A Cascade Framework for a Real-Time Statistical Plate Recognition System

This paper describes a plate recognition system that can process images rapidly at high accuracy rates. This system is designed to meet the requirements of performance, computational speed, and adaptation for vehicle surveillance applications, such as stolen car detection systems. These requirements are satisfied by adopting a cascade framework, utilizing plate characteristics, and developing fast one-pass algorithms. Our system is composed of three main cascading modules for plate detection, character segmentation, and postprocessing. Each module is further decomposed into several cascading procedures, which are composed of successively more complex rejecters. The first module rapidly rejects a majority of nonplate regions by using low computational gradient features and a one-pass scanning algorithm followed by heavy computational statistical rejecters. The second module rejects a majority of noncharacter regions in a similar manner. A peak-valley analysis algorithm is proposed to rapidly detect all promising candidates of character regions. The third module eliminates the plate characters that do not satisfy the plate specifications. In our experiments, the system can recognize plates over 38 frames per second with a resolution of 640 times 480 pixels on a 3-GHz Intel Pentium 4 personal computer     

A Statistical Framework for Online Arabic Character Recognition

The widely-used PDAs, touch screens, tablet-PCs are alternatives to keyboards with the advantages of being more friendly, easy, and natural. A framework for Arabic online character recognition is developed. The framework integrates the different phases of online Arabic text recognition. The used data poses several challenges such as delayed strokes handling, connectivity problems, variability, and style change of text. We process the delayed strokes at the different phases differently to improve the overall performance. This work includes feature extraction of many features, including several novel statistical features. Experimental results on challenging online Arabic characters show encouraging results.     

一个用语义分类实现的图象检索框架

基于语义分类的图像检索是根据图像的逻辑特征和抽象属性进行检索的技术,文章提出了基于语义的图像检索概念模型,在此基础上给出了一个用语义分类实现的的图像检索框架,重点讨论了图像语义分类、图像特征提取、检索匹配等问题。     

一种基于构图分析的图像压缩策略

自适应的图像压缩方法VQIC一直都是数字图像处理领域研究的热点之一。该文所叙述的方法,就是在JPEG格式的基础之上,通过简单分析被处理图像的构图来策略性地配置图像中重要性不同区域的不同压缩比。     

A Variational Framework for Exemplar-Based Image Inpainting

Non-local methods for image denoising and inpainting have gained considerable attention in recent years. This is in part due to their superior performance in textured images, a known weakness of purely local methods. Local methods on the other hand have demonstrated to be very appropriate for the recovering of geometric structures such as image edges. The synthesis of both types of methods is a trend in current research. Variational analysis in particular is an appropriate tool for a unified treatment of local and non-local methods. In this work we propose a general variational framework for non-local image inpainting, from which important and representative previous inpainting schemes can be derived, in addition to leading to novel ones. We explicitly study some of these, relating them to previous work and showing results on synthetic and real images.     

A Continuous Probabilistic Framework for Image Matching

In this paper we describe a probabilistic image matching scheme in which the image representation is continuous and the similarity measure and distance computation are also defined in the continuous domain. Each image is first represented as a Gaussian mixture distribution and images are compared and matched via a probabilistic measure of similarity between distributions. A common probabilistic and continuous framework is applied to the representation as well as the matching process, ensuring an overall system that is theoretically appealing. Matching results are investigated and the application to an image retrieval system is demonstrated.     

图象中目标的快速搜索算法

随着系统技术的发展,对目标识别跟踪系统的要求正朝着智能化方向发展,即要求系统具有对目标的自动捕获、自动识别和自动跟踪的能力。为此,在利用目标与背景之间的灰度分布特性的基础上,提出了一种在一定的范围内能自动搜索并锁定目标的目标搜索算法。该算法假定搜索过程是在一个较大的区域开始进行的,而目标仅是该区域内一个在灰度上与背景有差别的小区域。由于这个假定是符合实际情况的,因此该搜索算法可以看作是一个简单的主动边界方法,它首先由一个收缩算法逐步缩小搜索区域,再结合图象的梯度信息来搜索目标,最后锁定目标轮廓。该算法在搜索过程中只对少数的控制点进行计算,而且对控制点的初始位置无严格限制,因而可以在含有目标的区域快速完成搜索过程,实验结果表明,该算法对不同大小、不同形状的目标都可以取得很好的搜索结果。     

