Showing papers on "Corner detection published in 2006"

Machine learning for high-speed corner detection

Abstract: Where feature points are used in real-time frame-rate applications, a high-speed feature detector is necessary. Feature detectors such as SIFT (DoG), Harris and SUSAN are good methods which yield high quality features, however they are too computationally intensive for use in real-time applications of any complexity. Here we show that machine learning can be used to derive a feature detector which can fully process live PAL video using less than 7% of the available processing time. By comparison neither the Harris detector (120%) nor the detection stage of SIFT (300%) can operate at full frame rate. Clearly a high-speed detector is of limited use if the features produced are unsuitable for downstream processing. In particular, the same scene viewed from two different positions should yield features which correspond to the same real-world 3D locations [1]. Hence the second contribution of this paper is a comparison corner detectors based on this criterion applied to 3D scenes. This comparison supports a number of claims made elsewhere concerning existing corner detectors. Further, contrary to our initial expectations, we show that despite being principally constructed for speed, our detector significantly outperforms existing feature detectors according to this criterion.

Machine Learning for High-Speed Corner Detection

Abstract: Where feature points are used in real-time frame-rate applications, a high-speed feature detector is necessary. Feature detectors such as SIFT (DoG), Harris and SUSAN are good methods which yield high quality features, however they are too computationally intensive for use in real-time applications of any complexity. Here we show that machine learning can be used to derive a feature detector which can fully process live PAL video using less than 7% of the available processing time. By comparison neither the Harris detector (120%) nor the detection stage of SIFT (300%) can operate at full frame rate. Clearly a high-speed detector is of limited use if the features produced are unsuitable for downstream processing. In particular, the same scene viewed from two different positions should yield features which correspond to the same real-world 3D locations[1]. Hence the second contribution of this paper is a comparison corner detectors based on this criterion applied to 3D scenes. This comparison supports a number of claims made elsewhere concerning existing corner detectors. Further, contrary to our initial expectations, we show that despite being principally constructed for speed, our detector significantly outperforms existing feature detectors according to this criterion. © Springer-Verlag Berlin Heidelberg 2006.

Adaptive Structure Tensors and their Applications

Abstract: The structure tensor, also known as second moment matrix or Forstner interest operator, is a very popular tool in image processing. Its purpose is the estimation of orientation and the local analysis of structure in general. It is based on the integration of data from a local neighborhood. Normally, this neighborhood is defined by a Gaussian window function and the structure tensor is computed by the weighted sum within this window. Some recently proposed methods, however, adapt the computation of the structure tensor to the image data. There are several ways how to do that. This chapter wants to give an overview of the different approaches, whereas the focus lies on the methods based on robust statistics and nonlinear diffusion. Furthermore, the data-adaptive structure tensors are evaluated in some applications. Here the main focus lies on optic flow estimation, but also texture analysis and corner detection are considered.

Obstacle Avoidance For Unmanned Air Vehicles Using Image Feature Tracking

Abstract: This paper discusses a computer vision algorithm and a control law for obstacle avoidance for small unmanned air vehicles using a video camera as the primary sensor. Small UAVs are used for low altitude surveillance ∞ights where unknown obstacles can be encountered. Small UAVs can be given the capability to navigate in uncertain environments if obstacles are identifled. This paper presents an obstacle detection methodology using feature tracking in a forward looking, onboard camera. Features are found using the Harris Corner Detector and tracked through multiple video frames which provides three dimensional localization of the salient features. A sparse three dimensional map of features provides a rough estimate of obstacle locations. The features are grouped into potentially problematic areas using agglomerative clustering. The small UAV then employs a sliding mode control law in the autopilot to avoid obstacles.

