Results 1  10
of
38
Review of shape representation and description techniques
, 2004
"... More and more images have been generated in digital form around the world. There is a growing interest in finding images in large collections or from remote databases. In order to nd an image, the image has to be described or represented by certain features. Shape is an important visual feature of a ..."
Abstract

Cited by 145 (2 self)
 Add to MetaCart
More and more images have been generated in digital form around the world. There is a growing interest in finding images in large collections or from remote databases. In order to nd an image, the image has to be described or represented by certain features. Shape is an important visual feature of an image. Searching for images using shape features has attracted much attention. There are many shape representation and description techniques in the literature. In this paper, we classify and review these important techniques. We examine implementation procedures for each technique and discuss its advantages and disadvantages. Some recent research results are also included and discussed in this paper. Finally, we identify some promising techniques for image retrieval according to standard principles.
Data Exploration Using SelfOrganizing Maps
 ACTA POLYTECHNICA SCANDINAVICA: MATHEMATICS, COMPUTING AND MANAGEMENT IN ENGINEERING SERIES NO. 82
, 1997
"... Finding structures in vast multidimensional data sets, be they measurement data, statistics, or textual documents, is difficult and timeconsuming. Interesting, novel relations between the data items may be hidden in the data. The selforganizing map (SOM) algorithm of Kohonen can be used to aid the ..."
Abstract

Cited by 96 (4 self)
 Add to MetaCart
Finding structures in vast multidimensional data sets, be they measurement data, statistics, or textual documents, is difficult and timeconsuming. Interesting, novel relations between the data items may be hidden in the data. The selforganizing map (SOM) algorithm of Kohonen can be used to aid the exploration: the structures in the data sets can be illustrated on special map displays. In this work, the methodology of using SOMs for exploratory data analysis or data mining is reviewed and developed further. The properties of the maps are compared with the properties of related methods intended for visualizing highdimensional multivariate data sets. In a set of case studies the SOM algorithm is applied to analyzing electroencephalograms, to illustrating structures of the standard of living in the world, and to organizing fulltext document collections. Measures are proposed for evaluating the quality of different types of maps in representing a given data set, and for measuring the robu...
PartofSpeech Tagging and Partial Parsing
 CorpusBased Methods in Language and Speech
, 1996
"... m we can carve o# next. `Partial parsing' is a cover term for a range of di#erent techniques for recovering some but not all of the information contained in a traditional syntactic analysis. Partial parsing techniques, like tagging techniques, aim for reliability and robustness in the face of the va ..."
Abstract

Cited by 96 (0 self)
 Add to MetaCart
m we can carve o# next. `Partial parsing' is a cover term for a range of di#erent techniques for recovering some but not all of the information contained in a traditional syntactic analysis. Partial parsing techniques, like tagging techniques, aim for reliability and robustness in the face of the vagaries of natural text, by sacrificing completeness of analysis and accepting a low but nonzero error rate. 1 Tagging The earliest taggers [35, 51] had large sets of handconstructed rules for assigning tags on the basis of words' character patterns and on the basis of the tags assigned to preceding or following words, but they had only small lexica, primarily for exceptions to the rules. TAGGIT [35] was used to generate an initial tagging of the Brown corpus, which was then handedited. (Thus it provided the data that has since been used to train other taggers [20].) The tagger described by Garside [56, 34], CLAWS, was a probabilistic version of TAGGIT, and the DeRose tagger improved on
Context and hierarchy in a probabilistic image model
 in CVPR
, 2006
"... It is widely conjectured that the excellent ROC performance of biological vision systems is due in large part to the exploitation of context at each of many levels in a part/whole hierarchy. We propose a mathematical framework (a “composition machine”) for constructing probabilistic hierarchical ima ..."
Abstract

Cited by 64 (0 self)
 Add to MetaCart
It is widely conjectured that the excellent ROC performance of biological vision systems is due in large part to the exploitation of context at each of many levels in a part/whole hierarchy. We propose a mathematical framework (a “composition machine”) for constructing probabilistic hierarchical image models, designed to accommodate arbitrary contextual relationships, and we build a demonstration system for reading Massachusetts license plates in an image set collected at Logan Airport. The demonstration system detects and correctly reads more than 98 % of the plates, with a negligible rate of false detection. Unlike a formal grammar, the architecture of a composition machine does not exclude the sharing of subparts among multiple entities, and does not limit interpretations to single trees (e.g. a scene can have multiple license plates, or no plates at all). In this sense, the architecture is more like a general Bayesian network than a formal grammar. On the other hand, unlike a Bayesian network, the distribution is nonMarkovian, and therefore more like a probabilistic contextsensitive grammar. The conceptualization and construction of a composition machine is facilitated by its formulation as the result of a series of nonMarkovian perturbations of a “Markov backbone. ” 1 1.
TwoDimensional Languages
, 1997
"... this paper, much work have been done in studying properties of picture languages recognized by finitestate machines and several other models have been designed. A survey on this subject can be found in [21]. An intersting model of twodimensional tape acceptor is the twodimensional online tessell ..."
Abstract

