Clustering by scale-space filtering

In pattern recognition and image processing, the major application areas of cluster analysis, human eyes seem to possess a singular aptitude to group objects and find important structures in an efficient and effective way. Thus, a clustering algorithm simulating a visual system may solve some basic problems in these areas of research. From this point of view, we propose a new approach to data clustering by modeling the blurring effect of lateral retinal interconnections based on scale space theory. In this approach, a data set is considered as an image with each light point located at a datum position. As we blur this image, smaller light blobs merge into larger ones until the whole image becomes one light blob at a low enough level of resolution. By identifying each blob with a cluster, the blurring process generates a family of clustering along the hierarchy. The advantages of the proposed approach are: 1) The derived algorithms are computationally stable and insensitive to initialization and they are totally free from solving difficult global optimization problems. 2) It facilitates the construction of new checks on cluster validity and provides the final clustering a significant degree of robustness to noise in data and change in scale. 3) It is more robust in cases where hyperellipsoidal partitions may not be assumed. 4) it is suitable for the task of preserving the structure and integrity of the outliers in the clustering process. 5) The clustering is highly consistent with that perceived by human eyes. 6) The new approach provides a unified framework for scale-related clustering algorithms derived from many different fields such as estimation theory, recurrent signal processing on self-organization feature maps, information theory and statistical mechanics, and radial basis function neural networks     

Fast and robust copy-move forgery detection based on scale-space representation

Multimedia Tools and Applications - Copy-move forgery (CMF), which copies a part of an image and pastes it into another region, is one of the most common methods for digital image tampering. For...     

Linear scale-space

The formulation of afront-end orearly vision system is addressed, and its connection with scale-space is shown. A front-end vision system is designed to establish a convenient format of some sampled scalar field, which is suited for postprocessing by various dedicated routines. The emphasis is on the motivations and implications of symmetries of the environment; they pose natural, a priori constraints on the design of a front-end.The focus is on static images, defined on a multidimensional spatial domain, for which it is assumed that there are no a priori preferred points, directions, or scales. In addition, the front-end is required to be linear. These requirements are independent of any particular image geometry and express the front-end's pure syntactical, bottom up nature.It is shown that these symmetries suffice to establish the functionality properties of a front-end. For each location in the visual field and each inner scale it comprises a hierarchical family of tensorial apertures, known as the Gaussian family, the lowest order of which is the normalised Gaussian. The family can be truncated at any given order in a consistent way. The resulting set constitutes a basis for alocal jet bundle. Note that scale-space theory shows up here without any call upon the prohibition of spurious detail, which, in some way or another, usually forms the basic starting point for diffusion-like scale-space theories.     

Legendre序列快速生成的CUDA实现

序列设计在信息安全,无线通信等诸多领域中有着重要应用。在流密码系统中,要求产生的随机序列具有理想的随机复杂度度量如线性复杂度,k阶相关复杂度等。其中Legendre序列具有这些理想的随机性质。实用中序列的生成速度也是很重要的考虑因素。探讨了大素数周期的Legendre序列生成的相关算法,并运用统一计算设备架构平台（CUDA）对其进行优化以加快序列的生成速度。实验结果表明,运用CUDA进行序列的并行生成,序列的生成速度有数量级的提高。     

Affine invariant scale-space

A newaffine invariant scale-space for planar curves is presented in this work. The scale-space is obtained from the solution of a novel nonlinear curve evolution equation which admits affine invariant solutions. This flow was proved to be the affine analogue of the well knownEuclidean shortening flow. The evolution also satisfies properties such ascausality, which makes it useful in defining a scale-space. Using an efficient numerical algorithm for curve evolution, this continuous affine flow is implemented, and examples are presented. The affine-invariant progressive smoothing property of the evolution equation is demonstrated as well.     

