstner and Gulch [78] used the same cornerness measure as Harris and Stephens [76], but their algorithm has higher computational complexity. Tomasi and Kanade [79] derived the same equation by analyzing the optical flow equation presented by Lucas and Kanade [80]. Noble [81] explained the method of estimation of image curvature by Harris and characterized twodimensional surface features. Deriche and Giraudon [82] detected corners using a scale space based approach by combining useful properties from Laplacian and Beaudet’s cornerness measure. Shi and Tomasi [83] proposed a method for feature selection, a tracking algorithm based on a model of affine image changes, and a technique for monitoring features during tracking. Wang and Brady [84, 85] presented a simple and accurate corner detector based on the cornerness measurement of the total surface curvature. Cui and Lawrence [86] proposed scale-space consistent algorithm to detect corners in binary images based on corner attributes. Lee and Bien [87] formulated a pattern classification problem to I E T E
T E C H N I C A L
R E V I E W
[Downloaded free from http://www.tr.ietejournals.org on Monday, August 01, 2011, IP: 210.210.45.178] || Click here to download free Android application for this jou
127
detect gray-level corners in real-time algorithm using fuzzy logic. Diaz, Domingo and Ayala [88] detected two-dimensional feature point from a grayscale image using the application of statistical techniques. Smith and Brady [89] proposed SUSAN corner detector using a concept that each image point is associated with it a local area of similar brightness. If the brightness of each pixel within a mask is compared with the brightness of that mask’s nucleus, then an area of the mask can be defined which has the same (or similar) brightness as the nucleus. This area of the mask is known as the “USAN”, an acronym for “Univalue Segment Assimilating Nucleus”. The value of USAN gets smaller on both sides of an edge and becomes even smaller on each side of a corner. The local minima of the USAN map represent corners in the image. Kautsky, Zitova, Flusser and Peters [90, 91] proposed a two-stage method for the detecting the feature points in which all possible candidates are found first and then the desirable number of resulting significant points is selected among them by maximizing the weight function. Laganiere [92] proposed a morphological corner detector using an asymmetric closing operator. Lin, Chu and Hsueh [93] also used mathematical morphological operators for corner detection with simple integer computation. Stammberger, Michaelis, Reiser and Englmeier [94] proposed a hierarchical approach to corner detection in which the whole image is convolved with only one kernel. Trajkovic and Hedley [95] proposed a fast corner detection algorithm using a multigrid approach to reduce the computational complexity and to improve the quality of the detected corners. Chabat, Yang and Hansell [96] used an operator to detect the true location and orientation of corners. Lv and Zhou [97] modified the cornerness measure of KitchenRosenfeld detector [73] based on the perception of human vision system to make the detector effective in variable illumination scenes. Zheng, Wang and Toeh [2] presented a gradient direction corner detector, derived from the Plessey corner detector, which is based on the measure of the gradient module of image gradient direction. Sojka [98] presented a reliable, robust corner detection algorithm in digital images. Ruzon and Tomasi [99] used both a region model based on the distributions of pixel colors and an edge model for the detection of corners in textured color images. Basak and Mahata [100] proposed a connectionist model to detect corners in binary and gray images. Vol. 25, No. 3, May-June’08
Deschenes and Ziou [101] presented an approach to detect the line junctions in gray images. Alvarez, Cuenca and Mazorra [102] proposed a morphological corner detection algorithm to estimate corners with sub-pixel accuracy and tested the detector’s accuracy in the problem of multiple camera calibration. Wurtz and Laurens [103] presented a corner detection algorithm in color images through a multi-scale combination of end-stopped cortical cells. Telle and Aldon [104] proposed a interest point detector for color images based on non-linear filtering of the image. Gao, Yu, Sattar and Venkateswarlu [105] proposed an improved Plessey corner detector, worked in scalespace domain, for gray level images using multiscale analysis. Bae, Kweon and Yoo [106] used two oriented cross operators, COP (crosses as ordered pair) to extract low-level image features, viz., corners. Elias and Laganiere [107] proposed an approach based on a data structure similar to pyramid, but of circular levels, to determine the location and orientation of corners. Golightly and Jones [108] presented an algorithm for corner detection and matching for visual tracking of power line inspection and proposed two performance measures – detection rate and error rate – for the corner detection algorithms. Mikolajczyk and Schmid [109] presented two techniques for corner detection invariant to scale and affine transformations. Alkaabi and Deravi [110] presented a fast corner detection algorithm based on pruning candidate corners. Zhou, Liut and Cai [111] improved SUSAN corner detector [89] by presenting a robust and efficient corner detection algorithm which is capable of detecting the features in different contrast images automatically through self-adjust multi-threshold. Kenney, Zuliani and Manjunath [112] presented an axiomatic approach to corner detection. Vincent and Laganiere [113] proposed a new feature point detector which first performs a simple segmentation based on the intensity values found in the vicinity of each considered point, and then, it tries to fit a simple wedge corner model to the resulting segmented area. Cooke and Whatmough [114] proposed two ways – one by using genetic algorithm and another by using supervised classification techniques – towards the application of learning algorithms in corner detection. Pei and Ding [115] proposed a corner detection algorithm based on determining orientations of the adaptive vertical and tangent axes and observing the variations of brightness I E T E
T E C H N I C A L
R E V I E W
[Downloaded free from http://www.tr.ietejournals.org on Monday, August 01, 2011, IP: 210.210.45.178] || Click here to download free Android application for this jou
128
along the positive and negative directions of these axes. Rosten and Drummond [116] used machine learning for fast and high quality corner detection.
