Showing papers on "Corner detection published in 2009"

Image Processing and Mathematical Morphology: Fundamentals and Applications

Abstract: Introduction to Mathematical Morphology Basic Concept in Digital Image Processing Brief History of Mathematical Morphology Essential Morphological Approach to Image Analysis Scope of This Book Binary Morphology Set Operations on Binary Images Logical Operations on Binary Images Binary Dilation Binary Erosion Opening and Closing Hit-or-Miss Transformation Grayscale Morphology Grayscale Dilation and Erosion Grayscale Dilation Erosion Duality Theorem Grayscale Opening and Closing Basic Morphological Algorithms Boundary Extraction Region Filling Extraction of Connected Components Convex Hull Thinning Thickening Skeletonization Pruning Morphological Edge Operator Basic Morphological Filters Alternating Sequential Filters Recursive Morphological Filters Soft Morphological Filters OSSM Filters RSM Filters (RSMFs) ROSSM Filters Regulated Morphological Filters Fuzzy Morphological Filters Distance Transformation DT by Iterative Operations DT by Mathematical Morphology Approximation of Euclidean Distances Decomposition of Distance SEs Iterative Erosion Algorithm Two Scan-Based Algorithm Three-Dimensional Euclidean Distance Acquiring Approaches Deriving Approaches 7 Feature Extraction Edge Linking by MM Corner Detection by Regulated Morphology Shape Database with Hierarchical Features Corner and Circle Detection Size Histogram Object Representation Object Representation and Tolerances Skeletonization or MA Transformation Morphological Shape Description Decomposition of Morphological Structuring Elements Decomposition of Geometric-Shaped SEs Decomposition of Binary SEs Decomposition of Grayscale SEs Architectures for Mathematical Morphology Threshold Decomposition of Grayscale Morphology into Binary Morphology Implementing Morphological Operations Using Programmable Neural Networks MLP as Processing Modules A Systolic Array Architecture Implementation on Multicomputers General Sweep Mathematical Morphology Theoretical Development of General Sweep MM Blending of Sweep Surfaces with Deformations Image Enhancement Edge Linking Geometric Modeling and Sweep MM Formal Language and Sweep Morphology Grammars Parsing Algorithms Morphological Approach to Shortest Path Planning Relationships between Shortest Path Finding and MM Rotational MM The Shortest Path-Finding Algorithm Experimental Results and Discussions Dynamic Rotational MM The Rule of Distance Functions in Shortest Path Planning Index

Combining Harris interest points and the SIFT descriptor for fast scale-invariant object recognition

Abstract: In the recent past, the recognition and localization of objects based on local point features has become a widely accepted and utilized method. Among the most popular features are currently the SIFT features, the more recent SURF features, and region-based features such as the MSER. For time-critical application of object recognition and localization systems operating on such features, the SIFT features are too slow (500–600 ms for images of size 640×480 on a 3GHz CPU). The faster SURF achieve a computation time of 150–240 ms, which is still too slow for active tracking of objects or visual servoing applications. In this paper, we present a combination of the Harris corner detector and the SIFT descriptor, which computes features with a high repeatability and very good matching properties within approx. 20 ms. While just computing the SIFT descriptors for computed Harris interest points would lead to an approach that is not scale-invariant, we will show how scale-invariance can be achieved without a time-consuming scale space analysis. Furthermore, we will present results of successful application of the proposed features within our system for recognition and localization of textured objects. An extensive experimental evaluation proves the practical applicability of our approach.

Geometric Description of Images as Topographic Maps

Abstract: This volume discusses the basic geometric contents of an image and presents a tree data structure to handle those contents efficiently. The nodes of the tree are derived from connected components of level sets of the intensity, while the edges represent inclusion information. Grain filters, morphological operators simplifying these geometric contents, are analyzed and several applications to image comparison and registration, and to edge and corner detection, are presented.The mathematically inclined reader may be most interested in Chapters 2 to 6, which generalize the topological Morse description to continuous or semicontinuous functions, while mathematical morphologists may more closely consider grain filters in Chapter 3. Computer scientists will find algorithmic considerations in Chapters 6 and 7, the full justification of which may be found in Chapters 2 and 4 respectively. Lastly, all readers can learn more about the motivation for this work in the image processing applications presented in Chapter 8.