SIFT and shape context for feature-based nonlinear registration of thoracic CT images

Abstract: Nonlinear image registration is a prerequisite for various medical image analysis applications. Many data acquisition protocols suffer from problems due to breathing motion which has to be taken into account for further analysis. Intensity based nonlinear registration is often used to align differing images, however this requires a large computational effort, is sensitive to intensity variations and has problems with matching small structures. In this work a feature-based image registration method is proposed that combines runtime efficiency with good registration accuracy by making use of a fully automatic feature matching and registration approach. The algorithm stages are 3D corner detection, calculation of local (SIFT) and global (Shape Context) 3D descriptors, robust feature matching and calculation of a dense displacement field. An evaluation of the algorithm on seven synthetic and four clinical data sets is presented. The quantitative and qualitative evaluations show lower runtime and superior results when compared to the Demons algorithm.

A new approach to corner detection

Abstract: A new approach for detection of corner points in planar curves is presented in this paper Detection of corner point is based on calculation of distances from the straight line joining two contour points on two sides of that corner The presented algorithm is simple to implement, efficient and robust to noise It performs well on noisy shapes and leads to various applications Results of this algorithm are compared with some commonly referred corner detectors

Multiscale Contour Corner Detection Based on Local Natural Scale

Abstract: A new corner detection method for contour images is proposed based on dyadic wavelet transform (WT) at local natural scales. The points corresponding to wavelet transform modulus maxima (WTMM) at difierent scales are taken as corner candidates. For each candidate, the scale at which the maximum value of the normalized WTMM exists is deflned as its \local natural scale", and the corresponding modulus is taken as its signiflcance measure. This approach achieves more accurate estimation of the natural scale of each candidate than the existing global natural scale based methods. Furthermore, the proposed algorithm is suitable for both long contours and short contours. The simulation and the objective evaluation results reveal better performance of the proposed algorithm compared to the existing methods.

A Proposed Pipelined-Architecture for FPGA-Based Affine-Invariant Feature Detectors

Abstract: This paper describes a hardware architecture for an FPGAbased implementation of affine-invariant image feature detectors, following the algorithm of Mikolajczyk & Schmid. The architecture mimics the structure of the algorithm by implementing a multi-scale Harris corner detector which feeds candidate points into an iterative procedure to determine the local affine shape of the feature’s neighbourhood (up to an undetermined rotation). Since the algorithm is iterative, and since we desire a high throughput rate, the iterations are "unrolled" into a sequence of identical computation blocks arranged in a pipeline architecture. The modularity of the resulting architecture allows for scaling the implementation to devices of different resource capacity, as well as partitioning the algorithm over several devices. The final implementation, when completed, will be part of a smart-camera system which outputs features at the same time as the associated images.

A video shot boundary detection algorithm based on feature tracking

Abstract: Partitioning a video sequence into shots is the first and key step toward video-content analysis and content-based video browsing and retrieval A novel video shot boundary detection algorithm is presented based on the feature tracking First, the proposed algorithm extracts a set of corner-points as features from the first frame of a shot Then, based on the Kalman filtering, these features are tracked with windows matching method from the subsequent frames According to the characteristic pattern of pixels intensity changing between corresponding windows, the measure of shot boundary detection can be obtained to confirm the types of transitions and the time interval of gradual transitions The experimental results illustrate that the proposed algorithm is effective and robust with low computational complexity

Advanced concepts for intelligent vision systems : 8th International Conference, ACIVS 2006, Antwerp, Belgium, September 18-21, 2006, proceedings