Cited by 56 (3 self)
 Add to MetaCart
this paper, much work have been done in studying properties of picture languages recognized by finitestate machines and several other models have been designed. A survey on this subject can be found in [21]. An intersting model of twodimensional tape acceptor is the twodimensional online tessellation automaton introduced by K. Inoue and A. Nakamura in [18]. This is defined as an infinite twodimensional array of identical conventional finitestate automata and it is a special type of cellular automaton. Despite it is not evident that it is a generalization of a onedimensional model, it can be easily 2 identified to a conventional automaton when restricted to onerow (or onecolumn) pictures. Moreover, the family of picture languages recognized by this model of automaton satisfy many important properties. Different systems to generate pictures using grammars have been also explored (cf. [31, 32, 33, 35, 34, 36, 29, 30, 39]). However, in the finite state case, this approach is shown to be less powerful than others. Another possible generalization is to describe picture languages by logic formulas. Recently, W. Thomas gave a general formalism to describe graphs (and, in particular, pictures) as model theoretical structures and showed as "recognizability" corresponds to the notions of definability on existential monadic second order logic (cf. [38]). This is coherent with the string language recognizability theory where Buchi's Theorem holds. In a recent proposal (cf. [13, 14]) a notion of recognizability of a set of pictures in terms of tiling systems is introduced. The underlying idea is to define recognizability by "projection of local properties". Informally, recognition in a tiling system is defined in terms of a finite set of square pictures of side two which c...
Learning of ContextFree Languages: A Survey of the Literature
 REP
, 1996
"... We survey methods for learning contextfree languages (CFL's) in the theoretical computer science literature. We first present some important negative results. Then, we consider five types of methods: those that take text as input, those that take structural information as input, those that rely on ..."
Abstract

Cited by 21 (0 self)
 Add to MetaCart
We survey methods for learning contextfree languages (CFL's) in the theoretical computer science literature. We first present some important negative results. Then, we consider five types of methods: those that take text as input, those that take structural information as input, those that rely on CFL formalisms that are not based on contextfree grammars, those which learn subclasses of CFL's, and stochastic methods. A description of the subclasses of CFL's considered is provided, as is an extensive bibliography.
Stochastic Language Models for StyleDirected Layout Analysis of Document Images
 IEEE TRANSACTIONS ON IMAGE PROCESSING
, 2003
"... Image segmentation is an important component of any document image analysis system. While many segmentation algorithms exist in the literature, very few i) allow users to specify the physical style, and ii) incorporate userspecified style information into the algorithm's objective function that is ..."
Abstract

Cited by 13 (1 self)
 Add to MetaCart
Image segmentation is an important component of any document image analysis system. While many segmentation algorithms exist in the literature, very few i) allow users to specify the physical style, and ii) incorporate userspecified style information into the algorithm's objective function that is to be minimized. We describe a segmentation algorithm that models a document's physical structure as a hierarchical structure where each node describes a region of the document using a stochastic regular grammar. The exact form of the hierarchy and the stochastic language is specified by the user, while the probabilities associated with the transitions are estimated from groundtruth data. We demonstrate the segmentation algorithm on images of bilingual dictionaries.
Image registration and object recognition using affine invariants and convex hulls
 IEEE Transactions on Image Processing
, 1999
"... Abstract — This paper is concerned with the problem of feature point registration and scene recognition from images under weak perspective transformations which are well approximated by affine transformations, and under possible occlusion and/or appearance of new objects. It presents a set of local ..."
Abstract

Cited by 9 (0 self)
 Add to MetaCart
Abstract — This paper is concerned with the problem of feature point registration and scene recognition from images under weak perspective transformations which are well approximated by affine transformations, and under possible occlusion and/or appearance of new objects. It presents a set of local absolute affine invariants derived from the convex hull of scattered feature points (e.g., fiducial or marking points, corner points, inflection points, etc.) extracted from the image. The affine invariants are constructed from the areas of the triangles formed by connecting three vertices among a set of four consecutive vertices (quadruplets) of the convex hull, and hence do make direct use of the area invariance property associated with the affine transformation. Because they are locally constructed, they are very well suited to handle the occlusion and/or appearance of new objects. These invariants are used to establish the correspondences between the convex hull vertices of a test image with a reference image in order to undo the affine transformation between them. A point matching approach for recognition follows this. The time complexity for registering v feature points on the test image with x feature points of the reference image is of order y@x 2 vA vA. vA The method has been tested on real indoor and outdoor images and performs well. Index Terms—Affine invariants, affine transformations, alignment, convex hull, occlusion, perspective, registration, weak. I.
Inductive Inference Theory  A Unified Approach To Problems In Pattern Recognition And Artificial Intelligence
 Proceedings of the 4th International Conference on Artificial Intelligence , pp 274 280
, 1975
"... Recent results in induction theory are reviewed that demonstrate the general adequacy of the induction system of Solomono# and Willis. Several problems in pattern recognition and A.I. are investigated through these methods. The theory is used to obtain the a priori probabilities that are necessa ..."
Abstract

Cited by 9 (3 self)
 Add to MetaCart
Recent results in induction theory are reviewed that demonstrate the general adequacy of the induction system of Solomono# and Willis. Several problems in pattern recognition and A.I. are investigated through these methods. The theory is used to obtain the a priori probabilities that are necessary in the application of stochastic languages to pattern recognition.
An FPGAbased coprocessor for the parsing of contextfree grammars
, 2000
"... This paper presents an FPGAbased implementation of a coprocessing unit able to parse contextfree grammars of reallife sizes. The application fields of such a parser range from programming languages syntactic analysis to very demanding Natural Language Applications where parsing speed is an impor ..."
Abstract

Cited by 9 (4 self)
 Add to MetaCart
This paper presents an FPGAbased implementation of a coprocessing unit able to parse contextfree grammars of reallife sizes. The application fields of such a parser range from programming languages syntactic analysis to very demanding Natural Language Applications where parsing speed is an important issue.