scispace - formally typeset
Search or ask a question

Showing papers on "Corner detection published in 1997"


Journal ArticleDOI
TL;DR: The method, based on linear least squares fitting to a conic section equation, proposes using the conic equation's natural classification property to help classify sketch strokes and identify lines, elliptic arcs, and corners composed of two lines with an optional fillet.
Abstract: This paper presents a method for classifying pen strokes in an on-line sketching system. The method, based on linear least squares fitting to a conic section equation, proposes using the conic equation's natural classification property to help classify sketch strokes and identify lines, elliptic arcs, and corners composed of two lines with an optional fillet. The hyperbola form of the conic equation is used for corner detection. The proposed method has proven to be fast, suitable for real-time classification, and capable of tolerating noisy input, including cusps and spikes. The classification is obtained in o(n) time in a single path, where n is the number of sampled points. In addition, an improved adaptive method for clustering disconnected endpoints is proposed. The notion of in-context analysis is discussed, and examples from a working implementation are given.

88 citations


Proceedings Article
01 Jan 1997
TL;DR: An operator for the detection of the true location and orientation of corners is introduced and its strength in dealing with junctions as well as corners is demonstrated.

66 citations


Journal ArticleDOI
TL;DR: The method is not only fast, with the detected corners stable to rotations and scaling, but also the curvature function presents a high signal-noise relationship, and thus offers excellent performance for real contours.
Abstract: A new method for determining the shape of an object by obtaining its dominant points or border corners is presented. The algorithm uses the contour chain code as descriptor and calculates the curvature of each border point, comparing two histograms of the chain code. The method is not only fast, with the detected corners stable to rotations and scaling, but also the curvature function presents a high signal-noise relationship, and thus offers excellent performance for real contours.

63 citations


Journal ArticleDOI
TL;DR: All features of corners, tangent points and inflection points can be extracted from the boundary of any arbitrary shape by using both artificial neural networks.

61 citations


Book ChapterDOI
08 Oct 1997
TL;DR: The notion of an end-stopped cell and the resulting corner detector is generalized to color channels in a biologically plausible way and yields good results in the presence of high frequency texture, noise, varying contrast, and rounded corners.
Abstract: We present a corner-detection algorithm based on a model for end-stopping cells in the visual cortex. Shortcomings of this model are overcome by a combination over several scales. The notion of an end-stopped cell and the resulting corner detector is generalized to color channels in a biologically plausible way. The resulting corner detection method yields good results in the presence of high frequency texture, noise, varying contrast, and rounded corners. This compares favorably with known corner detectors.

52 citations


Proceedings ArticleDOI
17 Jun 1997
TL;DR: This paper presents an alternative approach-corners along ridges/troughs and local minima points and these features seem to be more reliable for tracking, using a local approximation of the image surface.
Abstract: Traditionally, corners are found along step edges. In this paper we present an alternative approach-corners along ridges/troughs and local minima points. These features seem to be more reliable for tracking. A new approach for sub-pixel localization of these corners is suggested, using a local approximation of the image surface.

39 citations


Book
13 Apr 1997
TL;DR: This paper presents a meta-analysis of statistical linear models used in image segmentation to derive Radial masks in line and edge detection and some approaches to image restoration.
Abstract: Preface 1. Introduction 2. Statistical linear models 3. Line detection 4. Edge detection 5. Object detection 6. Image segmentation 7. Radial masks in line and edge detection 8. Performance analysis 9. Some approaches to image restoration References Index.

38 citations


Proceedings ArticleDOI
17 Jun 1997
TL;DR: The theory and performance characterization of the proposed corner detector is discussed, showing that the algorithm is robust and accurate for complex images and has an average misdetection rate and false alarm rate of 2.5%.
Abstract: This paper presents a statistical approach for detecting corners from chain encoded digital arcs. An arc point is declared as a corner if the estimated parameters of the two fitted lines of the two arc segments immediately to the right and left of the are point are statistically significantly different. The corner detection algorithm consists of two steps: corner detection and optimization. While corner detection involves statistically identifying the most likely corner points along an arc sequence, corner optimization deals with improving the locational errors of the detected corners. The major contributions of this research include developing a method for analytically estimating the covariance matrix of the fitted line parameters and developing a hypothesis test statistic to statistically test the difference between the parameters of two fitted lines. Performance evaluation study showed that the algorithm is robust and accurate for complex images. It has an average misdetection rate of 2.5% and false alarm rate of 2.2% for the complex RADIUS images. This paper discusses the theory and performance characterization of the proposed corner detector.

