Shape retrieval with eigen-CSS search

This paper presents a new affine-invariant matching algorithm based on B-Spline modeling, which solves the problem of the non-uniqueness of B-Spline in curve matching. This method first smoothes the B-Spline curve by increasing the degree of the curve. It is followed by a reduction of the curve degree using the Least Square Error (LSE) approach to construct the Curvature Scale Space (CSS) image. CSS matching is then carried out. Our method combines the advantages of B-Spline that are continuous curve representation and the robustness of CSS matching with respect to noise and affine transformation. It avoids the need for other matching algorithms that have to use the re-sampled points on the curve. Thus, the curve matching error is reduced. The proposed algorithm has been tested by matching similar shapes from a prototype database. The experimental results showed the robustness and accuracy of the proposed method in B-Spline curve matching.

. We introduce a very fast and reliable method for shape similarity retrieval in large image databases which is robust with respect to noise, scale and orientation changes of the objects. The maxima of curvature zero crossing contours of Curvature Scale Space (CSS) image are used to represent the shapes of object boundary contours. While a complex boundary is represented by about five pairs of integer values, an effective indexing method based on the aspect ratio of the CSS image, eccentricity and circularity is used to narrow down the range of searching. Since the matching algorithm has been designed to use global information, it is sensitive to major occlusion, but some minor occlusion will not cause any problems. We have tested and evaluated our method on a prototype database of 450 images of marine animals with a vast variety of shapes with very good results. The method can either be used in real applications or produce a reliable shape description for more complicated images when ...

In a previous work (de Almeida), we presented an approach for shape-based image retrieval using the curvature scale space (CSS) and self-organizing map (SOM) methods. Here, we examine the robustness of the representation with images under variations of rotation. Moreover, the CSS images extracted from a database are processed and represented by median vectors that constitutes the training data set for a SOM neural network. This way of representation improves the accuracy of image retrieval in comparison with the previous work (de Almeida) that used the first principal component of the PCA technique. A benchmark database is used to demonstrate the usefulness of the proposed methodology.

A complete and practical isolated-object recognition system has been developed which is very robust with respect to scale, position and orientation changes of the objects as well as noise and local deformations of shape due to perspective projection, segmentation errors and non-rigid material used in some objects. The system has been tested on a wide variety of 3-D objects with different shapes and surface properties. A light-box setup is used to obtain silhouette images which are segmented to obtain the physical boundaries of the objects which are classified as either convex or concave. Convex curves are recognized using their four high-scale curvature extrema points. Curvature scale space (CSS) representations are computed for concave curves. The CSS representation is a multi-scale organization of the natural invariant features of a curve. A three-stage coarse-to-fine matching algorithm quickly detects the correct object in each case. >

Registration is a fundamental task in image processing used to match two or more images taken at different times, from different sensors or from different viewpoints. Problems that can occur are change over time, occlusion, image noise and differences in image geometry. The authors concentrate on the automatic registation of shorelines extracted from multisensor imagery. The authors examine the use of curvature scale space (CSS) to represent the shape of shorelines. In CSS, curve evolution is studied by smoothing a shape with a Gaussian kernel and computing the curvature at varying levels of detail. A representation can be constructed that is robust to image noise and is scale invariant, allowing the extraction of control points which characterise a shoreline regardless of its original scale. To map a (sub)set of control points unto another set, the authors use relaxation labeling built on constraints of CSS features and sensor geometry.

The problem of extending the curvature scale-space (CSS) technique to represent open curves is addressed. Various approaches for dealing with the endpoint problem of open curves are considered, and one is selected which allows us to handle the evolution of the open curves as a special case of the evolution of closed curves. The convergence theory of evolved open curves is established, and the CSS shape representation is investigated.

A graph-based approach for multiscale shape analysis

Localization of the dominant points of cervical spines in medical images is important for improving the medical automation in clinical head and neck applications. In order to automatically identify the dominant points of cervical vertebrae in neck CT images with precision, we propose a method based on multi-scale contour analysis to analyzing the deformable shape of spines. To extract the spine contour, we introduce a method to automatically generate the initial contour of the spine shape, and the distance field for level set active contour iterations can also be deduced. In the shape analysis stage, we at first coarsely segment the extracted contour with zero-crossing points of the curvature based on the analysis with curvature scale space, and the spine shape is modeled with the analysis of curvature scale space. Then, each segmented curve is analyzed geometrically based on the turning angle property at different scales, and the local extreme points are extracted and verified as the dominant feature points. The vertices of the shape contour are approximately derived with the analysis at coarse scale, and then adjusted precisely at fine scale. Consequently, the results of experiment show that we approach a success rate of 93.4% and accuracy of 0.37mm by comparing with the manual results.

