%0 Conference Paper %B 2011 18th IEEE International Conference on Image Processing (ICIP) %D 2011 %T Component-based restoration of speckled images %A Patel, Vishal M. %A Easley,G. R %A Chellapa, Rama %K coherent imaging modalities %K component optimization formulation %K component-based restoration %K Dictionaries %K image restoration %K iterative algorithm %K iterative methods %K multiplicative noise %K NOISE %K optimisation %K radar imaging %K SAR images %K Speckle %K speckle reduction algorithm %K speckled images %K structure components %K surrogate functionals %K synthetic aperture radar %K texture components %K transforms %K TV %X Many coherent imaging modalities are often characterized by a multiplicative noise, known as speckle which often makes the interpretation of data difficult. In this paper, we present a speckle reduction algorithm based on separating the structure and texture components of SAR images. An iterative algorithm based on surrogate functionals is presented that solves the component optimization formulation. Experiments indicate this proposed method performs favorably compared to state-of-the-art speckle reduction methods. %B 2011 18th IEEE International Conference on Image Processing (ICIP) %I IEEE %P 2797 - 2800 %8 2011/09/11/14 %@ 978-1-4577-1304-0 %G eng %R 10.1109/ICIP.2011.6116252 %0 Conference Paper %B 2011 18th IEEE International Conference on Image Processing (ICIP) %D 2011 %T Illumination robust dictionary-based face recognition %A Patel, Vishal M. %A Tao Wu %A Biswas,S. %A Phillips,P.J. %A Chellapa, Rama %K albedo %K approximation theory %K classification %K competitive face recognition algorithms %K Databases %K Dictionaries %K Face %K face recognition %K face recognition method %K filtering theory %K human face recognition %K illumination robust dictionary-based face recognition %K illumination variation %K image representation %K learned dictionary %K learning (artificial intelligence) %K lighting %K lighting conditions %K multiple images %K nonstationary stochastic filter %K publicly available databases %K relighting %K relighting approach %K representation error %K residual vectors %K Robustness %K simultaneous sparse approximations %K simultaneous sparse signal representation %K sparseness constraint %K Training %K varying illumination %K vectors %X In this paper, we present a face recognition method based on simultaneous sparse approximations under varying illumination. Our method consists of two main stages. In the first stage, a dictionary is learned for each face class based on given training examples which minimizes the representation error with a sparseness constraint. In the second stage, a test image is projected onto the span of the atoms in each learned dictionary. The resulting residual vectors are then used for classification. Furthermore, to handle changes in lighting conditions, we use a relighting approach based on a non-stationary stochastic filter to generate multiple images of the same person with different lighting. As a result, our algorithm has the ability to recognize human faces with good accuracy even when only a single or a very few images are provided for training. The effectiveness of the proposed method is demonstrated on publicly available databases and it is shown that this method is efficient and can perform significantly better than many competitive face recognition algorithms. %B 2011 18th IEEE International Conference on Image Processing (ICIP) %I IEEE %P 777 - 780 %8 2011/09/11/14 %@ 978-1-4577-1304-0 %G eng %R 10.1109/ICIP.2011.6116670 %0 Conference Paper %B Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on %D 2011 %T Learning a discriminative dictionary for sparse coding via label consistent K-SVD %A Zhuolin Jiang %A Zhe Lin %A Davis, Larry S. %K classification error %K Dictionaries %K dictionary learning process %K discriminative sparse code error %K face recognition %K image classification %K Image coding %K K-SVD %K label consistent %K learning (artificial intelligence) %K object category recognition %K Object recognition %K optimal linear classifier %K reconstruction error %K singular value decomposition %K Training data %X A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding is presented. In addition to using class labels of training data, we also associate label information with each dictionary item (columns of the dictionary matrix) to enforce discriminability in sparse codes during the dictionary learning process. More specifically, we introduce a new label consistent constraint called `discriminative sparse-code error' and combine it with the reconstruction error and the classification error to form a unified objective function. The optimal solution is efficiently