Abstract: Noise Reduction and Restoration.- Directional Filtering for Upsampling According to Direction Information of the Base Layer in the JVT/SVC Codec.- A New Fuzzy-Based Wavelet Shrinkage Image Denoising Technique.- Mathematical Models for Restoration of Baroque Paintings.- Motion Blur Concealment of Digital Video Using Invariant Features.- Hybrid Sigma Filter for Processing Images Corrupted by Multiplicative Noise.- Automatic Restoration of Old Motion Picture Films Using Spatiotemporal Exemplar-Based Inpainting.- Dedicated Hardware for Real-Time Computation of Second-Order Statistical Features for High Resolution Images.- Greyscale Image Interpolation Using Mathematical Morphology.- Dilation Matrices for Nonseparable Bidimensional Wavelets.- Evolutionary Tree-Structured Filter for Impulse Noise Removal.- Perceived Image Quality Measurement of State-of-the-Art Noise Reduction Schemes.- Multiway Filtering Applied on Hyperspectral Images.- Segmentation.- A Linear-Time Approach for Image Segmentation Using Graph-Cut Measures.- The RIM Framework for Image Processing.- A Proposal Method for Corner Detection with an Orthogonal Three-Direction Chain Code.- A Charged Active Contour Based on Electrostatics.- Comparison of Statistical and Shape-Based Approaches for Non-rigid Motion Tracking with Missing Data Using a Particle Filter.- An Active Contour Model Guided by LBP Distributions.- Characterizing the Lacunarity of Objects and Image Sets and Its Use as a Technique for the Analysis of Textural Patterns.- Adaptive Vision Leveraging Digital Retinas: Extracting Meaningful Segments.- A Fast Dynamic Border Linking Algorithm for Region Merging.- Motion Estimation and Tracking.- Fast Sub-pixel Motion Estimation for H.264.- Temporal Error Concealment Based on Optical Flow in the H.264/AVC Standard.- Foreground-to-Ghost Discrimination in Single-Difference Pre-processing.- Moving Object Removal Based on Global Feature Registration.- Object Tracking Using Discriminative Feature Selection.- Color-Based Multiple Agent Tracking for Wireless Image Sensor Networks.- A Fast Motion Vector Search Algorithm for Variable Blocks.- Video Processing and Coding.- Constrained Region-Growing and Edge Enhancement Towards Automated Semantic Video Object Segmentation.- Spatio-temporal Composite-Features for Motion Analysis and Segmentation.- New Intra Luma Prediction Mode in H.264/AVC Using Collocated Weighted Chroma Pixel Value.- Fast Mode Decision for H.264/AVC Using Mode Prediction.- Performing Deblocking in Video Coding Based on Spatial-Domain Motion-Compensated Temporal Filtering.- Improving DCT-Based Coders Through Block Oriented Transforms.- Improvement of Conventional Deinterlacing Methods with Extrema Detection and Interpolation.- Adaptive Macroblock Mode Selection for Reducing the Encoder Complexity in H.264.- Dynamic Light Field Compression Using Shared Fields and Region Blocks for Streaming Service.- Complexity Scalability in Motion-Compensated Wavelet-Based Video Coding.- Spatial Error Concealment with Low Complexity in the H.264 Standard.- A Real-Time Content Adaptation Framework for Exploiting ROI Scalability in H.264/AVC.- Complexity Reduction Algorithm for Intra Mode Selection in H.264/AVC Video Coding.- Simple and Effective Filter to Remove Corner Outlier Artifacts in Highly Compressed Video.- Content-Based Model Template Adaptation and Real-Time System for Behavior Interpretation in Sports Video.- New Approach to Wireless Video Compression with Low Complexity.- Fast Multi-view Disparity Estimation for Multi-view Video Systems.- AddCanny: Edge Detector for Video Processing.- Video-Based Facial Expression Hallucination: A Two- Level Hierarchical Fusion Approach.- Blue Sky Detection for Picture Quality Enhancement.- Requantization Transcoding in Pixel and Frequency Domain for Intra 16x16 in H.264/AVC.- Motion-Compensated Deinterlacing Using Edge Information.- Video Enhancement for Underwater Exploration Using Forward Looking Sonar.- Camera Calibration, Image Registration and Stereo Matching.- Optimal Parameters Selection for Non-parametric Image Registration Methods.- Camera Calibration from a Single Frame of Planar Pattern.- Stereo Matching Using Scanline Disparity Discontinuity Optimization.- A New Stereo Matching Model Using Visibility Constraint Based on Disparity Consistency.