6.
INTENSITY BASED TRANSFORM DOMAIN METHODS
Quddus and Falmy [117] proposed a corner detection algorithm based on scale interaction model using Gabor filter suitable for both binary and gray level images with variable background. Pedersini, Pozzoli, Sarti and Tubaro [118] proposed a wavelet-based multi-resolution corner detection algorithm based on the analysis of multi-scale Laplacian’s profile. Quddus and Gabbouj [119] proposed a wavelet-based corner detection algorithm using singular value decomposition (SVD). Gao, Sattar and Venkateswarlu [120] presented a multi-scale corner detection algorithm on gray images using Gabor wavelets.
found that most of the work has been carried out on boundary (binary) and gray-scale images. So, there is huge scope of work in the field of corner detection that will directly operate on the color images as well. In addition, any boundary-based corner detection algorithm consists of finding boundary from an image, followed by following and closing the boundary, which always requires some manual intervention resulting in high computational time. 7. REFERENCES 1.
W S Rutkowski & A Rosenfeld, A comparison of corner detection techniques for chain-coded curves, Technique Report TR-623, Computer Science Center, University of Maryland, 1978.
2.
A Heyden & K Rohr, Evaluation of Corner Extraction Schemes Using Invariance Methods, in: Proc International Conference on Pattern Recognition, vol 1, Vienna, Austria, pp 895-899, 1996.
3.
Z Zheng, H Wang & E K Toeh, Analysis of Gray Level Corner Detectors, Pattern Recognition Letters, vol 20, pp 149-162, 1999.
4.
C Schmid, R Mohr & C Bauckhage, Evaluation pf Interest Point Detectors, International Journal of Computer Vision, vol 37, no 2, pp 151-172, 2000.
5.
P I Rockett, Performance Assessment of Feature Detection Algorithms: A Methodology and Case Study on Corner Detectors, IEEE Transaction on Image Processing, vol 12, no 12, pp 1668-1676, December, 2003.
6.
F Mohanna & F Mokhtarian, “Performance Evaluation of Corner Detection Algorithms under Similarity and Affine Transforms,” in Proc British Machine Vision Conference, Manchester, UK, pp 353–362, September 2001.
7.
F Mokhtarian & F Mohanna, Performance evaluation of corner detectors using consistency and accuracy measures, Computer Vision and Image Understanding, vol 102, pp 81- 94, 2006.
8.
H Freeman & L S Davis, A Corner Finding Algorithm for Chain-Code Curves, IEEE Transaction on Computers, vol 26, pp 297-303, 1977.
9.
G Medioni & Y Yasumoto, Corner Detection and Curve Representation using Cubic B-Splines, Computer Vision Graphics & Image Processing, vol 39, no 3, pp 267-278, 1987.
10.
H L Beus & S S H Tiu, An Improved Corner Detection Algorithm Based on Chain-Coded Plane Curves, Pattern Recognition, vol 20, no 3, pp 291-296, 1987.
11.