33 citations


Journal ArticleDOI
TL;DR: The form of the most common differential operators and surface characteristics in the space-variant domain are derived and examples of their use are shown, including the Laplacian, the gradient and the divergence.

21 citations


Journal ArticleDOI
TL;DR: A boundary-constrained morphological method is presented for filling closed curves into shapes which are subsequently used for corner detection and it is demonstrated that the algorithm can be effectively executed on an SIMD parallel computer.

21 citations


Proceedings ArticleDOI
26 Oct 1997
TL;DR: The resulting classifier is a robust, threshold-free corner detector which labels with (approximate) Bayesian posterior probabilities; this is in contrast to conventional feature detectors which produce binary labels contingent on a heuristically set threshold.
Abstract: We present a recasting of corner detection to a problem in statistical pattern recognition which we then address with a simple feedforward neural network. The resulting classifier is a robust, threshold-free corner detector which labels with (approximate) Bayesian posterior probabilities; this is in contrast to conventional feature detectors which produce binary labels contingent on a heuristically set threshold. We have generated the training data for our classifier using a grey-level model of the corner feature which permits sampling of the pattern space at arbitrary density as well as providing a validation set to assess the classifier generalisation. Results are presented for real images and the robustness illustrated over a well-known state-of-the-art conventional corner detector.

Proceedings ArticleDOI
19 May 1997
TL;DR: A new computationally efficient method for the tracking and measurement of center location is presented, well suited to real-time focus-of-attention applications in which regions- of-interest, or windows, are used to reduce image data rates.
Abstract: In this paper, a new computationally efficient method for the tracking and measurement of center location is presented. This algorithm is well suited to real-time focus-of-attention applications in which regions-of-interest, or windows, are used to reduce image data rates. These techniques can be used in robot guidance applications, where high speed image processing is required for real-time position control, such as robot assembly operations in flexible manufacturing. The method is applied in a system based on a 200 frames/s digital camera, programmable gate array technology, and a network of TMS320C40 digital signal processor modules. A real-time motion tracking experiment that uses this corner detection technique is described to demonstrate the advantages of this approach. Experimental results show that the center location of an object in a gray scale image can be determined at 114 Hz.

Journal ArticleDOI
TL;DR: This paper shows the application of the discrete scale-space kernel T(n;t) with continuous parameter to scale- space analysis of digital curves and the corner detector is shown to operate successfully on noisy curves and at varying orientation.

Patent
10 Nov 1997
TL;DR: In this paper, a video signal processing device capable of further decreasing the operator's operation can be realized by inserting the source video signal into the prescribed frame of the video signal, and the operation of the operator can be further decreased.
Abstract: Since the corner detection means (7, 9) to detect each position of the blue board area from video signal, the conversion address generation means (11) to generate the conversion address based on the position information detected and the position information showing each corner position of the image area of video signal to be inserted and the image conversion means (16) to form conversion source video signal based on the conversion address are provided and the source video signal is to be inserted to the video signal, the operator's operation adjustment as the conventional device becomes unnecessary when inserting the source video signal into the prescribed frame of the video signal, and the operation of the operator can be further decreased. Thus, a video signal processing device capable of further decreasing the operator's operation can be realized.

Journal ArticleDOI
Kil-jae Lee1, Zeungnam Bien1
TL;DR: An effective model-based machine vision system is designed for use in practical production lines and a corner matching method is developed to minimize the amount of calculation.