- Refine Stereo Correspondence Using Bayesian Network and Dynamic Programming on a Color Based Minimal Span Tree.- Estimation of Rotation Parameters from Blurred Image.- Hierarchical Stereo Matching: From Foreground to Background.- Biometrics and Security.- Gabor Feature Based Face Recognition Using Supervised Locality Preserving Projection.- Alternative Fuzzy Clustering Algorithms with L1-Norm and Covariance Matrix.- A Statistical Approach for Ownership Identification of Digital Images.- Rigid and Non-rigid Face Motion Tracking by Aligning Texture Maps and Stereo-Based 3D Models.- Curve Mapping Based Illumination Adjustment for Face Detection.- Common Image Method(Null Space + 2DPCAs) for Face Recognition.- Discrete Choice Models for Static Facial Expression Recognition.- Scalable and Channel-Adaptive Unequal Error Protection of Images with LDPC Codes.- Robust Analysis of Silhouettes by Morphological Size Distributions.- Enhanced Watermarking Scheme Based on Texture Analysis.- A Robust Watermarking Algorithm Using Attack Pattern Analysis.- Probability Approximation Using Best-Tree Distribution for Skin Detection.- Fusion Method of Fingerprint Quality Evaluation: From the Local Gabor Feature to the Global Spatial-Frequency Structures.- 3D Face Recognition Based on Non-iterative Registration and Single B-Spline Patch Modelling Techniques.- Automatic Denoising of 2D Color Face Images Using Recursive PCA Reconstruction.- Facial Analysis and Synthesis Scheme.- Medical Imaging.- Detection of Pathological Cells in Phase Contrast Cytological Images.- Water Flow Based Complex Feature Extraction.- Seeded Region Merging Based on Gradient Vector Flow for Image Segmentation.- System for Reading Braille Embossed on Beverage Can Lids for Authentication.- Leukocyte Segmentation in Blood Smear Images Using Region-Based Active Contours.- Multiresolution Lossy-to-Lossless Coding of MRI Objects.- A Novel Fuzzy Segmentation Approach for Brain MRI.- Extrema Temporal Chaining: A New Method for Computing the 2D-Displacement Field of the Heart from Tagged MRI.- Data Fusion and Fuzzy Spatial Relationships for Locating Deep Brain Stimulation Targets in Magnetic Resonance Images.- Robust Tracking of Migrating Cells Using Four-Color Level Set Segmentation.- Image Retrieval and Image Understanding.- Robust Visual Identifier for Cropped Natural Photos.- Affine Epipolar Direction from Two Views of a Planar Contour.- Toward Visually Inferring the Underlying Causal Mechanism in a Traffic-Light-Controlled Crossroads.- Computer Vision Based Travel Aid for the Blind Crossing Roads.- A Novel Stochastic Attributed Relational Graph Matching Based on Relation Vector Space Analysis.- A New Similarity Measure for Random Signatures: Perceptually Modified Hausdorff Distance.- Tracking of Linear Appearance Models Using Second Order Minimization.- Visibility of Point Clouds and Mapping of Unknown Environments.- Adjustment for Discrepancies Between ALS Data Strips Using a Contour Tree Algorithm.- Visual Bootstrapping for Unsupervised Symbol Grounding.- A 3D Model Acquisition System Based on a Sequence of Projected Level Curves.- Scale Invariant Robust Registration of 3D-Point Data and a Triangle Mesh by Global Optimization.- Fast Hough Transform Based on 3D Image Space Division.- Context-Based Scene Recognition Using Bayesian Networks with Scale-Invariant Feature Transform.- A Portable and Low-Cost E-Learning Video Capture System.- On Building Omnidirectional Image Signatures Using Haar Invariant Features: Application to the Localization of Robots.- Accurate 3D Structure Measurements from Two Uncalibrated Views.- A Fast Offline Building Recognition Application on a Mobile Telephone.- Adaptive Learning Procedure for a Network of Spiking Neurons and Visual Pattern Recognition.- Interactive Learning of Scene Context Extractor Using Combination of Bayesian Network and Logic Network.- Classification and Recognition.- Adaptative Road Lanes Detection and Classification.- An Approach to the Recognition of Informational Traffic Signs Based on 2-D Homography and SVMs.- On Using a Dissimilarity Representation Method to Solve the Small Sample Size Problem for Face Recognition.- A Comparison of Nearest Neighbor Search Algorithms for Generic Object Recognition.- Non Orthogonal Component Analysis: Application to Anomaly Detection.- A Rough Set Approach to Video Genre Classification.