E R Davies, Application of the Generalized Hough Transform to Corner Detection, in: IEE Proceedings
7. CONCLUSIONS In this paper, we provide a literature survey on existing corner detection algorithms developed in the last three decades starting from 1977 which include a total of 114 algorithms. We then classify these algorithms into two main categories – boundary-based and intensity-based methods, which, in turn, are again subdivided into spatial domain and transform domain methods. After this classification, we have observed that out of these 114 algorithms, 54 algorithms belong to boundarybased spatial domain, 10 belong to boundary-based transform domain, 46 belong to intensity-based spatial domain and only 4 to intensity-based transform domain. But since transform domain methods are intensely used in various applications in image analysis and processing and comparatively much less work has been carried out in transform domain, there is a tremendous scope of work in the field of corner detection in transform domain. Moreover, all transform domain methods discussed in this survey were based on wavelet transform and since there are many other transforms available, e.g. Fourier, Hartley, WalshHadamard, Haar, Slant, Karhunen-Loeve etc, so efficiency of these transforms may be investigated and noted. Though the majority of work in this field has been carried out in the spatial domain, still there is scope more work in this area. We have also
Vol. 25, No. 3, May-June’08
I E T E
T E C H N I C A L
R E V I E W
[Downloaded free from http://www.tr.ietejournals.org on Monday, August 01, 2011, IP: 210.210.45.178] || Click here to download free Android application for this jou
129 on Computers and Digital Techniques, vol 135, Part E, no 1, pp 49-54, January 1988. 12.
H Ogawa, Corner Detection on Digital Curves Based on Local Symmetry of the Shape, Pattern Recognition, vol 22, no 4, pp 351-357, 1989.
13.
K Rangarajan, M Shah & D V Brackle, Optimal Corner Detector, Computer Vision Graphics & Image Processing, vol 48, pp 230-245, 1989.
14.
J F Canny, A Computational Approach to Edge Detection, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol 8, no 6, pp 679-698, 1986.
15.
A Rattarangsi & R T Chin, Scale-based Detection of Corners of Planar Curves, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol 14, pp 430-449, 1992.
16.
R Mehrotra, S Nichani & N Ranganathan, Corner Detection, Pattern Recognition, vol 23, no 11, pp 1223-1233, 1990.
17.
B Bell & L F Pau, Contour Tracking and Corner Detection in a Logic Programming Environment, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol 12, no 9, pp 913-917, September 1990.
18.
19.
20.
S T Liu & W H Tsai, Moment-Preserving Corner Detection, Pattern Recognition, vol 23, no 5, pp 441460, 1990. J Cooper, S Venkatesh & L Kitchen, Early Jump-out Corner Detectors, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol 15, no 8, pp 823-828, August 1993. C M Orange & F C A Greon, Model Based Corner Detection, in: Proc IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA, pp 690-691, June 1993.
21.
X Xie, R Sudhakar and H Zhuang, Corner Detection by a Cost Minimization Approach, Pattern Recognition, vol 26, no 8, pp 1235-1243, 1993.
22.
S C Pei & J H Horng, Corner Point Detection using Nest Moving Average, Pattern Recognition, vol 27, no 11, pp 1533-1537, 1994.
23.
U Seeger & R Seeger, Fast Corner Detection in Gray-level Images, Pattern Recognition Letters, vol 15, pp 669-675, 1994.
24.
K Sugiamoto & F Tomita, Boundary Segmentation by Detection of Corner, Inflection and Transition Points, in Proc IEEE Workshop on Visualization and Machine Vision, Seattle, CA, USA, pp 13-17, June 1994.
25.
X Zhang, R M Haralick & V Ramesh, Corner Detection using the MAP Technique, Conference A: Computer Vision & Image Processing, Proceedings
Vol. 25, No. 3, May-June’08
of the 12th IAPR International Conference on Pattern Recognition, Jerusalem, Israel, vol 1, pp 549-552, October 1994. 26.
A Pikaz & I Dinstein, Using Simple Decomposition for Smoothing and Feature Point Detection of Noisy Digital Curves, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol 16, no 8, pp 808-813, August 1994.
27.
K Sohn, W E Alexander, J H Kim & W E Snyder, A Constrained Regularization Approach to Robust Corner Detection, IEEE Transaction On Systems, Man, and Cybernetics, vol 24, no 5, pp 820-828, May 1994.
28.
J Koplowitz & S Plante, Corner Detection for Chain Coded Curves, Pattern Recognition, vol 28, no 6, pp 843-852, 1995.