Proceedings ArticleDOI
26 Oct 1997
TL;DR: A new approach to grey-level image corner characterization is proposed, based on the statistical analysis of the gradient-direction in an intensity image, and takes the signal to noise ratio (SNR) into account.
Abstract: A new approach to grey-level image corner characterization is proposed in this paper which is based on the statistical analysis of the gradient-direction in an intensity image, and takes the signal to noise ratio (SNR) into account. The proposed approach can detect corner structure, the number of lines and their orientations which construct the corner; as well as the corner location (intersection point of the lines) in subpixel accuracy. Experiments on both synthetic and real images reveal that the proposed approach can cope well with image noise.

Journal ArticleDOI
TL;DR: The parameters obtained by the presented algorithm are more accurate than those by conventional methods such as the moment method, projection method, and Hough transform methods and can be applied to fast and accurate automatic inspection and placement systems.
Abstract: A two-stage high-precision algorithm for detecting the orientation and position of the surface mount device (SMD) is described. In the preprocessing step, a coarse orientation of the SMD is obtained by line fitting. A high-precision fuzzy Hough transform (FHT) is applied to the corner points to estimate precisely the orientation of the device, with its position determined by using four detected corner points. The FHT employed has a real-valued accumulator over the limited range of angles that is determined in the preprocessing step. Computer simulation with a number of test images shows that the parameters obtained by the presented algorithm are more accurate than those by conventional methods such as the moment method, projection method, and Hough transform methods. It can be applied to fast and accurate automatic inspection and placement systems.

Proceedings ArticleDOI
20 Oct 1997
TL;DR: The overall architecture has been successfully implemented and integrated to a custom machine vision system with real-time edge-extraction and edge-tracking capabilities and some experimental results obtained using this system are presented and discussed.
Abstract: This paper presents a special-purpose VLSI architecture for dominant point extraction along 2D contours. Such dominant points carry useful information for shape analysis and pattern recognition applications since they represent a local shape property and segment object contours into piecewise linear segments and circular arcs. The proposed architecture implements an algorithm based on the curvature primal sketch. It consists of a set of 1D systolic FIR filters performing a multiresolution analysis of the scene's object contours, a set of finite-state-machines extracting zero-crossings and extrema of the filtered data, and a set of scale-space integration cells combining the accurate locations provided by the finest filters with the noise rejection properties of the coarsest ones in order to reliably extract relevant dominant points with accurate localization. The overall architecture has been successfully implemented and integrated to a custom machine vision system with real-time edge-extraction and edge-tracking capabilities. Some experimental results obtained using this system are presented and discussed. Performance issues are also addressed.

Book ChapterDOI
10 Sep 1997
TL;DR: This paper proposes an efficient approach to calculate the response of differential geometric based corner detectors based on convolutions with derivative kernels in 21 or 31 respectively.
Abstract: There are a number of differential geometric based corner detectors in the literature. These operators require 5 or 9 convolutions with derivative kernels in 21) or 31) respectively, what is expensive in terms of time and memory requirements. In this paper we propose an efficient approach to calculate the response of these operators.