The Comparison and Application of Corner Detection Algorithms

Abstract: Corners in images represent a lot of important information. Extracting corners accurately is significant to image processing, which can reduce much of the calculations. In this paper, two widely used corner detection algorithms, SUSAN and Harris corner detection algorithms which are both based on intensity, were compared in stability, noise immunity and complexity quantificationally via stability factor η, anti-noise factor ρ and the runtime of each algorithm. It concluded that Harris corner detection algorithm was superior to SUSAN corner detection algorithm on the whole. Moreover, SUSAN and Harris detection algorithms were improved by selecting an adaptive gray difference threshold and by changing directional differentials, respectively, and compared using these three criterions. In addition, SUSAN and Harris corner detectors were applied to an image matching experiment. It was verified that the quantitative evaluations of the corner detection algorithms were valid through calculating match efficiency, defined as correct matching corner pairs dividing by matching time, which can reflect the performances of a corner detection algorithm comprehensively. Furthermore, the better corner detector was used into image mosaic experiment, and the result was satisfied. The work of this paper can provide a direction to the improvement and the utilization of these two corner detection algorithms.

Distance Measurement System Based on Binocular Stereo Vision

Abstract: This system is modeled on the distance perception methods of human eyes. It uses DSP to process the images obtained by two CCD cameras and calculate the distance by the principle of parallax. This paper describes the working principle and hardware platform design. It focuses on the image matching methods based on Canny edge detection and Harris corner detection. The results of the experiment show that the system is efficient and reliable.

Simple real-time human detection using a single correlation filter

Abstract: This paper presents an extremely simple human detection algorithm based on correlating edge magnitude images with a filter. The key is the technology used to train the filter: Average of Synthetic Exact Filters (ASEF). The ASEF based detector can process images at over 25 frames per second and achieves a 94.5% detection rate with less than one false detection per frame for sparse crowds. Filter training is also fast, taking only 12 seconds to train the detector on 32 manually annotated images. Evaluation is performed on the PETS 2009 dataset and results are compared to the OpenCV cascade classifier and a state-of-the-art deformable parts based person detector.

An Improved Algorithm for Harris Corner Detection

Abstract: Corner points are formed from two or more edges and edges usually define the boundary between two different objects or parts of the same objects. In this novel we discuss the theory of the Harris corner detection and indicate its disadvantage. Then it proposes an improved algorithm of Harris detection algorithm based on the neighboring point eliminating method. It reduces the time of the detection, and makes the corners distributing more homogenous so that avoids too many corners stay together. Experimental results show that the algorithm can detect corner more equality distributing, and can be used in some fact applications such as image registration well. Key words-Corner point; Harris corner; neighboring

A Fast and Accurate Algorithm for Chessboard Corner Detection

Abstract: The authors point out the limitations of SUSAN corner detector in detecting chessboard corner, then describe an improved SUSAN(Smallest Univalue Segment Assimilating Nucleus) detector algorithm for detecting chessboard corner on the basis of symmetrical geometry structure of USAN (Univalue Segment Assimilating Nucleus) area. And the algorithm has been applied to the chessboard images on real photos. The improved algorithm can quickly detect corner from real photos shot from every angle. The theory of detecting corner at sub-pixel level is Orthogonal Vector Theory, that is, vector from the corner to its adjacent area pixel point should be vertical to gray grads of the adjacent area pixel point. In order to get the coordinate of corner at sub-pixel level, we establish the neighboring area equation and solve it via iterative method, and propose to check its validity according to cross ratio invariability in perspective projection. Keywords-insert chessboard corner; USAN; sub-pixel; cross ratio invariability