Evaluation of Intensity and Color Corner Detectors for Affine Invariant Salient Regions

Abstract: Global features are commonly used to describe the image content. The problem with this approach is that these features cannot capture all parts of the image having different characteristics. Therefore, local computation of image information is necessary. By using salient points to represent local information, more discriminative features can be computed. This research is based on an existing affine invariant local feature detector, in which the features are assumed to be intensity corners. First, the existing algorithm is extended with the intensity based SUSAN corner detector which fundamentally differs from the original Harris corner detector. Second, the algorithm is extended to incorporate color information into the detection process. This results in a comparison between three different detection algorithms: the intensity based algorithm using the Harris or SUSAN detector and a color based algorithm that uses two color extended Harris detectors. The different algorithms are compared in terms of invariance and distinctiveness of the regions and computational complexity.

A venation-based leaf image classification scheme

Abstract: Most content-based image retrieval systems use image features such as textures, colors, and shapes However, in the case of leaf image, it is not appropriate to rely on color or texture features only because such features are similar in most leaves In this paper, we propose a novel leaf image retrieval scheme which first analyzes leaf venation for leaf categorization and then extracts and utilizes shape feature to find similar ones from the categorized group in the database The venation of a leaf corresponds to the blood vessel of organisms Leaf venations are represented using points selected by the curvature scale scope corner detection method on the venation image, and categorized by calculating the density of feature points using non-parametric estimation density We show its effectiveness by performing several experiments on the prototype system

Morphological Edge Detection and Corner Detection Algorithm Using Chain Encoding.

Abstract: Edges and corners are regions of interest where there is a sudden change in intensity. These features play an important role in object identification methods used in machine vision and image processing systems. This paper presents a novel method for edge and corner detection in images. The approach used here is extracting Edges of the input image using morphological operator and then sending it for Chain Encoding. We are proposing a new morphological edge detector which returns a one pixel thick m-connected binary boundary image. This is followed by our chain encoding method to detect corners on the extracted edges. The algorithm works on all types of images (i.e. binary, gray level and color images). Since the proposed methods are based on morphological operations, these are very simple, efficient and fast. Experimental results on a variety of images identified all the prominent edges and significant corners efficiently.

Automatic 3D Building Extraction from Stereo IKONOS Images

Abstract: In 3D GIS research and development, how to effectively acquire and input a large amount of 3D buildings is always a tough challenge. To date, as the most stable and accurate method, through a photogrammetric instrument, manually measuring buildings one by one, is really a tiring and time-consuming work. Therefore, many researchers have been trying to develop semi-automatic building extraction method or even completely automatic building extraction methods. In this paper we introduce a new method of automatic 3D building extraction based on stereo Ikonos images. This method includes several steps, such as edge detection and connection, building block detection and corner detection, and building extraction and image matching. The final result is 3D coordinates of buildings. We used a scene of stereo images to test our program. Only about 15 minutes were needed to process a scene of Ikonos image (2613 by 3539 pixels). The final result is reported. Corresponding discussions are conducted and conclusions are given based on the test results and discussions.

Towards a Robust Feature-Based Watermarking Scheme

Abstract: This paper presents a feature-based watermarking scheme which is robust to geometric and common image processing attacks. The improved Harris corner detector is used to find the robust feature points, which correspond to high corner responses and survive various attacks. The watermark is embedded in the Fourier frequency domain of the disk area centered at each feature point to ensure the resilience to the local attacks and common image processing. The image normalization method is adopted to determine the possible rotation for reducing synchronization errors between the embedded and extracted watermarks. The watermark detection decision is based on the number of matched disks in terms of the number of matched bits between the recovered and embedded watermarks in embedding blocks. Experimental results demonstrate that our scheme is more robust to geometric and common image processing attacks than the peer feature-point-based approaches.