obtained using the K-SVD algorithm. Our algorithm learns a single over-complete dictionary and an optimal linear classifier jointly. It yields dictionaries so that feature points with the same class labels have similar sparse codes. Experimental results demonstrate that our algorithm outperforms many recently proposed sparse coding techniques for face and object category recognition under the same learning conditions. %B Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on %P 1697 - 1704 %8 2011/06// %G eng %R 10.1109/CVPR.2011.5995354 %0 Conference Paper %B 2011 IEEE International Conference on Computer Vision (ICCV) %D 2011 %T Sparse dictionary-based representation and recognition of action attributes %A Qiang Qiu %A Zhuolin Jiang %A Chellapa, Rama %K action attributes %K appearance information %K class distribution %K Dictionaries %K dictionary learning process %K Encoding %K Entropy %K Gaussian process model %K Gaussian processes %K Histograms %K HUMANS %K Image coding %K image representation %K information maximization %K learning (artificial intelligence) %K modeled action categories %K Mutual information %K Object recognition %K probabilistic logic %K sparse coding property %K sparse dictionary-based recognition %K sparse dictionary-based representation %K sparse feature space %K unmodeled action categories %X We present an approach for dictionary learning of action attributes via information maximization. We unify the class distribution and appearance information into an objective function for learning a sparse dictionary of action attributes. The objective function maximizes the mutual information between what has been learned and what remains to be learned in terms of appearance information and class distribution for each dictionary item. We propose a Gaussian Process (GP) model for sparse representation to optimize the dictionary objective function. The sparse coding property allows a kernel with a compact support in GP to realize a very efficient dictionary learning process. Hence we can describe an action video by a set of compact and discriminative action attributes. More importantly, we can recognize modeled action categories in a sparse feature space, which can be generalized to unseen and unmodeled action categories. Experimental results demonstrate the effectiveness of our approach in action recognition applications. %B 2011 IEEE International Conference on Computer Vision (ICCV) %I IEEE %P 707 - 714 %8 2011/11/06/13 %@ 978-1-4577-1101-5 %G eng %R 10.1109/ICCV.2011.6126307 %0 Conference Paper %B 2011 International Joint Conference on Biometrics (IJCB) %D 2011 %T Synthesis-based recognition of low resolution faces %A Shekhar, S. %A Patel, Vishal M. %A Chellapa, Rama %K Dictionaries %K Face %K face images %K face recognition %K face recognition literature %K face recognition systems %K illumination variations %K image resolution %K low resolution faces %K Organizations %K PROBES %K support vector machines %K synthesis based recognition %X Recognition of low resolution face images is a challenging problem in many practical face recognition systems. Methods have been proposed in the face recognition literature for the problem when the probe is of low resolution, and a high resolution gallery is available for recognition. These methods modify the probe image such that the resultant image provides better discrimination. We formulate the problem differently by leveraging the information available in the high resolution gallery image and propose a generative approach for classifying the probe image. An important feature of our algorithm is that it can handle resolution changes along with illumination variations. The effective- ness of the proposed method is demonstrated using standard datasets and a challenging outdoor face dataset. It is shown that our method is efficient and can perform significantly better than many competitive low resolution face recognition algorithms. %B 2011 International Joint Conference on Biometrics (IJCB) %I IEEE %P 1 - 6 %8 2011/10/11/13 %@ 978-1-4577-1358-3 %G eng %R 10.1109/IJCB.2011.6117545 %0 Journal Article %J IEEE Security & Privacy %D 2003 %T The dangers of mitigating security design flaws: a wireless case study %A Petroni,N. L. %A Arbaugh, William A. %K Communication system security %K computer security %K cryptography %K design flaw mitigation %K Dictionaries %K legacy equipment %K privacy %K Protection %K Protocols %K security design flaws %K security of data %K synchronous active attack %K telecommunication security %K Telecommunication traffic %K wired equivalent privacy protocol %K Wireless LAN %K wireless local area networks %K Wireless networks %X Mitigating design flaws often provides the only