An algebraic model for fast corner detection

Abstract: This paper revisits the classical problem of detecting interest points, popularly known as “corners,” in 2D images by proposing a technique based on fitting algebraic shape models to contours in the edge image. Our method for corner detection is targeted for use on structural images, i.e., images that contain man-made structures for which corner detection algorithms are known to perform well. Further, our detector seeks to find image regions that contain two distinct linear contours that intersect. We define the intersection point as the corner, and, in contrast to previous approaches such as the Harris detector, we consider the spatial coherence of the edge points, i.e., the fact that the edge points must lie close to one of the two intersecting lines, an important aspect to stable corner detection. Comparisons between results for the proposed method and that for several popular feature detectors are provided using input images exhibiting a number of standard image variations, including blurring, affine transformation, scaling, rotation, and illumination variation. A modified version of the repeatability rate is proposed for evaluating the stability of the detector under these variations which requires a 1-to-1 mapping between matched features. Using this performance metric, our method is found to perform well in contrast to several current methods for corner detection. Discussion is provided that motivates our method of evaluation and provides an explanation for the observed performance of our algorithm in contrast to other algorithms. Our approach is distinct from other contour-based methods since we need only compute the edge image, from which we explicitly solve for the unknown linear contours and their intersections that provide image corner location estimates. The key benefits to this approach are: (1) performance (in space and time); since no image pyramid (space) and no edge-linking (time) is required and (2) compactness; the estimated model includes the corner location, and direction of the incoming contours in space, i.e., a complete model of the local corner geometry.

Scale-Space Behavior of Planar-Curve Corners

Abstract: The curvature scale-space (CSS) technique is suitable for extracting curvature features from objects with noisy boundaries. To detect corner points in a multiscale framework, Rattarangsi and Chin investigated the scale-space behavior of planar-curve corners. Unfortunately, their investigation was based on an incorrect assumption, viz., that planar curves have no shrinkage under evolution. In the present paper, this mistake is corrected. First, it is demonstrated that a planar curve may shrink nonuniformly as it evolves across increasing scales. Then, by taking into account the shrinkage effect of evolved curves, the CSS trajectory maps of various corner models are investigated and their properties are summarized. The scale-space trajectory of a corner may either persist, vanish, merge with a neighboring trajectory, or split into several trajectories. The scale-space trajectories of adjacent corners may attract each other when the corners have the same concavity, or repel each other when the corners have opposite concavities. Finally, we present a standard curvature measure for computing the CSS maps of digital curves, with which it is shown that planar-curve corners have consistent scale-space behavior in the digital case as in the continuous case.

Spine Localization in X-ray Images Using Interest Point Detection

Abstract: This study was conducted to evaluate a new method used to calculate vertebra orientation in medical x-ray images. The goal of this work is to develop an x-ray image segmentation approach used to identify the location and the orientation of the cervical vertebrae in medical images. We propose a method for localization of vertebrae by extracting the anterior—left—faces of vertebra contours. This approach is based on automatic corner points of interest detection. For this task, we use the Harris corner detector. The final goal is to determine vertebral motion induced by their movement between two or several positions. The proposed system proceeds in several phases as follows: (a) image acquisition, (b) corner detection, (c) extracting of the corners belonging to vertebra left sides, (d) global estimation of the spine curvature, and (e) anterior face vertebra detection.

3D reconstruction based on SIFT and Harris feature points

Abstract: This paper presents a new 3D reconstruction method using feature points extracted by the SIFT and Harris corner detector. Since the SIFT feature points can be detected stably and relatively accurately, the proposed algorithm first uses the SIFT matching points to calculate the fundamental matrix. On the other hand many of the feature points detected by the SIFT are not what we need for reconstruction, so by combining the SIFT feature points with the Harris corners it is possible to obtain more vivid and detailed 3D information. Experiments have been conducted to validate the proposed method.

Optimizing the SUSAN corner detection algorithm for a high speed FPGA implementation

Abstract: In many embedded systems for video surveillance distinctive features are used for the detection of objects. In this contribution a real-time FPGA implementation of a feature detector, namely the SUSAN algorithm is described. As the original SUSAN algorithm performs poorly on non-synthetic images a significant quality improvement of this algorithm is presented. The hardware accelerator outperforms a comparable software version running on an Intel Core2Duo E8400 core at 3.00GHz and delivers almost the same execution time compared to an implementation of the Harris corner detector running on an Nvidia GeForce 8800 GTX GPU.

