Abstract: We propose an approach to accurately detecting two-dimensional (2-D) shapes. The cross section of the shape boundary is modeled as a step function. We first derive a one-dimensional (1-D) optimal step edge operator, which minimizes both the noise power and the mean squared error between the input and the filter output. This operator is found to be the derivative of the double exponential (DODE) function, originally derived by Ben-Arie and Rao (1994). We define an operator for shape detection by extending the DODE filter along the shape's boundary contour. The responses are accumulated at the centroid of the operator to estimate the likelihood of the presence of the given shape. This method of detecting a shape is in fact a natural extension of the task of edge detection at the pixel level to the problem of global contour detection. This simple filtering scheme also provides a tool for a systematic analysis of edge-based shape detection. We investigate how the error is propagated by the shape geometry. We have found that, under general assumptions, the operator is locally linear at the peak of the response. We compute the expected shape of the response and derive some of its statistical properties. This enables us to predict both its localization and detection performance and adjust its parameters according to imaging conditions and given performance specifications. Applications to the problem of vehicle detection in aerial images, human facial feature detection, and contour tracking in video are presented.

Abstract: Biometrics systems based on lip shape recognition are of great interest, but have received little attention in the scientific literature. This is perhaps due to the belief that they have little discriminative power. However, a careful study shows that the difference between lip outlines is greater than that between shapes at different lip images of the same person. So, biometric identification by lip outline is possible. In this paper the lip outline is obtained from a color face picture: the color image is transformed to the gray scale using the transformation of Chang et al. (1994) and binarized with the Ridler and Calvar threshold. Considering the lip centroid as the origin of coordinates, each pixel lip envelope is parameterized with polar (ordered from -/spl pi/ to +/spl pi/) and Cartesian coordinates (ordered as heights and widths). To asses identity, a multilabeled multiparameter hidden Markov model is used with the polar coordinates and a multilayer neural network is applied to Cartesian coordinates. With a database of 50 people an average classification hit ratio of 96.9% and equal error ratio (EER) of 0.015 are obtained.

Abstract: Image-processing thresholding algorithms are extended segmentation tools that are suitable for tracking applications. The centroid of the tracked image distribution is a good point of reference for the location of the image. We describe a new thresholding technique that is based on the estimation of the optimum threshold for achieving minimal variance in the centroid of the processed image. Experimental proofs for evaluating the technique's performance are given. The direct extension of these results to Shack-Hartmann wave-front sensors is also shown.

Abstract: Associating documents to relevant categories is critical for effective document retrieval. Here, we compare the well-known k-nearest neighborhood (kNN) algorithm, the centroid-based classifier and the highest average similarity over retrieved documents (HASRD) algorithm, for effective document categorization. We use various measures such as the micro and macro F1 values to evaluate their performance on the Reuters-21578 corpus. The empirical results show that kNN performs the best, followed by our adapted HASRD and the centroid-based classifier for common document categories, while the centroid-based classifier and kNN outperform our adapted HASRD for rare document categories. Additionally, our study clearly indicates that each classifier performs optimally only when a suitable term weighting scheme is used All these significant results lead to many exciting directions for future exploration.

Abstract: Mechanism synthesis, the identification of the parameters of a mechanism, has been extensively studied especially for four-bar linkages using graphical and numerical optimization approaches. Graphical techniques follow a number of predefined steps and rely heavily on the user. Numerical optimization techniques that require the user to provide "good initial guesses" or bounds for the design variables have also been applied. In general, a linkage is synthesized for function generation, motion generation, and path generation. This article studies four-bar mechanism synthesis by combining Differential Evolution, an evolutionary optimization scheme that can search outside the initial defined bounds for the design variables, and a newly developed novel technique called the Geometric Centroid of Precision Points (GCPP) and the distant precision point in defining the initial bounds for the design variables. The developed methodology has been applied to the synthesis of four-bar linkages for path generation with p...