29.
B K Ray & K S Ray, Corner Detection using Iterative Gaussian Smoothing with Constant Window Size, Pattern Recognition, vol 28, no 11, pp 1765-1781, 1995.
30.
P G T Dias, A A Kassim & V Srinivasan, A Neural Network Based Corner Detection Method, in: Proc IEEE International Conference on Neural Networks, Perth, WA, Australia, vol 4, pp 2116-2120, November-December 1995.
31.
M J J Wang , W Y Wu, L K Huang & D M Wang, Corner Detection using Bending Value, Pattern Recognition Letters, vol 16, pp 575-583, 1995.
32.
K K Lai & P S Y Wu, Effective Edge-Corner Detection Method for Defected Images, in: Proc of 3rd International Conference on Signal Processing, Beijing, China, vol 2, pp 1151-1154, October 1996.
33.
H T Sheu & W C Hu, A Rotationally Invariant TwoPhase Scheme for Corner Detection, Pattern Recognition, vol 29, no 5, pp 819-828, 1996.
34.
F Arrebola, A Bandera, P Camacho & F Sandoval, Corner Detection by Local Histograms of Contour Chain Code, Electronics Letters, vol 33, no 21, pp 1769-1771, 9th October, 1997.
35.
F Arrebola, P Camacho, A Bandera and F Sandoval, Corner Detection and Curve Representation by Circular Histograms of Contour Chain Code, Electronics Letters, vol 35, no 13, pp 1065-1067, 24th June, 1999.
36.
Q Ji & R M Haralick, Corner Detection with Covariance Propagation, in: Proc of Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, pp 362-367, June 1997.
37.
B K Ray & K S Ray, Scale-Space Analysis and Corner Detection on Digital Curves using a Discrete Scale-Space Kernel, Pattern Recognition, vol 30, no 9, pp 1463-1474, 1997.
I E T E
T E C H N I C A L
R E V I E W
[Downloaded free from http://www.tr.ietejournals.org on Monday, August 01, 2011, IP: 210.210.45.178] || Click here to download free Android application for this jou
130 38.
D M Tsai, Boundary-Based Corner Detection using Neural Networks, Pattern Recognition, vol 30, no 1, pp 85-97, 1997.
51.
M Marji & P Siy, A New Algorithm for Dominant Points Detection and Polygonization of Digital Curves, Pattern Recognition, vol 36, pp 2239-2251, 2003.
39.
Z Zheng & D Zhao, Parallel Algorithm for Detecting Dominant Points on Multiple Digital Curves, Pattern Recognition, vol 30, no 2, pp 239-244, 1997.
52.
W Y Wu, Dominant Point Detection using Adaptive Bending Value, Image and Vision Computing, vol 21, pp 517-525, 2003.
40.
E Shilat, M Werman & Y Gdalyahu, Ridge’s Corner Detection and Correspondence, in: Proc IEEE Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, pp 976-981, June 1997.
53.
C Urdiales, C Trazegnies, A Bandera & E Sandoval, Corner Detection Based on Adaptively Filtered Curvature Function, Electronics Letters, vol 39 no 5, pp 426-428, 6th March 2003.
54.
41.
F Mokhtarian & R Suomela, Robust Image Corner Detection through Curvature Scale Space, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol 20, no 12, pp 1376-1381, December 1998.
M Banerjee, M K Kundu & P Mitra, Corner Detection using Support Vector Machines, in: Proceedings of the 17th International Conference on Pattern Recognition, vol 2, pp 819-822, August 2004.
55.
D S Guru, R Dinesh & P Nagabhushan, Boundary Based Corner Detection and Localization using New ‘Cornerity’ Index: A Robust Approach, in: Proceedings of the First Canadian Conference on Computer and Robot Vision, pp 423-427, May 2004.
56.
F Arrebola & F Sandoval, Corner Detection and Curve Segmentation by Multiresolution Chain-Code Linking, Pattern Recognition, vol 38, pp 1596-1614, 2005.
57.
M Sarfraz, A Rasheed, & Z Muzaffar, A Novel Linear Time Corner Detection Algorithm, in: Proceedings of the Computer Graphics, Imaging and Vision: New Trends, pp 191-196, July 2005.
58.