一个应用模糊方法的智能搜索引擎的构建

旨在建立一种新型的搜索引擎,它利用模糊的方法,动态收集和使用人工的智能,并在用户的搜索过程中不断地自我学习,以一种人类的方式积累经验和知识,从而同时提高搜索引擎的查准率和查全率。     

A Fourier Domain Framework for Variational Image Registration

Vector fields arise in many problems of computer vision, particularly in non-rigid registration. In this paper, we develop coupled partial differential equations (PDEs) to estimate vector fields that define the deformation between objects, and the contour or surface that defines the segmentation of the objects as well. We also explore the utility of inequality constraints applied to variational problems in vision such as estimation of deformation fields in non-rigid registration and tracking. To solve inequality constrained vector field estimation problems, we apply tools from the Kuhn-Tucker theorem in optimization theory. Our technique differs from recently popular joint segmentation and registration algorithms, particularly in its coupled set of PDEs derived from the same set of energy terms for registration and segmentation. We present both the theory and results that demonstrate our approach.

A Model-Selection Framework for Multibody Structure-and-Motion of Image Sequences

Given an image sequence of a scene consisting of multiple rigidly moving objects, multi-body structure-and-motion (MSaM) is the task to segment the image feature tracks into the different rigid objects and compute the multiple-view geometry of each object. We present a framework for multibody structure-and-motion based on model selection. In a recover-and-select procedure, a redundant set of hypothetical scene motions is generated. Each subset of this pool of motion candidates is regarded as a possible explanation of the image feature tracks, and the most likely explanation is selected with model selection. The framework is generic and can be used with any parametric camera model, or with a combination of different models. It can deal with sets of correspondences, which change over time, and it is robust to realistic amounts of outliers. The framework is demonstrated for different camera and scene models. Most of the presented research was carried out while all three authors were at Monash University.     

正电子发射层析成像的鲁棒最小二乘重建

提出的鲁棒最小二乘算法综合考虑了正电子发射层析成像中的各种误差,适用于实际正电子发射层析成像系统．实验结果表明：该算法比传统的最小二乘重建算法具有更加鲁棒的重建特性．     

A Framework for Model-Based Tracking Experiments in Image Sequences

Motris, an integrated system for model-based tracking research, has been designed modularly to study the effects of algorithmic variations on tracking results. Motris attempts to avoid introducing bias into the relative assessment of alternative approaches. Such a bias may be caused by differences of implementation and parameterization if the component approaches are evaluated in separate testing environments. Tracking results are evaluated automatically on a significant test sample in order to quantify the effects of different combinations of alternatives. The Motris system environment thus allows an in-depth comparison between the so-called ‘Edge-Element Association’ approach documented in Haag and Nagel (1999) and the more recent ‘Expectation-Maximization’ approach reported by Pece and Worrall (2002).     

Tabu Search within a Pivot and Complement Framework

The Pivot and Complement heuristic is a procedure that frequently finds feasible solutions for general 0–1 integer programs. We present a refinement of the heuristic based on Tabu Search techniques. Local search strategies for the search phase, as well as the improvement phase of the heuristic are presented.     

Fine-tuning a Tabu Search Algorithm with Statistical Tests

Tabu Search is a metaheuristic that has proven to be very effective for solving various types of combinatorial optimization problems. To achieve the best results with a tabu search algorithm, significant benefits can sometimes be gained by determining preferred values for certain search parameters such as tabu tenures, move selection probabilities, the timing and structure of elite solution recovery for intensification, etc. In this paper, we present and implement some new ideas for fine-tuning a tabu search algorithm using statistical tests. Although the focus of this work is to improve a particular tabu search algorithm developed for solving a telecommunications network design problem, the implications are quite general. The same ideas and procedures can easily be adapted and applied to other tabu search algorithms as well.     