An image mosaic method based on interest points matching

Abstract: Since the corresponding pair of feature points was difficult to be extracted in feature points registration methods, an image mosaic method based on interest point matching was presented Firstly, the interest points from two images were extracted by Harris corner detector, then the corresponding interest point pair of features were got by comparison maximum algorithm At last the images could be stitched by the corresponding pair of featuresThe experiments show that this algorithm can efficiently avoid the affect of false interest point pair of features, reducing the likelihood of false matching at the same time This algorithm can be applied in panoramic images successfully

Corner detection using morphological skeleton: an efficient and nonparametric approach

Abstract: In this paper we propose an effective and robust approach for detecting corner points on a given binary image. Unlike other corner detection methods the proposed method is non-parametric in nature, that is, it does not require any input parameter. The proposed method is based on mathematical morphology. It makes use of morphological skeleton for detecting corner points. Convex corner points are obtained by intersecting the morphological boundary and the corresponding skeleton, where as the concave corner points are obtained by intersecting the boundary and the skeleton of the complement image. Experimental results show that the proposed method is more robust and efficient in detecting corner points.

Feature Motion for Monocular Robot Navigation

Abstract: Monocular vision based robot navigation requires feature tracking for localization. In this paper we present a tracking system using discriminative features as well as less discriminative features. Discriminative features such as SIFT are easily tracked and useful to obtain the initial estimates of the transforms such as affinities and homographies. On the other hand less discriminative features such as Harris corners and manually selected features are not easily tracked in a subsequent frame due to problems in matching. We use SIFT features to obtain the the estimates of the planar homographies representing the motion of the major planar structures in the scene. Planar structure assumption is valid for indoor and architectural scenes. The combination of discriminative and less discriminative feature are tracked using the prediction by these homographies. Then normalized cross correlation matching is used to find the exact matches. This produces robust matching and feature motion can be accurately estimated. We show the performance of our system with real image sequences.

Self-calibration with two views using the scale-invariant feature transform

Abstract: In this paper, we present a self-calibration strategy to estimate camera intrinsic and extrinsic parameters using the scale-invariant feature transform (SIFT). The accuracy of the estimated parameters depends on how reliably a set of image correspondences is established. The SIFT employed in the self-calibration algorithms plays an important role in accurate estimation of camera parameters, because of its robustness to changes in viewing conditions. Under the assumption that the camera intrinsic parameters are constant, experimental results show that the SIFT-based approach using two images yields more competitive results than the existing Harris corner detector-based approach using two images.

Sub-pixels corner detection for camera calibration

Abstract: Two simple and efficient algorithms of sub-pixel corner detection for camera calibration dy using plane pattern were presented.The pixel level corners were detected by classical Harris corner detector,and then some methods were used to get sub-pixel accuracy.In one algorithm,the subpixel location was achieved through a quadratic approximation of the 3×3 neighborhood of the local maxima of the corner response function,and a closed form solution developed to the problem.In the other algorithm,the sub-pixel accurate corner locator was obtained from the observation that any vector from true corner location to its neighborhood is orthogonal to the image gradient.So the sub-pixel location was calculated iteratively by minimizing an error function.The result of the camera calibration shows that high precision can be acquired by using the sub-pixel algorithms and the mean reprojection error is below 0.15 pixels.

Feature-based deformable image registration with RANSAC based search correspondence

Abstract: The paper presents an algorithm for deformable image registration based on point features extracted from input images using the Harris corner detector. The correspondence between the points extracted from the different images is established using RANdom SAmple Consensus (RANSAC) method with the affine and perspective global transformation used to model the deformations. The initial correspondence is established using an enumerative search with rotation invariant cross-correlation measure. Based on the estimated corresponding set of points the further refinement of the displacement field is achieved through application of the multilevel B-spline technique applied to the overlapping image area. The performance of this method is demonstrated using few pairs of remote sensing images. The method is also evaluated against the global polynomial transformation and the registration results are compared with the results achieved using ENVI software.