G Olague & B Hernandez, A New Accurate and Flexible Model Based Multi-Corner Detector for Measurement and Recognition, Pattern Recognition Letters, vol 26, pp 27-41, 2005.
59.
A C Poyato, N L F Garcýa, R M Carnicer & F.J M Cuevas, Dominant Point Detection: A New Proposal, Image and Vision Computing, vol 23, pp 1226-1236, 2005.
60.
A Sobania & J P O Evans, Morphological Corner Detector using Paired Triangular Structuring Elements, Pattern Recognition, vol 38, pp 1087-1098, 2005.
61.
J S Lee, Y N Sun & C H Chen, Gray-Level-Based Corner Detection by using Wavelet Transform, IEEE TENCON, Beijing, China, pp 970-973, 1993.
62.
C H Chen, J S Lee & Y N Sun, Wavelet Transformation for Gray-Level Corner Detection, Pattern Recognition, vol 28, no 6, pp 853-861, 1995.
63.
J S Lee, Y N Sun & C H Chen, Multiscale Corner Detection by Wavelet Transform, IEEE Transaction on Image Processing, vol 4, no 1, pp 100-104, January 1995.
64.
K Kohlmann, Corner Detection in Natural Images Based on the 2-D Hilbert Transform, Signal Processing, vol 48, pp 225-234, 1996.
42.
43.
K Sohn, J H Kim & W E Alexander, A Mean Field Annealing Approach to Robust Corner Detection, IEEE Transaction on Systems, Man and Cybernetics - Part B: Cybernetics, vol 28, no 1, pp 82-90, February 1998. L Li & W Chen, Corner Detection and Interpretation on Planar Curves using Fuzzy Reasoning, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol 21, no 12, pp 1204-1210, December 1999.
44.
B Luo, A.D.J Cross & E.R Hancock, Corner Detection Via Topographic Analysis of VectorPotential, Pattern Recognition Letters, vol 20, pp 635-650, 1999.
45.
D M Tsai, H T Hou & H J Su, Boundary-Based Corner Detection using Eigen Values of Covariance Matrices, Pattern Recognition Letters, vol 20, pp 3140, 1999.
46.
R M Guest & M C Fairhurst, A Clustering Approach to Corner Point Analysis in Hand Drawn Images, in: Proceedings of the 16th International Conference on Pattern Recognition, vol 3, pp 940-943, 2002.
47.
N Ludtke, B Luo, E Hancock & R C Wilson, Corner Detection using a Mixture Model of Edge Orientation, in: Proceedings of the 16th International Conference on Pattern Recognition, vol 2, pp 574-577, 2002.
48.
H H Oh & S I Chien, Exact Corner Location using Attentional Generalized Symmetry Transform, Pattern Recognition Letters, vol 23, pp 1361-1372, 2002.
49.
F Shen & H Wang, Corner Detection Based on Modified Hough Transform, Pattern Recognition Letters, vol 23, pp 1039-1049, 2002.
50.
B K Ray & R Pandyan, ACORD – An Adaptive Corner Detector for Planar Curves, Pattern Recognition, vol 36, pp 703-708, 2003.
Vol. 25, No. 3, May-June’08
I E T E
T E C H N I C A L
R E V I E W
[Downloaded free from http://www.tr.ietejournals.org on Monday, August 01, 2011, IP: 210.210.45.178] || Click here to download free Android application for this jou
131 65.
66.
67.
68.
A Quddus & M M Falmy, An Improved WaveletBased Corner Detection Technique, in: Proc IEEE International Conference on Acoustics, Speech, and Signal Processing, Phoenix, AZ, USA, vol 6, pp 32133216, 1999.
and Tracking of Point Features, Technical Report, CMU-CS-91-132, 1991. 80.
B Lucas & T Kanade, An Iterative Registration Technique with an Application to Stereo Vision, in: Proc 7th International Joint Conference of Artificial Intelligence, vol 2, pp 674-679, 1981.
81.
A Noble, Finding comers, Image and Vision Computing, vol 6, no 2, pp 121-128, 1988.
82.
X Peng, C Zhou & M Ding, Corner Detection Method Based on Wavelet Transform, in: Proc SPIE, vol 4550, pp 319-323, 2001.
R Deriche & G Giraudon, A Computational Approach for Corner and Vertex Detection, International Journal of Computer Vision, vol 10, no 2, pp 101-124, 1993.
83.