BookDOI
01 Jan 1997
TL;DR: Computational complexity reduction in eigenspace approaches.
Abstract: Computational complexity reduction in eigenspace approaches.- An algorithm for intrinsic dimensionality estimation.- Fully unsupervised clustering using centre-surround receptive fields with applications to colour-segmentation.- Multi-sensor fusion with Bayesian inference.- MORAL - A vision-based object recognition system for autonomous mobile systems.- Real-time pedestrian tracking in natural scenes.- Non-rigid object recognition using principal component analysis and geometric hashing.- Object identification with surface signatures.- Computing projective and permutation invariants of points and lines.- Point projective and permutation invariants.- Computing 3D projective invariants from points and lines.- 2D ? 2D geometric transformation invariant to arbitrary translations, rotations and scales.- Extraction of filled-in data from colour forms.- Improvement of vessel segmentation by elastically compensated patient motion in digital subtraction angiography images.- Three-dimensional quasi-binary image restoration for confocal microscopy and its application to dendritic trees.- Mosaicing of flattened images from straight homogeneous generalized cylinders.- Well-posedness of linear shape-from-shading problem.- Comparing convex shapes using Minkowski addition.- Deformation of discrete object surfaces.- Non-Archimedean normalized fields in texture analysis tasks.- The Radon transform-based analysis of bidirectional structural textures.- Textures and structural defects.- Self-calibration from the absolute conic on the plane at infinity.- A badly calibrated camera in ego-motion estimation - propagation of uncertainty.- 6DOF calibration of a camera with respect to the wrist of a 5-axis machine tool.- Automated camera calibration and 3D egomotion estimation for augmented reality applications.- Optimally rotation-equivariant directional derivative kernels.- A hierarchical filter scheme for efficient corner detection.- Defect detection on leather by oriented singularities.- Uniqueness of 3D affine reconstruction of lines with affine cameras.- Distortions of stereoscopic visual space and quadratic Cremona transformations.- Self-evaluation for active vision by the geometric information criterion.- Discrete-time rigidity-constrained optical flow.- An iterative spectral-spatial Bayesian labeling approach for unsupervised robust change detection on remotely sensed multispectral imagery.- Contrast enhancement of badly illuminated images based on Gibbs distribution and random walk model.- Adaptive non-linear predictor for lossless image compression.- Beyond standard regularization theory.- Fast stereovision by coherence detection.- Stereo matching using M-estimators.- Robust location based partial correlation.- Optimization of stereo disparity estimation using the instantaneous frequency.- Segmentation from motion: Combining Gabor- and Mallat-wavelets to overcome aperture and correspondence problem.- Contour segmentation with recurrent neural networks of pulse-coding neurons.- Multigrid MRF based picture segmentation with cellular neural networks.- Computing stochastic completion fields in linear-time using a resolution pyramid.- A Bayesian network for 3d object recognition in range data.- Improving the shape recognition performance of a model with Gabor filter representation.- Bayesian decision versus voting for image retrieval.- A structured neural network invariant to cyclic shifts and rotations.- Morphological grain operators for binary images.- A parallel 12-subiteration 3D thinning algorithm to extract medial lines.- Architectural image segmentation using digital watersheds.- Morphological iterative closest point algorithm.- Planning multiple views for 3-D object recognition and pose determination.- Fast and reliable object pose estimation from line correspondences.- Statistical 3-D object localization without segmentation using wavelet analysis.- A real-time monocular vision-based 3D mouse system.- Face recognition by elastic bunch graph matching.- A conditional mixture of neural networks for face detection, applied to locating and tracking an individual speaker.- Lipreading using Fourier transform over time.- Phantom faces for face analysis.- A new hardware structure for implementation of soft morphological filters.- A method for anisotropy analysis of 3D images.- Fast line and rectangle detection by clustering and grouping.- 1st and 2nd order recursive operators for adaptive edge detection.- Smoothing noisy images without destroying predefined feature carriers.- Local subspace method for pattern recognition.- Testing the effectiveness of Non-Linear Rectification on gabor energy.- Neural-like thinning processing.- Detection of the objects with given shape on the grey-valued pictures.- Automatic parameter selection for object recognition using a parallel multiobjective genetic algorithm.- Unsupervised texture segmentation using Hermite transform filters.- Decomposition of the Hadamard matrices and fast Hadamard transform.- A characterization of digital disks by discrete moments.- "One-step" short-length DCT algorithms with data representation in the direct sum of the associative algebras.- Character extraction from scene image using fuzzy entropy and rule-based technique.- Facial image recognition using neural networks and genetic algorithms.- An energy minimisation approach to the registration, matching and recognition of images.- "Error-free" calculation of the convolution using generalized Mersenne and Fermat transforms over algebraic fields.- A new method of texture binarization.- Parameter optimisation of an image processing system using evolutionary algorithms.- Analysis of learning using segmentation models.- Stereo processing of image data from the Air-Borne CCD-scanner WAAC.- An adaptive method of color road segmentation.- Optical flow detection using a general noise model for gradient constraint.- Algorithmic solution and simulation results for vision-based autonomous mode of a planetary rover.- A framework for feature-based motion recovery in ground plane vehicle navigation.- Terrain reconstruction from multiple views.- Detecting motion independent of the camera movement through a log-polar differential approach.- Coordinate-free camera calibration.- A passive real-time gaze estimation system for human-machine interfaces.- An active vision system for obtaining high resolution depth information.