基于GPU的AES快速实现

为了充分利用图形处理器(GPU)的闲置资源,同时达到提高密码算法加密速度的目的,提出了一种在图形处理器上实现AES加密算法的方法,分别阐述了基于传统OpenGL的AES实现以及基于最新技术CUDA的AES实现,并对这两种方法的实现性能进行了分析,同时与传统CPU方法的实现性能进行了比较,基于CUDA的AES的实现速度达到了传统CPU上AES实现速度的19.6倍.     

变频器设备如何快速实现CANopen通信——基于CANopen协议的XGate-COP10应用

<正>步入20世纪80年代,全球变频器技术变革速度加快,走向成熟的变频产品被广泛应用在国民经济的各个行业中。随着中国变成世界工厂,制造业的快速发展也为变频器产品提供了越来越大的市场空间。然而时至今日,国内变频     

A hitherto unnoticed singularity of scale-space

A hitherto unnoticed singularity of scale space occurs only at isolated points in scale space. Thus it does not generically occur for single images, but it can occur occasionally in members of time sequences (say). It occurs at those critical points of the image at which the Laplacean of the illuminance vanishes (a nongeneric condition). The structure of scale space in an infinitesimal neighborhood of such a singularity is explored. The effect of the singularity of mappings between copies of an image at different levels of resolution is evaluated and checked with a numerical calculation     

B-spline scale-space of spline curves and surfaces

We present iterative algorithms for $B$-spline scale-space smoothing of geometric data and recovery of high frequency information in the smoothing process. The scale-space representation is based on a directional smoothing process using $B$-splines. If the geometric data are approximated or modelled by uniform $B$-splines or box-splines then the scale-space smoothing produces $B$-spline curves or box-spline surfaces. The method is applicable to geometric data processing and geometric modelling of free-form curves and surfaces from quadrilateral polyhedra with extraordinary vertices.     

基于CHMM孤立词识别系统的快速实现

介绍了基于连续隐含马尔可夫模型(CHMM)的非特定人孤立词语音识别系统.根据分析该系统计算复杂度,提出了一系列的优化方法,通过MATLAB平台下的研究实验数据表明,优化后的语音识别系统与传统CHMM语音识别系统对比,计算时间是传统CHMM系统的9.97%,而识别率仅从传统CHMM系统的94%下降到91.3%.     

New symmetric interpolatory quadrature formulas

We introduce two families of symmetric, interpolatory integration formulas on the interval [−1,1]. These formulas, related to the class of recursive monotone stable (RMS) formulas, allow the application of higher order or compound rules with an efficient reuse of computed function values. One family (SM) uses function values computed outside the integration interval, the other one (HR) uses derivative data. These formulas are evaluated using a practical test based on a tecnique for comparing automatic quadrature routine introduced by Lyness and Kaganove and improved by the authors. Work supported by CNR, Grant no. 93.00570, CT01     

On the scale-space theorem of Chen and Yan

Chen and Yan presented (ibid., vol.11, p.694-700, 1989) a theorem concerning zero crossings of boundary curvature under morphological openings. In this correspondence, we show by means of a counterexample a flaw in this theorem and suggest how the theorem may be modified to make it correct     

A spatio-frequency trade-off scale for scale-space filtering

We study implementation issues for spatial convolution filters and their Fourier alternative, with the aim to optimize the accuracy of filter output. We focus on Gaussian scale-space filters and show that there exists a trade-off scale that subdivides the available scale range into two subintervals of equal length. Below this trade-off scale Fourier filtering yields more accurate results than spatial filtering; above it is the other way around. This should be contrasted with demands of computational speed, which show the opposite tenet     

Fast buffering for FPGA implementation of vision-based object recognition systems

Real-time frame rate is an important factor for practical deployment of computer vision systems. Field programmable gate array (FPGA) technology has been considered for many applications due to its parallel computing capability. FPGA implementations of computer vision algorithms normally involve buffering data on external memory devices, which could slow down the whole system. This paper proposes a buffering scheme suitable for implementing real-time vision-based systems on an FPGA that does not require external memory to buffer data. A stop sign detection system implemented on an FPGA employing the proposed buffering scheme is presented as an example system. This system is capable of processing over 200?fps at the frame size of 480?×?752 pixels.