X Gao, F Sattar, A Quddus & R Venkateswarlu, Corner Detection of Contour Images using Continuous Wavelet Transform, ICICS-PCM, Singapore, pp 724-728, 15-18 December, 2003.
J Shi & C Tomasi, Good Features to Track, in: Proc IEEE Conference on Computer Vision and Pattern Recognition, Seattle, CA, USA, pp 593-600, June 1994.
84.
H Wang, and M Brady, A Practical Solution to Corner Detection, in: Proc 5th International Conference on Image Processing, Austin, TX, USA, vol 1, pp 919923, November 1994.
85.
H Wang, and M Brady, Real-Time Corner Detection Algorithm for Motion Estimation, Image and Vision Computing, vol 13, no 9, pp 695-703, 1995.
86.
Y Cui & P D Lawrence, Detecting Scale-Space Consistent Corners Based on Corner Attributes, IEEE International Conference on Systems, Man and Cybernetics, ‘Intelligent Systems for the 21st Century’, Vancouver, BC, Canada, vol 4, pp 35493554, 1995.
A Quddus & M M Falmy, Detection of Corners and Smooth Joins using Wavelet Transform, in: Proc of the 1999 IEEE International Symposium on Circuits and Systems, Orlando, FL, USA, vol 3, pp 395-398, 1999.
69.
C H Yeh, Wavelet-Based Corner Detection using Eigen Vectors of Covariance Matrices, Pattern Recognition Letters, vol 24, pp 2797- 2806, 2003.
70.
L Sun, Y.Y Tang & X You, Corner Detection for Object Recognition by using Wavelet Transform, Electronics Letters, vol 38 no 14, pp 699-701, July 2002
71.
H P Moravec, Towards Automatic Visual Obstacle Avoidance, in: Proc 5th International Joint Conference of Artificial Intelligence, pp 584, Cambridge, Massachusetts, 1977.
72.
P R Beaudet, Rotationally Invariant Image Operators, in: Proc International Joint Conference of Pattern Recognition, pp 579-583, Kyoto, 1978.
87.
K J Lee & Z Bien, A Gray-Level Corner Detector using Fuzzy Logic, Pattern Recognition Letters, vol 17, pp 939-950, 1996.
73.
L Kitchen & A Rosenfeld, Gray Level Corner Detection, Pattern Recognition Letters, vol 1, no 2, pp 95-102, 1982.
88.
M E Dýaz, J Domingo & G Ayala, A Gray-Level 2D Feature Detector using Circular Statistics, Pattern Recognition Letters, vol 18, pp 1083-1089, 1997.
74.
Z O Wu & A Rosenfeld, Filtered Projection as an Aid to Corner Detection, Pattern Recognition, vol 16, no 31, pp , 1983.
89.
S M Smith & J M Brady, A New Approach to LowLevel Image Processing, International Journal of Computer Vision, vol 23, no 1, pp 45-78, 1997.
75.
O A Zuniga & R M Haralick, Corner Detection using the Facet Model, in: Proc Conference on Computer Vision and Pattern Recognition, pp 30-37, 1983.
90.
76.
K Paler, J Foglein, J Illingworth & J Kittler, Local Ordered Gray-Levels as an Aid to Corner Detection, Pattern Recognition, vol 17, no 5, pp 535-543, 1984.
J Kautsky, B Zitova, J Flusser & G Peters, Feature Point Detection in Blurred Images, in: Proc International Conference IVCNZ ’98, Image and Vision Computing Proceedings (Klette R., Gimelfarb G., Kakarala R eds.), University of Auckland, Auckland, New Zealand, pp 103-108, November 1998.
91.
77.
C Harris, and M Stephens, “A Combined Corner and Edge Detector”, 4th Alvey Vision Conference, pp 147-151, Manchester, UK, 1988.
B Zitova, J Kautsky, G Peters & J Flusser, Robust Detection of Significant Points in Multiframe Images, Pattern Recognition Letters, vol 20, pp 199-206, 1999.
78.
W Forstner & E Gulch, A Fast Operator for Detection and Precise Location of Distinct Points, Corners and Centers of Circular Features, ISPRS Inter Commission Workshop, pp 147-151, June 1987.
92.
R Laganiere, A Morphological Operator for Corner Detection, Pattern Recognition, vol 31, no 11, pp 1643-1652, 1998.
93.