A proposal method for corner detection with an orthogonal three-direction chain code

Abstract: Only three set of pattern chain elements to detect corners in irregular shapes are introduced. A code based on three orthogonal change directions, when visiting a contour shape, are used. Previous approaches for detecting corners employ eight different symbols and usually compute angles and maximum curvature. The three basic pattern contour chain elements, founded in this paper, represent changes of direction in the contour curves, requiring few computing power to obtain corners. Also, we have found that the method is independent of shape orientation.

A proposal method for corner detection with an orthogonal three-direction chain code

Abstract: Only three set of pattern chain elements to detect corners in irregular shapes are introduced. A code based on three orthogonal change directions, when visiting a contour shape, are used. Previous approaches for detecting corners employ eight different symbols and usually compute angles and maximum curvature. The three basic pattern contour chain elements, founded in this paper, represent changes of direction in the contour curves, requiring few computing power to obtain corners. Also, we have found that the method is independent of shape orientation.

Robust Image Measurement and Analysis Based on Perspective Transformations

Abstract: In the paper, perspective transformation is used to project points from the front horizon of the camera to an image plane and thus to measure the distance between the detected object and the camera. With the information about points on the ground, the projective positions of every tip in a rigid object can be figured out through transformation. Features of the object's projection at different distances, such as size and shape, can also be predicted. Besides, the paper has analyzed difference in the result of the measurement and errors caused by the application of different parameters. The information assists engineers of vision-based detection system in determining the parameters of the system and identifying features of an object's projection to accelerate the detection. Also, the camera parameters compensate automatically when being influenced by outer force to promote the effects of detection and make a robust system.

A Novel Corner Detector Approach using Sliding Rectangles

Abstract: This paper introduces a new corner detection approach for planar curves. The proposed algorithms finds the corners by sliding set of three rectangles along the curve and counting number of contour points lying in each rectangle. This structure incorporates both local and global view of given shape which is a key to find all corners successfully. Proposed technique has been found very consistent with human vision system. This is a novel and an efficient method as it does not involve calculation of cosine angle and curvature. A comparative study with two popular existing corner detectors is also presented.

Neural network corner detection of vertex chain code

Abstract: This paper presents a Neural Network Classifier to be implemented in corner detection of chain code series. The classifier directly uses chain code which is derived using Freeman chain code as training, testing and validation set. The steps of developing Neural Network Classifier are included in this paper. Comparison results between Neural Network Classifier corner detection and other computational corner detection are presented to show the reliability of the proposed classifier. This paper ends with the discussions on the implementation of proposed neural network in corner detection of chain code series. Experimental results have shown that the proposed network has good robustness and detection performance. This makes this method a great choice for machine vision.

Finding corners in images by foveated search

Abstract: We develop a new approach to finding corners in images that combines foveated edge detection and curvature calculation with saccadic placement of foveal fixations. Each saccade moves the fovea to a location of high curvature combined with high edge gradient. Edges are located using a foveated Canny edge detector with spatial constant that increases with eccentricity. Next, we calculate a measure of local corner strength , based on a product of curvature and gradient. An inhibition factor based on previous visits to a region of the image prevents the system from repeatedly returning to the same locale. A long saccade is move thes fovea to previously unexplored areas of the image. Subsequent short saccades improve the accuracy of the location of the corner approximated by the long saccade. The system is tested on two natural scenes and the results compared against subjects observing the same test images through an eyetracker. Results show that the algorithm is a good locator of corners.

Geometrically Invariant Feature Points Detection Based on Scale Space Theory

Abstract: Feature extraction is a vital part of watermarking technology that resists geometrically attacks.The points extracted from the image will directly influence the robustness of the watermak exists in the image.This paper improves Harris-Laplace corner detector by presenting a novel method to extract geometrically invariant feature points based on the scale space theory.According to the experiments,the proposed method can select those feature points that resist several geometrically attacks such as scaling and cropping,but at the cost of lower computation.