this paper focuses on designing a handwriting recognition system dealing with on-line signal, i.e. temporel handwriting signal captured through an electronic pen or a digitalized tablet. We present here some new resul...
详细信息
ISBN:
(纸本)0769512631
this paper focuses on designing a handwriting recognition system dealing with on-line signal, i.e. temporel handwriting signal captured through an electronic pen or a digitalized tablet. We present here some new results concerning a hybrid on-line handwriting recognition system based on Hidden Markov Models (HMMs) and Neural Networks (NNs), which has already been presented in several contributions. In our approach, a letter-model is a Left-Right HMM, whose emission probability densities are approximated with mixtures of predictive multilayer perceptrons. the basic letter models are cascaded in order to build models for words and sentences. At the word level, recognition is performed thanks to a dictionary organized with a tree-structure. At the sentence level, a word-predecessor conditioned frame synchronous beam search algorithm allows to perform simultaneously segmentation into words and word recognition. It processes through the building of a word graph from which a set of candidate sentences may, be extracted. Word and sentence recognition performances are evaluated on parts of the UNIPEN international database.
In this paper we present a real-world evaluation of DMOS, a new generic document recognition method. this method uses a new grammatical formalism (EPF) and an associated parser able to introduce context in segmentatio...
详细信息
ISBN:
(纸本)0769512631
In this paper we present a real-world evaluation of DMOS, a new generic document recognition method. this method uses a new grammatical formalism (EPF) and an associated parser able to introduce context in segmentation. We have implemented this DMOS method to build an automatic generator of structured document recognition systems. We already produced three recognition systems by only changing the EPF grammar: one on musical scores, one on mathematical formulae and one on recursive table structures. We present here a specific light grammar to automatically recognize quite damaged 19th century military forms. the quality of those forms is far from perfect: table lines are not well printed, paper is so thin that there are transparency problems (the forms are two-sided) but the biggest problem comes from small paper sheets hidding part of the structure. the evaluation of this system has been made onto 5,268 images and the results show that the system did not make any mistake. Moreover it can recognize the entire structure in 97.2% of the forms (the other 2.8% are automatically set apart).
Motivated by several rulings in United States courts concerning expert testimony in general and handwriting testimony in particular, we undertook a study to objectively validate the hypothesis that handwriting is indi...
详细信息
ISBN:
(纸本)0769512631
Motivated by several rulings in United States courts concerning expert testimony in general and handwriting testimony in particular, we undertook a study to objectively validate the hypothesis that handwriting is individualistic. Handwriting samples of one thousand five hundred individuals, representative of the US population with respect to gender, age, ethnic groups, etc., were obtained. Analyzing differences in handwriting was done by using computer algorithms for extracting features from scanned images of handwriting. Attributes characteristic of the handwriting were obtained, e.g., line separation, slant, character shapes, etc. these attributes, which are a subset of attributes used by expert document examiners, were used to quantitatively establish individuality by using machine learning approaches. Using global attributes of hadwriting and very, few characters in the writing, the ability to determine the writer with a high degree of confidence was established. the work is a step towards providing scientific support for admitting handwriting evidence in court. the mathematical approach and the resulting software also have the promise of aiding the expert document examiner.
there tire many documents where text lines are not parallel to each other i.e. these lines have different inclinations withthe horizontal lines (mufti-skein documents). For the OCR of such a document we have to estim...
ISBN:
(纸本)0769512631
there tire many documents where text lines are not parallel to each other i.e. these lines have different inclinations withthe horizontal lines (mufti-skein documents). For the OCR of such a document we have to estimate the skew angle of individual text lines because a single rotation cannot de-skew all text lines of the document. In this paper, we describe a robust technique for multi-skew angle detection from Indian documents containing the most popular Indian scripts Devnagari and Bangla. Most characters in these scripts have horizontal lines at the top, called headlines. the character head-lines usually connect one another in a word and the word appears as a single component. In the proposed method, the connected components are tit,first labeled and selected. the upper envelopes of selected components tire found by column-wise scanning,from the top of the component. Portions of the zipper envelope satisfying the properties of a digital straight line tire detected. they arc then clustered into groups belonging to single text lines. Estimates from these individual clusters give the skew angle of each text line. the proposed mufti-skein detection technique has an accuracy about 98.3%.
the proceedings contain 73 papers. the special focus in this conference is on Representation and Analysis. the topics include: Invariant recognition and processing of planar shapes;recent advances in structural patter...
ISBN:
(纸本)3540421203
the proceedings contain 73 papers. the special focus in this conference is on Representation and Analysis. the topics include: Invariant recognition and processing of planar shapes;recent advances in structural patternrecognition with applications to visual form analysis;on learning the shape of complex actions;mereology of visual form;on matching algorithms for the recognition of objects in cluttered background;a fragment-based approach to object representation and classification;minimum-length polygons in approximation sausages;optimal local distances for distance transforms in 3D using an extended neighbourhood;independent modes of variation in point distribution models;qualitative estimation of depth in monocular vision;a new shape space for second order 3D-variations;spatial relations among pattern subsets as a guide for skeleton pruning;euclidean fitting revisited;on the representation of visual information;skeletons in the framework of graph pyramids;computational surface flattening;an adaptive image interpolation using the quadratic spline interpolator;the shock scaffold for representing 3D shape;curve skeletonization by junction detection in surface skeletons;representation of fuzzy shapes;skeleton-based shape models with pressure forces;a skeletal measure of 2D shape similarity;perception-based 2D shape modeling by curvature shaping and global topological properties of images derived from local curvature features.
this paper describes an on-line signature verification system using model-guided segmentation and discriminative feature selection for skilled forgeries. the system is based on segment-to-segment comparison between th...
详细信息
ISBN:
(纸本)0769512631
this paper describes an on-line signature verification system using model-guided segmentation and discriminative feature selection for skilled forgeries. the system is based on segment-to-segment comparison between the input signature and the reference model. To obtain a consistent segmentation, we propose a model-guided segmentation, which segments an input signature by the correspondence withthe reference model. To reject skilled forgeries effectively, we use a discriminative feature selection. It is motivated from the observation that a skilled forger can imitate the shape of the genuine signature better than even the owner, that is, some features distinguish skilled forgeries from genuine signatures though some features distinguish only random forgeries. For random forgeries and skilled forgeries respectively;we select the discriminative features among all the features according to the distance between references and forgeries. In the experiment, we collected 1,000 genuine signatures and 1,000 skilled forgeries. the result showed that the proposed method gave more stable segmentation, and the discriminative feature selection eliminated about 62% of the errors.
In this paper we show how the shape and dynamics of complex actions can be encoded using the intrinsic curvature and torsion signatures of their component actions. We then show how such invariant signatures can be int...
详细信息
We introduce a rule-based approach for the learning and recognition of complex movement sequences in terms of spatio-temporal attributes of primitive event sequences. During learning, spatio-temporal decision trees ar...
详细信息
the skeleton is an effective tool for shape analysis if its structure can be regarded as a faithful stick-like representation of the pattern. However, contour noise may affect this structure by originating spurious sk...
详细信息
We present an algorithm that, starting from the surface skeleton of a 3D solid object, computes the curve skeleton. the algorithm is based on the detection of curves and junctions in the surface skeleton. It can be ap...
详细信息
暂无评论