Scale is a fundamental concept in computer vision and pattern recognition, especially in the fields of shape analysis, image segmentation, and registration. It represents the level of detail of object information in scenes. Global scale methods in image processing process the scene at each of various fixed scales and combine the results, as in scale space approaches. Local scale approaches define the largest homogeneous region at each point, and treat these as fundamental units. A similar dichotomy exists for describing shapes also. To vary the level of detail depending on application, it is desirable to be able to detect dominant points on shape boundaries at different scales. In this paper, we compare global and local scale approaches to shape analysis. For global scale, the Curvature Scale Space (CSS) method is selected, which is a state of the art shape descriptor, and is used in the MPEG-7 standard. The local scale approach is based on the notion of curvature-scale (c-scale), which is a new local scale concept that brings the idea of local morphometric scale (such as ball-, tensor-, and generalized scale) developed for images to the realm of boundaries. All previous methods of extracting dominant points lack this concept of a local scale. In this paper, we present a thorough evaluation of these global and local scale methods. Our analysis indicates that locally adaptive scale has advantages over global scale in shape description, just as it has also been demonstrated in image filtering, segmentation, and registration.

Real-time shape description system based on MPEG-7 descriptors

Curve smoothing has two important applications in computer vision and image processing: 1) the curvature scale-space (CSS) technique for shape analysis, and 2) the Gaussian filter for noise suppression. In this paper, we study how planar curves converge as they are smoothed with increasing scales. First, two types of convergence behavior are clarified. The coined term shrinkage refers to the reduction of arc-length of a smoothed planar curve, which describes the convergence of the curve latitudinally; and another coined term collapse refers to the movement of each point to its limiting position, which describes the convergence of the curve longitudinally. A systematic study on the shrinkage and collapse of three categories of curve models is then presented. The corner models helps to reveal how the local structures of planar curves collapse and what the smoothed curves may converge to. The sawtooth models allows us to gain insights regarding how noise is suppressed from noisy planar curves by the Gaussian filter. Our investigation on the closed curves shows that each curve collapses to a point at its center of mass. However, different curves may yield different limiting shapes at the infinity scale. Finally, based upon the derived results the performance of the CSS technique in corner detection and shape representation is analyzed, and a fast implementation method of the Gaussian filter for noise suppression is proposed.

A complete and practical system for occluded object recognition has been developed which is very robust with respect to noise and local deformations of shape (due to weak perspective distortion, segmentation errors and non-rigid material) as well as scale, position and orientation changes of the objects. The system has been tested on a wide variety of free-form 3D objects. An industrial application is envisaged where a fixed camera and a light-box are utilized to obtain images. Within the constraints of the system, every rigid 3D object can be modeled by a limited number of classes of 2D contours corresponding to the object's resting positions on the light-box. The contours in each class are related to each other by a 2D similarity transformation. The Curvature Scale Space technique [26, 28] is then used to obtain a novel multi-scale segmentation of the image and the model contours. Object indexing [16, 32, 36] is used to narrow down the search space. An efficient local matching algorithm is utilized to select the best matching models.

A method based on curvature scale space to detect human head is proposed. The presented algorithm analyzes the head shape, and then gets the features different from other parts. Under the curvature scale space frame, the curvature of each point on the contour is calculated, combining the special features of head shape to detect the head. Experimental results show that the presented method can detect human head effectively in complex background, and provide a new approach of human head detection especially when the color information of image is limited.

The paper presents a robust corner tracking method for unconstrained motions. The aim is to track corners in video sequences and identify best correspondences under any transformation, perspective distortion and intensity changes. To extract corners from each video frame, the multi-scale enhanced CSS (curvature scale space) corner detector is applied. In the matching stage, a new two-frame correspondence algorithm using multiple matches is employed. Experiments have been carried out on a wide range of real video sequences depicting translation, scaling, rotation and affine transformation, including non-smooth motions with different lighting and different camera motions. All the results were compared to the results of the popular Tommasini feature tracking algorithm (Tommasini, T. et al., IEEE Conf. on Computer Vision and Pattern Recognition, 1998). Experiments and comparison of the results confirm that the proposed corner tracker is more efficient, and more robust for unconstrained and non-smooth motions. These properties make it specially useful for video database retrieval and multimedia applications.

• Premise of the study: Because plant identification demands extensive knowledge and complex terminologies, even professional botanists require significant time in the field for mastery of the subject. As plant leaves are normally regarded as possessing useful characteristics for species identification, leaf recognition through images can be considered an important research issue for plant recognition.• Methods: This study proposes a feature extraction method for leaf contours, which describes the lines between the centroid and each contour point on an image. A length histogram is created to represent the distribution of distances in the leaf contour. Thereafter, a classifier is applied from a statistical model to calculate the matching score of the template and query leaf.• Results: The experimental results show that the top value achieves 92.7% and the first two values can achieve 97.3%. In the scale invariance test, those 45 correlation coefficients fall between the minimal value of 0.98611 and the maximal value of 0.99992. Like the scale invariance test, the rotation invariance test performed 45 comparison sets. The correlation coefficients range between 0.98071 and 0.99988.• Discussion: This study shows that the extracted features from leaf images are invariant to scale and rotation because those features are close to positive correlation in terms of coefficient correlation. Moreover, the experimental results indicated that the proposed method outperforms two other methods, Zernike moments and curvature scale space.