Abstract: An imager chip has been designed, fabricated, and tested having two unique pixel types interleaved on the same array. The dual-pixel design enables optimization for two separate tasks. One type of pixel is an active pixel sensor (APS), which is used to produce a low-noise image. The other type is a custom-designed pixel optimized for computing the centroid of a moving object in the scene. The APS array is 120 columns /spl times/36 rows, with a pixel size of 14.7/spl times/14.7 /spl mu/m. The centroid array has 60 columns and 36 rows, with a larger pixel size of 29.4/spl times/29.4 /spl mu/m. The chip was fabricated using standard scalable rules on a 0.5 /spl mu/m 1P3M CMOS process. APS images were taken at a frame rate of 30 fps-8300 fps and centroid data was taken at a rate of 180-3580 (x,y) coordinates per second. The chip consumed 2.6 mW.

Abstract: We present a quantitative comparison of three categories of velocity estimation algorithms, including centroid techniques (the adaptive centroid technique and the weighted centroid technique), the sliding-window filtering technique, and correlation techniques (autocorrelation and cross correlation). We introduce, among these five algorithms, two new algorithms: weighted centroid and sliding-window filtering. Simulations and in vivo blood flow data are used to assess the velocity estimation accuracies of these algorithms. These comparisons demonstrate that the sliding-window filtering technique is superior to the other techniques in terms of velocity estimation accuracy and robustness to noise.

Abstract: Two novel computational techniques, harmonic cut and regularized centroid transform, are developed for segmentation of cells and their corresponding substructures observed with an epi-fluorescence microscope. Harmonic cut detects small regions that correspond to subcellular structures. These regions also affect the accuracy of the overall segmentation. They are detected, removed, and interpolated to ensure continuity within each region. We show that interpolation within each region (subcellular compartment) is equivalent to solving the Laplace equation on a multi-connected domain with irregular boundaries. The second technique, referred to as the regularized centroid transform, aims to separate touching compartments. This is achieved by adopting a quadratic model for the shape of the object and relaxing it for final segmentation.

Abstract: The integration of photo-detectors onto a standard CMOS integrated circuit is presented. This device provides the optical front end for a real time centroid detection system to be used as part of a larger system for implementing a Shack-Hartmann wavefront sensor. A hardware emulation system containing a Field Programmable Gate Array is used to prototype suitable algorithms prior to IC fabrication. Data is presented on the performance of photodetectors and the ability to extract in real time a centroid coordinate.

Abstract: In the close digital photogrammetric three-dimension coordinates measurement, the circular target is often taken as imaging feature and mounted on the measured object or the probe for 3D coordinates detection. The accuracy with which circular targets are located determines the effectiveness of measurement. Subpixel level accuracy is one of the methods that can improve the accuracy of target location. Many methods which based on subpixel edge or centroid detection have been developed and analyzed for target location, but little research focused on circular optical target location. In this research, a new algorithm named bilinear interpolation centroid algorithm was developed for circular optical target subpixel location. In this technique, the accuracy of the squared gray weighted centroid algorithm can be improved by increasing the available pixels which obtained by bilinear interpolation. The intensity profile of the imaging points and the signal to noise ratio, which affect the subpixel location accuracy, are optimized by automatic exposure control. The experiments have shown that the accuracy of this algorithm is better than the traditional centroid algorithm, and the absolute error of less than 0.0 1 pixels is obtained on the image of a rigid reference bar.

Abstract: A new method for improving centroid accuracy, thereby pointing accuracy, is proposed. Accurate centroid estimation is critical for free-space optical communications where the number of photons from the reference optical sources such as stars or an uplink beacon is limited. It is known that the centroid accuracy is proportional to the SNR. Presence of various noise sources during the exposure of CCD can lead to significant degradation of the centroid estimation. The noise sources include CCD read noise, background light, stray light, and CCD processing electronics. One of the most widely used methods to reduce the effects of the noise and background bias is the thresholding method, which subtracts a fixed threshold from the centroid window before centroid computation. The approach presented here, instead, utilizes the spot model to derive the signal boundary that is used to truncate the noise outside the signal boundary. This process effectively reduces both the bias and the noise. The effectiveness of the proposed method is demonstrated through simulations.

