An unsupervised approach to generating generic summaries of documents

We present an optimization-based unsupervised approach to automatic document summarization. In the proposed approach, text summarization is modeled as a Boolean programming problem. This model generally attempts to optimize three properties, namely, (1) relevance: summary should contain informative textual units that are relevant to the user; (2) redundancy: summaries should not contain multiple textual units that convey the same information; and (3) length: summary is bounded in length. The approach proposed in this paper is applicable to both tasks: single- and multi-document summarization. In both tasks, documents are split into sentences in preprocessing. We select some salient sentences from document(s) to generate a summary. Finally, the summary is generated by threading all the selected sentences in the order that they appear in the original document(s). We implemented our model on multi-document summarization task. When comparing our methods to several existing summarization methods on an open DUC2005 and DUC2007 data sets, we found that our method improves the summarization results significantly. This is because, first, when extracting summary sentences, this method not only focuses on the relevance scores of sentences to the whole sentence collection, but also the topic representative of sentences. Second, when generating a summary, this method also deals with the problem of repetition of information. The methods were evaluated using ROUGE-1, ROUGE-2 and ROUGE-SU4 metrics. In this paper, we also demonstrate that the summarization result depends on the similarity measure. Results of the experiment showed that combination of symmetric and asymmetric similarity measures yields better result than their use separately.     

The role of occlusion in the perception of depth, lightness, and opacity.

A theory is presented that explains how the visual system infers the lightness, opacity, and depth of surfaces from stereoscopic images. It is shown that the polarity and magnitude of image contrast play distinct roles in surface perception, which can be captured by 2 principles of perceptual inference. First, a contrast depth asymmetry principle articulates how the visual system computes the ordinal depth and lightness relationships from the polarity of local, binocularly matched image contrast. Second, a global transmittance anchoring principle expresses how variations in contrast magnitudes are used to infer the presence of transparent surfaces. It is argued that these principles provide a unified explanation of how the visual system computes the 3-D surface structure of opaque and transparent surfaces. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

When danger lurks in the background: Attentional capture by animal fear-relevant distractors is specific and selectively enhanced by animal fear.

Across 2 experiments, a new experimental procedure was used to investigate attentional capture by animal fear-relevant stimuli. In Experiment 1 (N = 34), unselected participants were slower to detect a neutral target animal in the presence of a spider than a cockroach distractor and in the presence of a snake than a large lizard distractor. This result confirms that phylogenetically fear-relevant animals capture attention specifically and to a larger extent than do non-fear-relevant animals. In Experiment 2 (N = 86), detection of a neutral target animal was slowed more in the presence of a feared fear-relevant distractor (e.g., a snake for snake-fearful participants) than in presence of a not-feared fear-relevant distractor (e.g., a spider for snake-fearful participants). These results indicate preferential attentional capture that is specific to phylogenetically fear-relevant stimuli and is selectively enhanced in individuals who fear these animals. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

混合高斯模型结合五帧差分的运动目标检测

在复杂背景下,光照变化、目标短暂遮挡以及背景运动等因素会导致运动目标检测精度较低.提出一种结合改进混合高斯模型和改进五帧差分的运动目标检测算法,首先在混合高斯模型中加入自适应学习率以及背景学习速率更新策略有效解决传统背景更新速率恒定而出现的残影现象;然后利用改进的五帧差分法克服运动目标短暂遮挡问题,并加入光照阈值判别因素,有效减弱光照变化带来的影响;最后对两者结果进行或运算进而得到最终检测结果.实验结果表明,该融合算法在复杂环境下具有一定的抗干扰能力,运动目标检测精度较高.     