Road shape estimating device, road shape estimating method and program

Abstract: A road shape estimating device has a data obtaining processing unit for obtaining interpolation point data for a plurality of shape interpolation points which are set along a road and represent a shape of the road, a radius calculation processing unit for calculating a radius of curvature at each of the shape interpolation points based on the interpolation point data for a predetermined section of the road, a corner detection processing unit for detecting a corner in the predetermined section based on the radii of curvature, and a corner dividing processing unit for dividing the corner at a shape interpolation point having a radius of curvature equal to or larger than a threshold in the detected corner. The threshold is set corresponding to an average value of radii of curvature at respective shape interpolation points in the detected corner.

A Fast and Accurate Corner Detector Based on Harris Algorithm

Abstract: Harris is one of the most widely used corner detection algorithms which is based on intensity. Because of the practice of Gaussian smoothing link, Harris algorithm has a good performance on its stability and robustness, but it is also the direct reason of the limitation of its computing speed. Furthermore, its positioning accuracy of T-type, L-type and Arrow-type corners is low. In this paper, an improved algorithm is presented to solve the efficiency and accuracy problem of Harris algorithm. Firstly, we integrated the corner response function of MIC algorithm into the Harris algorithm to reduce the calculation amount of Gaussian smoothing link, so that the computing speed is obviously increased. Then we investigate a 3×3 mask to calculate the number of the pixels which their gray values are similar to the central point of the mask. We found that for real corner, the number of its similar points is the minimum among its 8 neighborhoods. In view of this, we added a comparison function before the No Max Suppression step to exclude some disturbance points nearby the real corners. Hence the positioning accuracy is increased significantly. In order to compare the accuracy of the improved algorithm and Harris algorithm, an evaluation standard is also proposed. The experimental results show that the detection time of the improved algorithm is only 31.2% that of the original Harris algorithm, and also, the improvement on positioning accuracy of L-type, T-type and Arrow-type corners are realized.

Facial Features for Template Matching Based Face Recognition

Abstract: Problem statement: Template matching had been a conventional method for object detection especially facial features detection at t he early stage of face recognition research. The appearance of moustache and beard had affected the performance of features detection and face recognition system since ages ago. Approach: The proposed algorithm aimed to reduce the effect of beard and moustache for facial features detection a nd introduce facial features based template matching as the classification method. An automated algorithm for face recognition system based on detected facial features, iris and mouth had been d eveloped. First, the face region was located using skin color information. Next, the algorithm compute d the costs for each pair of iris candidates from intensity valleys as references for iris selection. As for mouth detection, color space method was use d to allocate lips region, image processing methods t o eliminate unwanted noises and corner detection technique to refine the exact location of mouth. Fi nally, template matching was used to classify faces based on the extracted features. Results: The proposed method had shown a better features detection rate (iris = 93.06%, mouth = 95.83%) than conventio nal method. Template matching had achieved a recognition rate of 86.11% with acceptable processi ng time (0.36 sec). Conclusion: The results indicate that the elimination of moustache and bear d has not affected the performance of facial featur es detection. The proposed features based template mat ching has significantly improved the processing time of this method in face recognition research.

Affine Adaptation of Local Image Features Using the Hessian Matrix

Abstract: Local feature detectors that make use of derivative based saliency functions to locate points of interest typically require adaptation processes after initial detection in order to achieve scale and affine covariance. Affine adaptation methods have previously been proposed that make use of the second moment matrix to iteratively estimate the affine shape of local image regions. This paper shows that it is possible to use the Hessian matrix to estimate local affine shape in a similar fashion to the second moment matrix. The Hessian matrix requires significantly less computation effort to compute than the second moment matrix, allowing more efficient affine adaptation. It may also be more convenient to use the Hessian matrix, for example, when the Determinant of Hessian detector is used. Experimental evaluation shows that the Hessian matrix is very effective in increasing the efficiency of blob detectors such as the Determinant of Hessian detector, but less effective in combination with the Harris corner detector.