Abstract: PROBLEM TO BE SOLVED: To provide a face direction detector which detects the direction of the face based on a picked-up image of an imaging means. SOLUTION: In a looking-aside monitor and alarm device applying the face direction detector, a centroid position G of an eye EO, a height H of the eye EO, and a width W of the eye EO of a full-faced face in an image picked up by the imaging means are defined as a reference centroid position G, a reference height H, and a reference width W respectively. and a vertical direction decision means compares a centroid position Gi and a height Hi of the eye in an image of the eye detected by an eye information detection means, with the reference centroid position G and the reference height H respectively to determine the vertical direction of the face, and a lateral direction decision means compares the centroid position Gi and a width Wi of the eye in the image of the eye detected by the eye information detection means, with the reference centroid position G and the reference width W respectively to determine the lateral direction of the face. COPYRIGHT: (C)2004,JPO

Abstract: Given three points O, G, I , we give a simple construction by paperfolding for a triangle having these points as circumcenter, centroid, and incenter. If two further points H and N are defined by OH = 3OG = 2ON, we prove that this procedure is successful if and only if I lies inside the circle on GH as diameter and differs from N . This locus for I is also independently derived from a famous paper of Euler, by complementing his calculations and properly discussing the reality of the roots of an algebraic equation of degree 3.

Abstract: The centroid shifts of the 5d level of Ce 3+ in BaF 2 , LaAlO 3 and LaCl 3 have been calculated using the ionic cluster approach. By applying configuration interaction as extension of the basic HF-LCAO approach the dynamical polarization contribution to the centroid shift was calculated. This was found to be only successful if basis sets are used optimized for polarization of the anions.

Abstract: Data clustering has become an important task for discovering significant patterns and characteristics in large spatial databases. The Mufti- Centroid, Multi-Run Sampling Scheme (MCMRS) has been shown to be effective in improving the k-medoids-based clustering algorit hms in our previous work. In this paper, a more advanced sampling scheme termed Incremental MultiCentrozd, Multi-Run Sampling Scheme (IMCMRS) is proposed for k-medoidsbased clustering algorithms. Experimental results demonstrate the proposed scheme can not only reduce by more than 80’ZOcomputation time but also reduce the average distance per object compared with CLARA and CLARANS. IMCMRS is also superior to MCMRS.

Abstract: A simple and robust method for determining the orientation angle of a scanned image or the angular orientation of an object in an electronic image based on using descriptors of the image and systems that implement the method are disclosed. A system including means for acquiring the electronic image, means for determining image centroid coordinates, means for obtaining second order moments corresponding to the image, and, means for determining an orientation angle of a principal axis of the image implements the method.

Abstract: An absorbent article including one or more graphics disposed thereon and a method and system for making the same are provided according to the present invention. A picture is taken of the graphic. Based on the picture, a centroid position of the graphic is determined. The centroid position is compared with a target position. Based on the variation of the centroid position with the target position, the processing is adjusted so as to apply the graphic as desired.

Abstract: In general the center of mass technique is a fast and robust way to approximate the location of a focal spot. This paper discusses in detail the relationship between the focal spot location and the center of mass. We start with a mathematical analysis and conclude with a few practical ideas to improve the accuracy of the center of mass technique.

Abstract: We present a novel method to learn arbitrary cluster boundaries by extending the k-means algorithm to use Mercer kernels. We inter- pret each cluster centroid as a linear com- bination of the cluster points in the higher dimensional space and use this formulation to kernel enable the k-means algorithm. The advantage of this formulation is that we work in the higher dimensional kernel space where it is easier to nd smooth surfaces which separate points belonging to di clus- ters. We also extend our formulation to the non separable case by penalizing the violat- ing points quadratically. We show that the clusters obtained vary as a function of the width parameter of the Gaussian kernel.

Abstract: It follows from our results that as n → ∞ the average distance between the root and the (nearer) centroid node of a recursive tree Tn tends to 1; and the average value of the label of the (nearer) centroid node tends to 5/2.