A Substitution-Translation-Restoration Framework for Handling Unknown Words in Statistical Machine Translation

Unknown words are one of the key factors that greatly affect the translation quality.Traditionally, nearly all the related researches focus on obtaining the translation of the unknown words.However, these approaches have two disadvantages.On the one hand, they usually rely on many additional resources such as bilingual web data;on the other hand, they cannot guarantee good reordering and lexical selection of surrounding words.This paper gives a new perspective on handling unknown words in statistical machine translation (SMT).Instead of making great efforts to find the translation of unknown words, we focus on determining the semantic function of the unknown word in the test sentence and keeping the semantic function unchanged in the translation process.In this way, unknown words can help the phrase reordering and lexical selection of their surrounding words even though they still remain untranslated.In order to determine the semantic function of an unknown word, we employ the distributional semantic model and the bidirectional language model.Extensive experiments on both phrase-based and linguistically syntax-based SMT models in Chinese-to-English translation show that our method can substantially improve the translation quality.     

A General Statistical Framework for Frequency-Domain Analysis of EEG Topographic Structure

A wide variety of rhythmic electrophysiological phenomena—including driven, induced, and endogenous activities of cortical neuronal masses—lend themselves naturally to analysis using frequency-domain techniques applied to multichannel recordings that discretely sample the overall spatial pattern of the rhythmic activity. For such cases, a large but so far poorly utilized body of statistical theory supports a third major approach to topographic analysis, complementing the more familiar mapping and source-recovery techniques. These methods, many of which have only recently become computationally feasible, collectively provide general solutions to the problem of detecting and characterizing systematic differences that arise—not only in the spatial distribution of the activity, but also in its frequency-dependent between-channel covariance structure—as a function of multiple experimental conditions presented in conformity with any of the conventional experimental designs. This application-oriented tutorial review provides a comprehensive outline of these resources, including: (1) real multivariate analysis of single-channel spectral measures (and measures of between-channel relationships such as coherence and phase), (2) complex multivariate analysis based on multichannel Fourier transforms, and (3) complex multivariate analysis based on multichannel parametric models. Special emphasis is placed on the potential of the multichannel autoregressive model to support EEG (and MEG) studies of perceptual and cognitive processes.     

Efficient Subwindow Search: A Branch and Bound Framework for Object Localization

Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To estimate the object's location, one can take a sliding window approach, but this strongly increases the computational cost because the classifier or similarity function has to be evaluated over a large set of candidate subwindows. In this paper, we propose a simple yet powerful branch and bound scheme that allows efficient maximization of a large class of quality functions over all possible subimages. It converges to a globally optimal solution typically in linear or even sublinear time, in contrast to the quadratic scaling of exhaustive or sliding window search. We show how our method is applicable to different object detection and image retrieval scenarios. The achieved speedup allows the use of classifiers for localization that formerly were considered too slow for this task, such as SVMs with a spatial pyramid kernel or nearest-neighbor classifiers based on the chi^2 distance. We demonstrate state-of-the-art localization performance of the resulting systems on the UIUC Cars data set, the PASCAL VOC 2006 data set, and in the PASCAL VOC 2007 competition.     

平行图像:图像生成的一个新型理论框架*

为了提高计算机视觉系统的泛化能力,要求利用大规模、多样化、带标注的图像数据集,对视觉模型进行充分的学习与评估.由于从实际场景中获取图像具有局限性,文中提出一种图像生成理论框架,称为平行图像.平行图像的核心单元是软件定义的人工图像系统.从实际场景中获取特定的图像“小数据”,输入人工图像系统,生成大量新的人工图像数据.文中总结平行图像的实现方法,包括图形渲染、图像风格迁移、生成式模型等,并且对比分析人工图像和实际图像的特点,讨论领域适应策略.     

基于统计翻译框架的蒙古文自动拼写校对方法

在以国际标准编码存储的传统蒙古文电子文本中,拼写错误十分普遍。人工校对这些错误不仅速度慢而且成本高。该文提出了一种基于统计翻译框架的传统蒙古文自动拼写校对方法,将拼写校对看作是从错误词到正确词的翻译。该文使用改进的基于短语的统计机器翻译模型来构建拼写校对模型,然后对测试文本进行校对。实验结果表明,该方法可以快速、有效地校对拼写错误,而且不依赖于特定语言的语法知识。使用该方法对包含1 026个正确词、1 102个错误词的测试集进行拼写校对,校对后文本中的正确词所占比例最高可达97.55%。