A multi-scale bilateral structure tensor based corner detector

Abstract: In this paper, a novel multi-scale nonlinear structure tensor based corner detection algorithm is proposed to improve effectively the classical Harris corner detector. By considering both the spatial and gradient distances of neighboring pixels, a nonlinear bilateral structure tensor is constructed to examine the image local pattern. It can be seen that the linear structure tensor used in the original Harris corner detector is a special case of the proposed bilateral one by considering only the spatial distance. Moreover, a multi-scale filtering scheme is developed to tell the trivial structures from true corners based on their different characteristics in multiple scales. The comparison between the proposed approach and four representative and state-of-the-art corner detectors shows that our method has much better performance in terms of both detection rate and localization accuracy.

Sort, merge, repeat: an algorithm for effectively finding corners in hand-sketched strokes

Abstract: Free-sketch recognition systems attempt to recognize freely-drawn sketches without placing stylistic constraints on the users. Such systems often recognize shapes by using geometric primitives that describe the shape's appearance rather than how it was drawn. A free-sketch recognition system necessarily allows users to draw several primitives using a single stroke. Corner finding, or vertex detection, is used to segment these strokes into their underlying primitives (lines and arcs), which in turn can be passed to the geometric recognizers. In this paper, we present a new multi-pass corner finding algorithm called MergeCF that is based on continually merging smaller stroke segments with similar, larger stroke segments in order to eliminate false positive corners. We compare MergeCF to two benchmark corner finders with substantial improvements in corner detection.

A comparative study of different corner detection methods

Abstract: Interest points are widely used in computer vision applications such as camera calibration, robot localization and object tracking that require fast and efficient feature matching. A large number of techniques have been proposed in the literature. This paper evaluates the state of art techniques for interest point detection including excution time and suitability for real time applications. Such comparative study is crucial for specific applications, since it is always necessary to understand the advantages and disadvantages of the existing techniques so that best possible ones can be selected. The comparative study shows that: (1) the CSS method performs best in corner extraction. It is the fast and the most reliable and has the lowest noise sensitivity with the highest true corner detection rate, even though it still detects some false corners; (2) SUSAN detector would be the second choice and is acceptable and useful in applications requiring a computationally efficient detector and working on a restricted set of images.

A Nonlinear Structure Tensor with the Diffusivity Matrix Composed of the Image Gradient

Abstract: We propose a nonlinear partial differential equation (PDE) for regularizing a tensor which contains the first derivative information of an image such as strength of edges and a direction of the gradient of the image. Unlike a typical diffusivity matrix which consists of derivatives of a tensor data, we propose a diffusivity matrix which consists of the tensor data itself, i.e., derivatives of an image. This allows directional smoothing for the tensor along edges which are not in the tensor but in the image. That is, a tensor in the proposed PDE is diffused fast along edges of an image but slowly across them. Since we have a regularized tensor which properly represents the first derivative information of an image, the tensor is useful to improve the quality of image denoising, image enhancement, corner detection, and ramp preserving denoising. We also prove the uniqueness and existence of solution to the proposed PDE.

A Novel Method for Eye Corner Detection Based on Weighted Variance Projection Function

Abstract: A novel eye corner detection method is presented in this paper. The method is capable of detecting a pair of inner and outer eye corners from a complex background. Faces and eyes are first detected from the image by Adaboost with Haar-like features. Next, the potential area of the eye corner is determined based on variance projection function. In view of the corner characteristics of the eye corner, the weighted variance projection function is proposed to locate the eye corner within the potential area, which combines Harris's response function with variance projection function. The robustness and accuracy of the proposed method are demonstrated in experiment.

Method for correcting distortion of image projected by projector, and projector

Abstract: A method for correcting distortion of an image projected by a projector includes: a first detection image data producing step which produces first detection image data containing marker images; a first detection image displaying step which displays a first detection image; a first image comparing step which compares the first detection image with the first detection image data; an area selecting step which selects an area having larger distortion of the detection image than distortion in other area based on the comparison; a second detection image data producing step which increases positioning density of the marker images in the selected area to produce second detection image data; a second detection image displaying step which displays the second detection image; a second image comparing step which compares the second detection image with the second detection image data; and an image correcting step which corrects the projection image.