Abstract: A new center position detecting algorithm of the spot image for the Shack-Hartmann wavefront sensor was developed. The new algorithm is a modified center of weight algorithm, which uses some power of the grey level intensity of the spot images instead of the grey level intensity itself of the spot images. From experiments, the repeatability and accuracy of the center position detection of the spot images of the Shack-Hartmann wavefront sensor which used the new algorithm were improved compared with the conventional center position detection algorithm using the center of weight. Applications of the algorithm to measurement of the displacement of the spot images and the Shack-Hartmann wavefront sensor for measuring wavefront distortion and the experimental results of closed-loop wavefront correction are described in this paper.© (2002) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Abstract: A model-based algorithm for long bone segmentation from digital X-Ray images is introduced. The model is based on statistical variations of anatomical data collected after examining diverse bone shapes. This method extends the centroid to boundary distance shape analysis approach. A bone is modeled by two centroid points, one for each of the two epiphysis, and a range of weighted values for the distances between the centroid and the boundary points. To locate the bone in an image, a strong edge belonging to the boundary of the shape should be present within the calculated ranges after edge detection has been performed. The algorithm is scale and rotation invariant. Preliminary results show that the method can identify complete or partial bones, which makes it applicable to detecting common bone fractures.

Abstract: The central problem of image based centroid tracking is that of target segmentation, that is, determining which pixels belong to the target and which belong to the background. Once the target pixels are identified, the centroid (the center of gravity) of these pixels can be used as the estimated target position. The underlying assumption made in centroid tracking is that the target image contains intensity values that are unlikely to occur in the background. Based on this assumption, the centroid tracker uses three concentric gates to determine which pixels are target pixels. The areas bounded by these gates form three disjoint regions; the inner region, the track region, and the outer region. An inner histogram is collected over inner region that should contain mostly target pixels. An outer histogram is collected over the outer region that should contain only background pixels. These histograms are then used to generate a probability map that indicates the probability that a pixel with a given intensity is part of the target. This probability map is then used to segment the target and find its centroid. This paper describes the methods used to generate the probability map and its use in the centroid tracking algorithm. The performance of this algorithm is compared to that of the previously used dual-threshold segmentation algorithm.

Abstract: We present a partitioning method able to manage Web log sessions. Sessions are assimilable to transactions, i.e., tuples of variable size of categorical data. We adapt the standard definition of mathematical distance used in the K-Means algorithm to represent transactions dissimilarity, and redefine the notion of cluster centroid. The cluster centroid is used as the representative of the common properties of cluster elements. We show that using our concept of cluster centroid together with Jaccard distance we obtain results that are comparable with standard approaches, but substantially improve their efficiency.

Abstract: A boundary sequence is a good representation of arbitrary shaped regions, but not directly used in computing shape features such as area, centroid, orientation, and so forth. In this paper we show that the shape features can be easily computed by using cross-sections derived from a boundary sequence. The cross-sections are vertical line segments in the region and can be determined by tracing the boundary sequence once. Furthermore, a boundary sequence extraction method is also proposed, which generates a boundary sequence for each region in a binary image by scanning the image only once. The proposed method works well even if a region has holes.

Abstract: Two distinct reaction path methods are combined with the imaginary time centroid formalism to yield an approximate means of computing effective quantum rates without a preconceived notion of a reaction coordinate or transition state. The first method, which combines the imaginary time centroid formalism with the determination of minimum energy pathways, is appropriate for use when energetic factors dominate the rate process. The second utilizes an approximate determination of an effective centroid potential and the transition path sampling method of Chandler and co-workers, an approach designed for reactions that occur on more complex landscapes. The two methods are applied to the isomerization of a seven-atom argon cluster at 5 K where quantum effects are relevant.

Abstract: This paper develops a new algorithm for high range resolution (HRR) radar centroid processing for scenarios where there are closely spaced objects. For range distributed targets with multiple discrete scatterers, HRR radars will receive detections across multiple range bins. When the resolution is very high, and the target has significant extent, then it is likely that the detections will not occur in adjacent bins. For target tracking purposes, the multiple detections must be grouped and fused to create a single object report and a range centroid estimate is computed since the detections are range distributed. With discrete scatterer separated by multiple range bins, then when closely spaced objects are present there is uncertainty about which detections should be grouped together for fusion. This paper applies the EM algorithm to form a recursive measurement fusion algorithm that segments the data into object clusters while simultaneously forming a range centroid estimate with refined bearing and elevation estimates.