改进的遮挡条件下瞳孔检测方法

受到眼睑、睫毛、反光等干扰,提取的瞳孔往往无法近似成标准的椭圆,给瞳孔精确检测带来了难度。针对遮挡问题,提出了一种改进的遮挡瞳孔精确检测方法,该方法首先获取瞳孔图像的感兴趣区域,在对该区域进行阈值分割的基础上,通过滤波去噪和扫描线法去除光源反光的影响;根据沿遮挡瞳孔的分界线进行水平旋转,应用内接平行四边形法确定瞳孔的中心;根据圆形检测理论,提出一种中心修正算法,将求得的两个圆的交点作为眼睑与瞳孔的交点,计算出旋转角度,从而精化瞳孔中心的定位;最后利用五点法计算得到的瞳孔椭圆参数作为初始值,通过最小化拟合椭圆与边缘点之间的欧氏距离,使得该椭圆在非线性最小二乘意义下是最优的。实验结果表明,该方法具有良好的鲁棒性和准确性,在遮挡不超过瞳孔面积一半的情况下,能得到较为精确的瞳孔位置和边界。     

带有局部控制因子的图割光流估计

提出一种带有局部空间项控制因子的图割光流估计算法,能判断和处理光流场的平移遮挡现象。文中分析了平移遮挡的形成机理,构造了遮挡判别公式,基于本次的正向和反向光流场,依靠遮挡判别结果调节局部空间项控制因子,建立下次的能量泛函,加强背景区域对遮挡区域的平滑作用,隔绝运动区域对遮挡区域的平滑作用,从而构造出新结构的网络流图。另外,该算法被证明可以阻断遮挡误判在各次图割优化过程间的传递,从而使逐次α-扩散移动图割光流算法具有自适应处理遮挡的能力。通过与Ground-truth光流场的实验对比,表明该算法能较好地判断与处理遮挡导致的光流场无效区域。     

整形美容外科用新材料—─瘢痕软化用硅胶纱布膜

本文研究了硅胶纱布膜的制备方法和治疗效果。在增生性瘢痕的治疗中，硅凝胶能较快地软化和减轻瘢痕，其治疗时间要比加压疗法短。目前，对硅凝胶的作用机理尚未完全明了，但一般认为水化和封闭是治疗作用的主要基础     

折半查找算法在电子会议系统调试中的应用

关联性故障代表单元的查找定位是电子会议系统调试的关键环节。为了提高查找定位效率,提出了一种基于折半查找的快速定位算法。通过对电子会议系统中干线上的代表单元可靠度的分析,把代表单元的故障情况转化成随着代表单元数量动态变化的量化数据,构成一组有序的可靠度数据,将工程调试问题转化成数据分析问题,引入折半查找算法,设计高效准确定位故障代表单元的算法,并进行了算法效率分析。该方法操作简单,无需借助特殊工具即可应用于复杂环境下电子会议系统的现场调试。     

增强现实中基于自然特征的实时跟踪方法

在增强现实系统的复杂场景中,对目标的实时跟踪受到场景中诸多因素的制约,导致实时跟踪方法效率低且不准确,为此提出一种基于自然特征的实时跟踪方法。设计了一种螺旋分割模型,对捕获的图像进行螺旋分割,利用SURF算法在分割子块中提取特征点,并进行匹配。在对目标进行跟踪定位时,利用前一帧来预测当前帧目标出现的位置,以减少SURF算法的扫描区域,加速系统运算效率。实验中分别对场景光线强弱、视点和仿射变化以及目标被部分遮挡等不同情况进行测试,该方法均表现出较高的跟踪效率。     

基于LASVM-NC和TF.RF的文本分类方法

非凸在线支持向量机（LASVM-NC）具有抗噪能力强和训练速度快的优点,而词频相关频率积（tf.rf）则是一种自适应能力很强、分类性能非常好的文本特征。通过把非凸在线支持向量机和词频相关频率积相结合,提出了一种新的文本分类方法,即LASVM-NC＋tf.rf。实验结果表明,这种方法在LASVM-NC与多种其他特征的结合中性能是最好的,且与SVM＋tf.rf相比,不仅所产生的分类器具有泛化能力更强、模型表达更稀疏的优点,而且在处理含噪声的数据时具有更好的鲁棒性,在处理大规模数据时具有快得多的训练速度。