Proceedings ArticleDOI
E.R. Davies1
14 Jul 1997
TL;DR: A mathematical analysis based on the matched filter concept shows that templates must be adjusted towards zero mean, with weights which take account of mask region areas and associated signal variability parameters.
Abstract: This paper studies the problem of designing optimal templates for detecting variable signals which appear on a varying baseline. A mathematical analysis based on the matched filter concept shows that templates must be adjusted towards zero mean, with weights which take account of mask region areas and associated signal variability parameters. In addition, a new equal area rule is derived and applied to the corner detection problem.

Patent
20 Feb 1997
TL;DR: In this paper, a simple constitution was proposed to detect the corner positions of a specific area from an input signal with simple constitution, where a storage means is provided with a storage key T and a corner detecting means 9C which detects a point where the signal level rises above a reference signal level for the first time by reading the input signal out of the storage means horizontally in order from the upper limit to the lower limit of a retrieval range and reading it out vertically in order in order, from the left end to the right end of the retrieval range.
Abstract: PROBLEM TO BE SOLVED: To detect the respective corner positions of a specific area from an input signal with simple constitution. SOLUTION: This device is provided with a storage means which stores the input signal keyT and a corner detecting means 9C which detects a point where the signal level rises above a reference signal level for the 1st time by reading the input signal out of the storage means horizontally in order from the upper limit to the lower limit of a retrieval range and reading it out vertically in order from the left end to the right end of the retrieval range, detects a point where the signal level rises above the reference signal level for the 1st time by reading the input signal out of the storage means 9B obliquely at a specific angle in order from each corner of the retrieval range, and detects the corner positions by detecting four points differing in position among detected points. Consequently, the respective corner positions of the area to be detected can be detected in a short time with the simple constitution.

Proceedings ArticleDOI
27 Mar 1997
TL;DR: In this article, a new method to detect an automobile registration plate using optical rank order hit-miss transform (HMT) is proposed, in which the optimal structuring elements are designed to recognize the corners of the registration plate and then they are applied to the optical rank-order HMT.
Abstract: A new method to detect an automobile registration plate using optical rank order hit-miss transform (HMT) is proposed. In this method, the optimal structuring elements are designed to recognize the corners of the registration plate and then they are applied to the optical rank order HMT. Optical rank order HMT gives better performance than the standard HMT in noisy or cluttered images. We present that whether the input images have random noise, clutter or not, the proposed method can easily detect automobile registration plates, and also when the detected plate have noise or clutter, they are presented after eliminating the noise or clutter from the detected plates by morphological opening and closing. Computer simulation shows the proposed method has good detection capability and we confirmed this by optical experiment.

Proceedings ArticleDOI
23 Jun 1997
TL;DR: A new method for object recognition based on the trilinearity theorem, a theoretical result from projectile geometry obtained by Shashua, is presented, which achieves a high correct classification rate.
Abstract: We present a new method for object recognition based on the trilinearity theorem, a theoretical result from projectile geometry obtained by Shashua. The trilinearity theorem relates, in a trilinear form, the pixel coordinates of a given object point visible in three images of an object under varying pose. In a preprocessing stage, the object of interest in every image is segmented from its background, and the background is removed. For such segmented images, our system achieves a high correct classification rate. Known objects are represented in the system by a database of images which show the objects as seen from several different viewing directions. In order to utilize the trilinearity theorem for the classification of an input image, it is necessary to construct several triples of closely matching image points -- one point in the input image and one each in two database images of a single object. The triple generation is accomplished by means of Gabor feature vector matching for selected feature points in the images. Using techniques from robust regression, the parameters in the trilinear forms are then determined, and a reprojection of feature points onto one of the three views is performed. The magnitude of the resulting match error then determines whether all three images show the same object, and hence whether recognition of the object in the input image is achieved.