无端点检测汉语识别算法的实现及改进——动态时间规整和隐马尔可夫统一模型的应用

语音识别算法中，动态时间规整（ＤＴＷ）和隐马尔可夫模型（ＨＭＭ）是最有效的识别算法，并且两者之间有着本质的联系和内在的统一［１］，据此前期工作中，已经建立了ＤＴＷ和ＨＭＭ的统一模型（ＤＨＵＭ）［２、３］。本文对ＤＨＵＭ进行了改进，在ＤＨＵＭ中引进寂静段自环，并根据汉语语音的特点，提出了一种无端点检测的语音识别算法。在识别过程中，该算法无需确定语音信号起止点位置，而是从寂静段开始，直接按帧提取特征（帧长２０ｍｓ，帧间重叠５０％），特征向量由１５阶倒谱系数和帧平均能量组成。实验中，用ＤＨＵＭ实现了该算法，对９９个相似汉语单字的识别测试结果表明：无端点检测的识别正识率为９４．９５％，正识率下降很少，但不作端点检测却降低了算法的复杂程度。为进一步改善识别性能，特征向量采用一种听觉模型特征，识别器具有更好的鲁棒性，识别率会略有提高。     

手写体汉字识别问题综论

本文在讨论了人对汉字的认知心理试验研究结果之后,认为人类的汉字识别是经由整字属性及分层结构的多种途径复合而成的。这些途径中的大多数都可以在手写体汉字的机器识别中模仿运用。由此可把汉字的机器识别方法归纳为整模式法和子模式法两个大类,对它们的有利方面和困难方面进行了讨论;对影响其性能的因素进行了分析;对识别率以及它与识别字集大小和后处理等的关系提出了评估的问题。     

Perceptually Grounded Language Learning: Part 2—DETE: A Neural/Procedural Model

In Part 1 of this two-part series, we introduced Katamic memory—a neural network architecture capable of robust sequence learning and recognition. In Part 2, we introduce the Blobs World taskjdomain for language learning and describe the DETE language learning system, which is composed of over 50 Katamic memory modules. DETE currently learns small subsets of English and Spanish via association with perceptual! motor inputs. In addition to Kaiamic memory, DETE employs several other novel features: (1) use of feature planes, to encode visual shapes, spatial relationships and the motions of objects, (2) phase-locking of neural firing, in order to represent focus of atention and to bind objects across multiple feature planes, and (3) a method for encoding temporal relationships, so that DETE can learn utterances involving the immediate past and future. We compare DETE to related models and discuss the implications of this approach for language-learning research.     

Self-calibration based on invariant view recognition: Dynamic approach to navigation

We extend a dynamic approach of behavior generation to the representation of spatial information. Two levels of dynamics integrate dead-reckoning, dominant far from home bases, and piloting, dominant near home bases. When the view-based piloting system recognizes a home base, visual place information recalibrates the dead-reckoning system, inverting the hierarchical ordering of the two dynamic levels by time scale inversion. Reference views taken at discrete home bases are recognized invariantly under rotation of views. This process yields compass information. Continuous translational information is obtained as a neural place representation built from view correlations with a scattered set of local views. This self-calibrating cognitive map couples into a dynamics of heading direction integrating the behaviors of obstacle avoidance and target acquisition. Targets can be designated in terms of the cognitive map. We demonstrate the dynamical model in simulation.     

Laplace spectra as fingerprints for image recognition

In the area of image retrieval from data bases and for copyright protection of large image collections there is a growing demand for unique but easily computable fingerprints for images. These fingerprints can be used to quickly identify every image within a larger set of possibly similar images. This paper introduces a novel method to automatically obtain such fingerprints from an image. It is based on a reinterpretation of an image as a Riemannian manifold. This representation is feasible for gray value images and color images. We discuss the use of the spectrum of eigenvalues of different variants of the Laplace operator as a fingerprint and show the usability of this approach in several use cases. Contrary to existing works in this area we do not only use the discrete Laplacian, but also with a particular emphasis the underlying continuous operator. This allows better results in comparing the resulting spectra and deeper insights in the problems arising. We show how the well known discrete Laplacian is related to the continuous Laplace-Beltrami operator. Furthermore, we introduce the new concept of solid height functions to overcome some potential limitations of the method.     

Target differentiation with simple infrared sensors using statistical pattern recognition techniques

This study compares the performances of various statistical pattern recognition techniques for the differentiation of commonly encountered features in indoor environments, possibly with different surface properties, using simple infrared (IR) sensors. The intensity measurements obtained from such sensors are highly dependent on the location, geometry, and surface properties of the reflecting feature in a way that cannot be represented by a simple analytical relationship, therefore complicating the differentiation process. We construct feature vectors based on the parameters of angular IR intensity scans from different targets to determine their geometry and/or surface type. Mixture of normals classifier with three components correctly differentiates three types of geometries with different surface properties, resulting in the best performance (100%) in geometry differentiation. Parametric differentiation correctly identifies six different surface types of the same planar geometry, resulting in the best surface differentiation rate (100%). However, this rate is not maintained with the inclusion of more surfaces. The results indicate that the geometrical properties of the targets are more distinctive than their surface properties, and surface recognition is the limiting factor in differentiation. The results demonstrate that simple IR sensors, when coupled with appropriate processing and recognition techniques, can be used to extract substantially more information than such devices are commonly employed for.     

基于模糊匹配的平面连杆机构反求设计研究

对平面连杆机构曲线进行了分析,提出了用一组特征参数来描述连杆曲线,建立了连杆曲线图谱库,并将模糊论应用于连杆机构的曲线匹配,从而获取所求的机构参数.最后给出了应用实例,证实了该方法的可行性与有效性.     

The importance of information localization in scene gist recognition.

People can recognize the meaning or gist of a scene from a single glance, and a few recent studies have begun to examine the sorts of information that contribute to scene gist recognition. The authors of the present study used visual masking coupled with image manipulations (randomizing phase while maintaining the Fourier amplitude spectrum; random image structure evolution [RISE]; J. Sadr & P. Sinha, 2004) to explore whether and when unlocalized Fourier amplitude information contributes to gist perception. In 4 experiments, the authors found that differences between scene categories in the Fourier amplitude spectrum are insufficient for gist recognition or gist masking. Whereas the global 1/f spatial frequency amplitude spectra of scenes plays a role in gist masking, local phase information is necessary for gist recognition and for the strongest gist masking. Moreover, the ability to recognize the gist of a target image was influenced by mask recognizability, suggesting that conceptual masking occurs even at the earliest stages of scene processing. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

碳/环氧复合材料的冲击拉伸

该文研究了T300碳纤维单向增强的环氧复合材料,在应变率从10~(-3)/s到10~3/s范围内的冲击拉伸行为.通过对实验数据进行拟合,得出该范围内材料对应变率具有弱的敏感性,表现在破坏强度及破坏应变随应变率增加不显著变化,平均模量几乎不受应变率的影响.分析了试件的几何尺寸效应,讨论了应力波作用对破坏形态的影响以及实验中观察到的拔出现象.从应变率在10~2～10~3/s附近材料行为某些非确定性,指出在更宽范围内了解其性能的必要性.     

基于自组织神经网络的实时统计特征抽取方法

应用人工神经网络讨论统计了特征抽取的原理，提出了相应的抽取方法。该方法具有实时性，容错性，高数据压缩率和良好的特征分辨率。通过计算机仿真和桥梁索力状态的实例计算分析证实了该技术具有广泛的应用价值。