Performance Evaluation of the Covariance Descriptor for Target Detection

Abstract: In computer vision, there has been a strong advance in creating new image descriptors. A descriptor that has recently appeared is the Covariance Descriptor, but there have not been any studies about the different methodologies for its construction. To address this problem we have conducted an analysis on the contribution of diverse features of an image to the descriptor and therefore their contribution to the detection of varied targets, in our case: faces and pedestrians. That is why we have defined a methodology to determinate the performance of the covariance matrix created from different characteristics. Now we are able to determinate the best set of features for face and people detection, for each problem. We have also achieved to establish that not any kind of combination of features can be used because it might not exist a correlation between them. Finally, when an analysis is performed with the best set of features, for the face detection problem we reach a performance of 99%, meanwhile for the pedestrian detection problem we reach a performance of 85%. With this we hope we have built a more solid base when choosing features for this descriptor, allowing to move forward to other topics such as object recognition or tracking.

An Improved Corner Detection Method Based on Harris

Abstract: By the study of the Harris corner detection algorithm,while some images' corners are extracted,there exists the following problems: extracting false corners,the information of the corners is missing,the positioning of the corners offsets.And also not easy to set up the threshold in non-maximal inhibition.Presents to set up a dual threshold method,one is relatively large,and the other is relatively small when perform the non-maximal inhibition,so get the corners information of different thresholds in the same image,through comparing the corners information,can better solve the corners information missing,location offsetting and eliminate some false corners,and then using the idea of the SUSAN to eliminate the leaving false corners.By comparing the results show that the algorithm to extract corners very effective,and better than the Harris algorithm in the performance of corner detection.

Information acquisition and transfer method of auxiliary vision system

Abstract: The invention discloses an information acquisition and transfer method for assistant vision systems. The method comprises the following steps: (1) extracting two original digital images of an object in different angles by using two cameras at the same time; (2) extracting characteristic points of the two original digital images by means of the Harris corner detection; (3) extracting three-dimensional geometrical information of the characteristic points by using the two cameras; (4) making a rectangular region where each characteristic point serves as the center, finding out the position of the next frame characteristic point and calculating motion vectors of the characteristic point; (5) dividing the road surface information of the original digital image by using a color histogram, according to the chromatic information and calculating the road information; (6) coding the motion information of the characteristic point of the original image, the three-dimensional geometrical information of the characteristic point and the road information respectively; and (7) transferring the coded information to a person with vision disorders via the information transfer array unit in the assistant vision system. The information acquisition and transfer method is advantageous in the accurate extraction of three-dimensional geometrical information of the object, and helps the patients with vision disorders to walk directionally and safely.

An improved corner point detection using extreme value of Susan method for measuring a displacement

Abstract: This paper proposes the corner point detection algorithm which uses extreme value from Gray Level image. There are various methods to detect corner point. Corner point includes information about the length and shape of model. Preprocessing step is required to detect corner point. First, the model image is converted to gray-level image. After removing noise from converted image, edge lines are detected by edge detection algorithm. Existing SUSAN algorithm detects edge line by using area, but also detects wrong corner points. But proposed extreme value method only detects corner point which belongs to the defined area, so detection ratio can be increased. Proposed method can be used to detect model's exact displacement or to perform 3-D reconstruction.

Fuzzy Edge and Corner Detector for Color Images

Abstract: Localization of edges and corner points by fuzzy detectors in images is the main concern of this paper. This paper presents an approach to edge and corner detection based on fuzzy logic. In this approach SUSAN mask is employed to compute USAN area. The histogram of USAN area permits us construct type 1 and type 2 fuzzy membership functions by fuzzifying USAN area computed about every pixel in an image. The edge map of the image is obtained using adaptive thresholding. An attempt is made to extend the proposed approach to the detection of colour edges. Experiments show that this approach is less sensitive to noise without causing edge displacement.