Curvature Scale Space Technique Research Articles

A Morphological Classification Method of ECG ST-Segment Based on Curvature Scale Space

Aomalous changes in the ST segment, including ST level deviation and ST shape change, are the major parameters in clinical electrocardiogram (ECG) diagnosis of myocardial ischemia. Automatic detection of ST segment morphology can provide a more accurate evidence for clinical diagnosis of myocardial ischemia. In this paper, we proposed a method for classifying the shape of the ST-segment based on the curvature scale space (CSS) technique. First, we established a reference ST set and preprocessed the ECG signal by using the CSS technique. Then, the corner points in the ST-segment were detected at a high scale of the CSS and tracked through multiple lower scales, in order to improve its localization. Finally, the current beat of ST morphology can be distinguished by the corner points. We applied the developed algorithm to the ECG recordings in European ST-T database and QT database to validate the accuracy of the algorithm. The experimental results showed that the average detection accuracy of our algorithm was 91.60%. We could conclude that the proposed method is able to provide a new way for the automatic detection of myocardial ischemia.

On the Convergence of Planar Curves Under Smoothing

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.

Automatic fitting of digitised contours at multiple scales through the curvature scale space technique

The curvature scale space (CSS) technique has been used in conjunction with Hermite curves for automatic fitting of digitised contours at multiple scales. CSS is a powerful contour shape descriptor which has been selected for MPEG-7 standardisation. Hermite curves were used since each Hermite curve is defined by two endpoints and the tangent vectors at those points. No points external to the input contour are required for Hermite curves. Hermite endpoints are defined as consecutive curvature zero-crossing points extracted at multiple scales using the CSS method. Hermite tangent vectors can also be determined using the CSS technique. Approximation error and compression ratio are computed at each scale. The graph of compression ratio as a function of approximation error is smoothed to remove noise. The bending point of that function is defined as the largest maximum of its second derivative. This point can be considered as the boundary between the mostly vertical and the mostly horizontal segments of the graph. It can be used for automatic selection of an optimal scale. Finally, the original contour reconstruction technique has been extended to improve the quality of fit. This has been achieved by adjusting the lengths of tangent vectors for each spline segment independently.

Robust automatic selection of optimal views in multi-view free-form object recognition

This paper addresses the issue of automatic selection of the best and the optimum number of representative views for each object in a database that can enable the accurate recognition of that object from any single arbitrary view of the object. The object boundary in each view is represented by its curvature scale space (CSS) image. The CSS representation has been selected for MPEG-7 standardisation as a contour shape descriptor. The paper also presents a novel method for fusion of results from combined shape descriptors. The utilisation of this method for multi-view three-dimensional (3-D) object recognition has been explored. The object boundary of each view is represented effectively using the CSS technique, moment invariants and Fourier descriptors. It has been shown that the results obtained from the fusion method are superior to the results obtained from any single technique. The method has been tested on a collection of free-form 3-D objects. Each object has been modelled using an optimal number of silhouette contours obtained from different viewpoints. This number varies depending on the complexity of the object and the measure of expected accuracy. A comprehensive analysis of the performance of the system has been given.

Silhouette-based occluded object recognition through curvature scale space

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.