means to protect legacy equipment, particularly in wireless local area networks. A synchronous active attack against the wired equivalent privacy protocol demonstrates how mitigating one flaw or attack can facilitate another. %B IEEE Security & Privacy %V 1 %P 28 - 36 %8 2003/02//Jan %@ 1540-7993 %G eng %N 1 %R 10.1109/MSECP.2003.1176993 %0 Conference Paper %B Proceedings of the 36th Annual Hawaii International Conference on System Sciences, 2003 %D 2003 %T The effect of bilingual term list size on dictionary-based cross-language information retrieval %A Demner-Fushman,D. %A Oard, Douglas %K bilingual term list %K Chinese language %K Computer science %K Control systems %K Cross-language information retrieval %K data mining %K Dictionaries %K dictionary-based information retrieval %K Educational institutions %K English language %K Frequency %K Information retrieval %K language translation %K named-entity translation %K natural languages %K Surface morphology %K Terminology %X Bilingual term lists are extensively used as a resource for dictionary-based cross-language information retrieval (CLIR), in which the goal is to find documents written in one natural language based on queries that are expressed in another. This paper identifies eight types of terms that affect retrieval effectiveness in CLIR applications through their coverage by general-purpose bilingual term lists, and reports results from an experimental evaluation of the coverage of 35 bilingual term lists in news retrieval application. Retrieval effectiveness was found to be strongly influenced by term list size for lists that contain between 3,000 and 30,000 unique terms per language. Supplemental techniques for named entity translation were found to be useful with even the largest lexicons. The contribution of named-entity translation was evaluated in a cross-language experiment involving English and Chinese. Smaller effects were observed from deficiencies in the coverage of domain-specific terminology when searching news stories. %B Proceedings of the 36th Annual Hawaii International Conference on System Sciences, 2003 %I IEEE %8 2003/01/06/9 %@ 0-7695-1874-5 %G eng %R 10.1109/HICSS.2003.1174250 %0 Conference Paper %B 19th International Conference on Data Engineering, 2003. Proceedings %D 2003 %T Using state modules for adaptive query processing %A Vijayshankar Raman %A Deshpande, Amol %A Hellerstein,J. M %K adaptive query processing %K Bandwidth %K Calibration %K data encapsulation %K data structure %K Data structures %K Databases %K Dictionaries %K eddy routing %K eddy routing operator %K Encapsulation %K join operator %K multiple algorithm automatic hybridization %K multiple competing join algorithm %K query architecture %K Query processing %K query spanning tree %K Routing %K routing policy %K Runtime %K shared materialization point %K State Module %K SteMs %K Telegraph dataflow system %K Telegraphy %K Tree data structures %X We present a query architecture in which join operators are decomposed into their constituent data structures (State Modules, or SteMs), and dataflow among these SteMs is managed adaptively by an eddy routing operator [R. Avnur et al., (2000)]. Breaking the encapsulation of joins serves two purposes. First, it allows the eddy to observe multiple physical operations embedded in a join algorithm, allowing for better calibration and control of these operations. Second, the SteM on a relation serves as a shared materialization point, enabling multiple competing access methods to share results, which can be leveraged by multiple competing join algorithms. Our architecture extends prior work significantly, allowing continuously adaptive decisions for most major aspects of traditional query optimization: choice of access methods and join algorithms, ordering of operators, and choice of a query spanning tree. SteMs introduce significant routing flexibility to the eddy, enabling more opportunities for adaptation, but also introducing the possibility of incorrect query results. We present constraints on eddy routing through SteMs that ensure correctness while preserving a great deal of flexibility. We also demonstrate the benefits of our architecture via experiments in the Telegraph dataflow system. We show that even a simple routing policy allows significant flexibility in adaptation, including novel effects like automatic "hybridization " of multiple algorithms for a single join. %B 19th International Conference on Data Engineering, 2003. Proceedings %I IEEE %P 353 - 364 %8 2003/03/05/8 %@ 0-7803-7665-X %G eng %R 10.1109/ICDE.2003.1260805 %0 Report %D 2000 %T Chinese-English Semantic Resource Construction %A Dorr, Bonnie J %A Levow,Gina-Anne %A Lin,Dekang %A Thomas,Scott %K *CHINESE LANGUAGE %K *ENGLISH LANGUAGE %K *LEXICONS %K *SEMANTICS %K *VERBS %K *WORD SENSES %K *WORDS(LANGUAGE) %K classification %K CONCEPTS %K CONSTRUCTION %K Dictionaries %K INFORMATION SCIENCE %K linguistics %K VERB CLASSES %K Vocabulary %X We describe an approach to large-scale construction of a semantic lexicon for Chinese verbs. We leverage off of three existing resources-- a classification of English verbs called EVCA (English Verbs Classes and Alternations), a Chinese conceptual database called HowNet, and a large-machine readable dictionary called Optilex. The resulting lexicon is used for determining appropriate word senses in applications such as machine translation and cross-language information retrieval. %I Instititue for Advanced Computer Studies, Univ of Maryland, College Park %8 2000/06// %G eng %U http://stinet.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA458703 %0 Conference Paper %B String Processing and Information Retrieval Symposium, 1999 and International Workshop on Groupware %D 1999 %T Effects of term segmentation on Chinese/English cross-language information retrieval %A Oard, Douglas %A Wang,Jianqiang %K alternative term weighting strategies %K cascading effect %K Chinese segmentation techniques %K Chinese/English cross-language information retrieval %K Chromium %K CLIR problems %K Cross-Language Information Retrieval research %K data mining %K Dictionaries %K dictionary-based Chinese %K East Asian languages %K English query translation %K European languages %K future work %K Information retrieval %K language translation %K linguistics %K natural language processing %K natural languages %K productive directions %K Reactive power %K retrieval effectiveness %K task-tuned segmentation algorithms %K technical terms %K term segmentation %K text analysis %K written Chinese texts %X The majority of recent Cross-Language Information Retrieval (CLIR) research has focused on European languages. CLIR problems that involve East Asian languages such as Chinese introduce additional challenges, because written Chinese texts lack boundaries between terms. The paper examines three Chinese segmentation techniques in combination with two variants of dictionary-based Chinese to English query translation. The results indicate that failure to segment terms, particularly technical terms and names, can have a cascading effect that reduces retrieval effectiveness. Task-tuned segmentation algorithms and alternative term weighting strategies are suggested as productive directions for future work %B String Processing and Information Retrieval Symposium, 1999 and International Workshop on Groupware %I IEEE %P 149 - 157 %8 1999/// %@ 0-7695-0268-7 %G eng %R 10.1109/SPIRE.1999.796590 %0 Report %D 1988 %T A Lexical Conceptual Approach to Generation for Machine Translation %A Dorr, Bonnie J %K *MACHINE TRANSLATION %K *NATURAL LANGUAGE %K *SYSTEMS APPROACH %K COMPUTATIONS %K CYBERNETICS %K Dictionaries %K grammars %K internal %K LEXICOGRAPHY %K SURFACES %K syntax %K THEORY %K TRANSLATIONS %K WORDS(LANGUAGE) %X Current approaches to generation for machine translation make use of direct-replacement templates, large grammars, and knowledge-based inferencing techniques. Not only are rules language-specific, but they are too simplistic to handle sentences that exhibit more complex phenomena. Furthermore, these systems are not easily extendable to other languages because the rules that map the internal representation to the surface form are entirely dependent on both the domain of the system and the language being generated. Finally an adequate interlingual representation has not yet been discovered; thus, knowledge-based inferencing is necessary and syntactic cross-linguistic generalization cannot be exploited. This report introduces a plan for the development of a theoretically based computational scheme of natural language generation for a translation system. The emphasis of the project is the mapping from the lexical conceptual structure of sentences to an underlying or base syntactic structure called deep structure. This approach tackles the problems of thematic and structural divergence, i.e., it allows generation of target language sentences that are not thematically or structurally equivalent to their conceptually equivalent source language counterparts. Two other more secondary tasks, construction of a dictionary and mapping from deep structure to surface structure, will also be discussed. The generator operates on a constrained grammatical theory rather than on a set of surface level tranformations. %I MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB %8 1988/01// %G eng %U http://stinet.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA197356