R S Lin, C H Chu & Y C Hsueh, A Modified Morphological Corner Detector, Pattern Recognition Letters, vol 19, pp 279-286, 1998.
79.
C Tomasi & T Kanade, Shape and Motion from Image Streams: A Factorization Method-Part 3, Detection
Vol. 25, No. 3, May-June’08
I E T E
T E C H N I C A L
R E V I E W
[Downloaded free from http://www.tr.ietejournals.org on Monday, August 01, 2011, IP: 210.210.45.178] || Click here to download free Android application for this jou
132 94.
T Stammberger, M Michaelis, M Reiser & K H Englmeier, A Hierarchical Filter Scheme for Efficient Corner Detection, Pattern Recognition Letters, vol 19, pp 687-700, 1998.
95.
M Trajkovic & M Hedley, Fast Corner Detection, Image and Vision Computing, vol 16, no 2, pp 75-87, 1998.
96.
F Chabat, G Z Yang & D M Hansell, A Corner Orientation Detector, Image and Vision Computing, vol 17, pp 761-769, 1999.
97.
X Lv & J Zhou, Robust Corner Detection under Varying Illumination, in: Proc International Conference on Information Intelligence and Systems, Bethesda, MD, USA, pp 396-398, 1999.
98.
99.
E Sojka, A New Algorithm for Detecting Corners in Digital Images, in: Proc of the 18th Spring Conference on Computer Graphics, Budmerice, Slovakia, pp 5562, 2002. M A Ruzon & C Tomasi, Corner Detection in Textured Color Images, in: Proc Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece, vol 2, pp 1039-1045, 1999.
100. J Basak & D Mahata, A Connectionist Model for Corner Detection in Binary and Gray Images, IEEE Transaction on Neural Networks, vol 11, no 5, pp 1124-1132, September 2000. 101. F Deschenes & D Ziou, Detection of Line Junctions and Line Terminations Using Curvilinear Features, Pattern Recognition Letters, vol 21, pp 637-649, 2000. 102. L Alvarez, C Cuenca & L Mazorra, Morphological Corner Detection Application to Camera Calibration, in: Proceedings of the IASTED International Conference Signal Processing, Pattern Recognition & Applications, Rhodes, Greece, pp 21-26, July 2001. 103. R.P Wurtz & T Lourens, Corner Detection in Color Images through a Multiscale Combination of EndStopped Cortical Cells, Image and Vision Computing, vol 18, pp 531-541, 2000. 104. B Telle & M J Aldon, Interest Points Detection in Color Images, in: Proc IARP Workshop on Machine Vision Applications, Nara (Japan), pp 550-553, December 11-13, 2002 105. X Gao, Z Yu, F Sattar & R Venkateswarlu, Multi Scale Corner Detection for Gray Level Images using Plessey Method, in: Proc 8th International Conference on Control, Automation, Robotics and Vision, Kunming, China, pp 363-368, December 2004. 106. S Bae, I S, Kweon & C D Yoo, COP: A New Corner Detector, Pattern Recognition Letters, vol 23, no 11, pp 1349-1360, 2002. 107. K Elias & R Laganiere, Cones: A New Approach Towards Corner Detection, in: Proc of the IEEE
Vol. 25, No. 3, May-June’08
Canadian Conference on Electrical & Computer Engineering, pp 912-916, 2002. 108. I Golightly & D Jones, Corner Detection and Matching for Visual Tracking during Power Line Inspection, Image and Vision Computing, vol 21, pp 827-840, 2003. 109. K Mikolajczyk & C Schmid, Scale and Affine Invariant Interest Point Detectors, International Journal of Computer Vision, vol 60, no 1, pp 63-86, 2004. 110. S Alkaabi & F Deravi, Candidate Pruning for Fast Corner Detection, Electronic Letters, vol 40, Issue 1, pp 18-19, 2004. 111. D Zhou, Y H Liut & X Cai, An Efficient and Robust Corner Detection Algorithm, in: Proc 5th World Congress on Intelligent Control and Automation, Hangzhou P.R China, pp 4020-4024, June 2004. 112. C S Kenney, M Zuliani & B S Manjunath, An Axiomatic Approach to Corner Detection, in: Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, pp 191-197, June 2005. 113. E Vincent & R Laganiere, Detecting and Matching Feature Points, Journal of Visual Communication and Image Representation, vol 16, pp 38-54, 2005. 114. T Cooke & R Whatmough, Using Learning Algorithms to Improve Corner Detection, in: Proc Digital Image Computing: Technqiues and Applications, pp 371378, December 2005. 