一种基于数据竞争的高分辨率图像的聚类分割算法

近些年,机器人技术得到了迅猛的发展,应用越来越广泛.随着机器人技术的推广和普及,对机器人使用的要求也越来越高,其中对智能机器人的要求尤显迫切.机器视觉是智能机器人研究领域的一个重要研究方向.在机器人视觉系统中,核心问题是目标提取,对目标实时、准确、快速提取的关键技术是图像分割.由于机器人感知的环境的复杂性及目标的多样性,往往导致机器人感知获得的图像数据量较大且图像本身存在不可预知的复杂性,这就对准确的目标分割和提取处理提出了挑战性问题.本文针对高分辨率图像数据集的分割处理,提出一种新的聚类算法,即根据数据点能量和的大小识别类代表点和类成员点,通过数据点间的竞争识别出最有能力成为簇成员的数据点,并将其与mean shift聚类算法有效地结合应用于彩色图像分割问题中,能够快速高效地实现高分辨率图像的目标分割,并得到较好的图像分割效果.实验结果表明,本文算法在分割效果和分割效率上明显优于传统聚类算法.     

基于样本块的破损唐卡图像修复算法的改进

基于样本块的修复算法由于能同时有效地修复图像的受损纹理和结构的优点被引入到唐卡图像的数字化保护中,而且它对特定破损唐卡图像修复效果良好,但是由于优先权计算和最佳样本块不唯一等问题的影响,算法对其他类唐卡图像修复效果不佳。针对此算法的不足,对信任度计算方法和等照线计算方法进行了改进,解决了最佳样本块不唯一的问题。实验结果证明,改进后的算法不仅能够得到令人满意的修复结果而且能够提高修复效率。     

Category Representation for Classification and Feature Inference.

This research's purpose was to contrast the representations resulting from learning of the same categories by either classifying instances or inferring instance features. Prior inference learning research, particularly T. Yamauchi and A. B. Markman (1998), has suggested that feature inference learning fosters prototype representation, whereas classification learning encourages exemplar representation. Experiment 1 supported this hypothesis. Averaged and individual participant data from transfer after inference training were better fit by a prototype than by an exemplar model. However, Experiment 2, with contrasting inference learning conditions, indicated that the prototype model was mimicking a set of label-based bidirectional rules, as determined by the inference learning task demands in Experiment 1. Only the set of rules model accounted for all the inference learning conditions in these experiments. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

信息的外部表征方式对贝叶斯推理成绩的影响

基于分布式认知观点,考察信息的外部表征方式对人们解决贝叶斯推理问题的影响。实验采用2(样例数:50、100)×2(呈现方式:频率信息集中呈现、样例信息逐个呈现)组间设计,并设置了概率信息呈现对照组。被试为159名大学生,均解决3个贝叶斯推理问题。结果表明,频率信息集中呈现组成绩最好,样例信息逐个呈现组成绩次之,概率信息呈现组成绩最差;样例数效应不显著;在样例信息逐个呈现条件下出现了明显的练习效应。     

Face recognition under arbitrary illumination using illuminated exemplars

Recently, the importance of face recognition has been increasingly emphasized since popular CCD cameras are distributed to various applications. However, facial images are dramatically changed by lighting variations, so that facial appearance changes caused serious performance degradation in face recognition. Many researchers have tried to overcome these illumination problems using diverse approaches, which have required a multiple registered images per person or the prior knowledge of lighting conditions. In this paper, we propose a new method for face recognition under arbitrary lighting conditions, given only a single registered image and training data under unknown illuminations. Our proposed method is based on the illuminated exemplars which are synthesized from photometric stereo images of training data. The linear combination of illuminated exemplars can represent the new face and the weighted coefficients of those illuminated exemplars are used as identity signature. We make experiments for verifying our approach and compare it with two traditional approaches. As a result, higher recognition rates are reported in these experiments using the illumination subset of Max-Planck Institute face database and Korean face database.     

Exemplar and prototype models revisited: Response strategies, selective attention, and stimulus generalization.

J. D. Smith and colleagues (J. P. Minda & J. D. Smith, 2001; J. D. Smith & J. P. Minda, 1998, 2000; J. D. Smith, M. J. Murray, & J. P. Minda, 1997) presented evidence that they claimed challenged the predictions of exemplar models and that supported prototype models. In the authors' view, this evidence confounded the issue of the nature of the category representation with the type of response rule (probabilistic vs deterministic) that was used. Also, their designs did not test whether the prototype models correctly predicted generalization performance. The present work demonstrates that an exemplar model that includes a response-scaling mechanism provides a natural account of all of Smith et al's experimental results. Furthermore, the exemplar model predicts classification performance better than the prototype models when novel transfer stimuli are included in the experimental designs. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

神经网络识别非平衡样本模式的网络优化方法

本文基于多目标优化的思想，分析了用神经网络实现非平衡样本模式识别与分类时，网络优化过程中基本ＢＰ算法收敛速度低的原因，给出了两种相应的改进算法，并利用这两种算法研究了两例非平衡样本模式的分类问题，研究结果表明：改进的算法有效地提高了网络优化收敛速度。     

The mapping model: A cognitive theory of quantitative estimation.

How do people make quantitative estimations, such as estimating a car's selling price? Traditionally, linear-regression-type models have been used to answer this question. These models assume that people weight and integrate all information available to estimate a criterion. The authors propose an alternative cognitive theory for quantitative estimation. The mapping model, inspired by the work of N. R. Brown and R. S. Siegler (1993) on metrics and mappings, offers a heuristic approach to decision making. The authors test this model against established alternative models of estimation, namely, linear regression, an exemplar model, and a simple estimation heuristic. With 4 experimental studies the authors compare the models under different environmental conditions. The mapping model proves to be a valid model to predict people's estimates. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

浅谈控制计划在生产实践中的应用

介绍了ISO／TS16949—2002标准中一项重要的质量控制工具，即制定控制计划的目的、方法、制定的依据以及控制计划的应用和管理。     

采用顺序修复的样本例图像修复算法

本文提出了一种采用顺序修复的样本例图像修复算法,该方法在原Criminisi经典图像修复算法的基础上对修复顺序进行新的尝试.原Criminisi经典算法的修复顺序通过计算优先级得出,随着修复的深入优先级逐渐趋近于0,导致算法失去作用.为解决该问题,本文采用顺序修复的方法来代替优先级决定顺序,避免出现算法失去作用的情况;同时本文提出的“倒L”型样本模板来增强结构的传播能力、提高匹配的正确率.实验结果证明,本文的修复算法相对Criminisi算法具有优势并取得很好的修复结果.