115. S C Pei & J J Ding, New Corner Detection Algorithm by Tangent and Vertical Axes and Case Table, in: Proc IEEE International Conference on Image Processing, vol 1, pp 365 – 368, September 2005. 116. E Rosten & T Drummond, Machine Learning for HighSpeed Corner Detection, in: Proc European Cinference on Computer Vision, pp 430-443, May 2006. 117. A Quddus & M M Falmy, Corner Detection using Gabor-type Filtering, in: Proceedings of the IEEE International Symposium on Circuits and Systems, vol 4, Monterey, CA, USA, pp 150-153, June 1998. 118. F Pedersini, E Pozzoli, A Sarti & S Tubaro, MultiResolution Corner Detection, in: Proceedings of the International Conference on Image Processing, vol 3, Vancouver, BC, Canada, pp 881-884, 2000. 119. A Quddus & M Gabbouj, Wavelet-Based Corner Detection Algorithm Technique using Optimal Scale, Pattern Recognition Letters, vol 23, pp 215-220, 2002. 120. X Gao, F Sattar & R Venkateswarlu, Corner Detection of Gray Level Images using Gabor Wavelets, in: Proc International Conference on Image Processing, vol 4, pp 2669-2672, October 2004.
I E T E
T E C H N I C A L
R E V I E W
[Downloaded free from http://www.tr.ietejournals.org on Monday, August 01, 2011, IP: 210.210.45.178] || Click here to download free Android application for this jou
133
Authors Ambar Dutta born on 3rd December, 1977, did his BSc (Honors) in Mathematics from Presidency College, Kolkata in 1999 and MCA from Jadavpur University, Kolkata in 2002. He is working as a Lecturer in the department of Computer Science and Engineering, Birla Institute of Technology, Mesra, Kolkata Extension Centre. He is pursuing his PhD from Jadavpur University, Kolkata in the area of image processing (corner detection and matching). His research interest includes Image Processing, Pattern Recognition, Data Mining and Soft Computing. Address: Department of Computer Science and Engineering, Birla Institute of Technology, Mesra, Kolkata Extension Centre, Southend Conclave, 1582, Rajdanga Main Road, Kolkata 700 107, India. email: *
*
*
Avijit Kar did his MSc and PhD in 1980 and 1984 respectively from IIT Kharagpur. He is currently a professor in the department of Computer Science and Engineering in Jadavpur University, Kolkata. He has supervised several PhD theses and is actively involved in many R & D activities and IT related consultancy for Government of India and the private sector. His research interest includes biomedical imaging as well as SAR imaging. He is also into computer systems reliability. He is involved in a large number of industry sponsored development projects. Address: Department of Computer Science and Engineering, Jadavpur University, Kolkata 700 032, India. email: *
*
*
B N Chatterji born on 10th November, 1942, obtained BTech (Hons) (1965) and PhD (1970) in Electronics and Electrical Communication Engineering of IIT, Kharagpur. He did Post Doctoral work at University of Erlangen-Nurenberg, Germany during 1972-73. Worked with Telerad Pvt Ltd, Bombay (1965), Central Electronics Research Institute, Pilani (1966) and IIT, Kharagpur as faculty member during 1967-2005. He was Professor during 1980-2005, Head of the Department during 1987-1991, Dean Academic Affairs during 1994-1997 and Member of Board of Governors of IIT, Kharagpur during 1998-2000. He has published about 150 journal papers, 200 conference papers and four books. He was Chairman of four International Conferences and ten National Conferences. He has coordinated 25 short-term courses and was the chief investigator of 24 Sponsored Projects. He is the Fellow/Life Member/Member of eight Professional Societies. He has received ten National Awards on the basis of his Academic/Research contributions. His areas of interests are Pattern Recognition, Image Processing, Signal Processing, Parallel Processing and Control Systems. Address: Department of Electronics Communication Engineering, B P Poddar Institute of Management and Technology, 137, VIP Road, Kolkata 700 052, India. email:
Paper No 138-B; Copyright © 2008 by the IETE.
Vol. 25, No. 3, May-June’08
I E T E
T E C H N I C A L
R E V I E W