Online and offline character recognition using alignment to prototypes

Alon, Jonathan; Athitsos, Vassilis; Sclaroff, Stan

doi:10.1109/icdar.2005.177

Cited by 11 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DTW had been proved to be an efficient method to calculate distance in online handwriting recognition [3][4][5]. Here we select the simple k-Nearest Neighbor (NN) classifier to compare the recognition performance of two distance metrics: DTW and AI-DTW.…”

Section: Figure 2 Examples Of Rotated Testing Samplesmentioning

confidence: 99%

“…The main drawback of using NN classifier is its low speed. However, one can reduce the computation time greatly by using learned prototypes [4]. Due to page limitation, we have to omit the detailed discussion on this.…”

Section: Figure 2 Examples Of Rotated Testing Samplesmentioning

confidence: 99%

“…By using the Dynamic Programming (DP) algorithm, the best warping path can be found in a polynomial time. DTW was originally developed in automatic speech recognition to cope with different speaking speeds [1], [2], and has been widely used in handwriting/document recognition [3][4][5][6], image analysis and etc.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Affine Invariant Dynamic Time Warping and its Application to Online Rotated Handwriting Recognition

Qiao

Yasuhara

2006

18th International Conference on Pattern Recognition (ICPR'06)

View full text Add to dashboard Cite

show abstract

Section: Figure 2 Examples Of Rotated Testing Samplesmentioning

confidence: 99%

Section: Figure 2 Examples Of Rotated Testing Samplesmentioning

confidence: 99%

See 1 more Smart Citation

Affine Invariant Dynamic Time Warping and its Application to Online Rotated Handwriting Recognition

Qiao

Yasuhara

2006

18th International Conference on Pattern Recognition (ICPR'06)

View full text Add to dashboard Cite

show abstract

“…This process is often vital in order to construct reliable and discriminative models of classes that appear in distinctly different forms. For such reasons this type of clustering is a natural part of unsupervised training of model based online handwriting recognition classifiers independently of the recognition approach used [1,2,6,7,8]. The most common approaches here are k-Means based algorithms [3,7] and algorithms based on Hierarchical Agglomerative Clustering [1,2].…”

Section: Clusteringmentioning

confidence: 99%

Class Dependent Cluster Refinement

Sternby

2006

18th International Conference on Pattern Recognition (ICPR'06)

View full text Add to dashboard Cite

Unsupervised classification is a very common problem in pattern recognition even when the classes are known. In many areas intra-class variations may be greater than the inter-class variations causing a need for a subdivision of the training set of a class into smaller subunits often referred to as clusters. The subdivision or clustering is often performed independently of the relative properties of the other present classes in the recognition task. This paper presents a novel class-dependent approach to the clustering problem. Experiments with online handwriting data show that the novel clustering approach CDCR produces a clustering better suited for the task of pattern recognition. Although only validated for two recognition methods in this paper, the same approach could be applied to other methods as well as to other pattern recognition problems.

show abstract

“…Each weak classifier is a classifierF i , where F i is a 1D embedding. In [56], [57], [58], we have described alternative families of weak classifiers that can be used within the context of this algorithm.…”

Section: Choosing the Next Weak Classifier And Weightmentioning

confidence: 99%

BoostMap: An Embedding Method for Efficient Nearest Neighbor Retrieval

Athitsos

Alon

Sclaroff

et al. 2008

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

Abstract-This paper describes BoostMap, a method for efficient nearest neighbor retrieval under computationally expensive distance measures. Database and query objects are embedded into a vector space in which distances can be measured efficiently. Each embedding is treated as a classifier that predicts for any three objects X, A, B whether X is closer to A or to B. It is shown that a linear combination of such embedding-based classifiers naturally corresponds to an embedding and a distance measure. Based on this property, the BoostMap method reduces the problem of embedding construction to the classical boosting problem of combining many weak classifiers into an optimized strong classifier. The classification accuracy of the resulting strong classifier is a direct measure of the amount of nearest neighbor structure preserved by the embedding. An important property of BoostMap is that the embedding optimization criterion is equally valid in both metric and nonmetric spaces. Performance is evaluated in databases of hand images, handwritten digits, and time series. In all cases, BoostMap significantly improves retrieval efficiency with small losses in accuracy compared to brute-force search. Moreover, BoostMap significantly outperforms existing nearest neighbor retrieval methods such as Lipschitz embeddings, FastMap, and VP-trees.

show abstract

Online and offline character recognition using alignment to prototypes

Abstract: Abstract

Cited by 11 publications

References 16 publications

Affine Invariant Dynamic Time Warping and its Application to Online Rotated Handwriting Recognition

Affine Invariant Dynamic Time Warping and its Application to Online Rotated Handwriting Recognition

Class Dependent Cluster Refinement

BoostMap: An Embedding Method for Efficient Nearest Neighbor Retrieval

Contact Info

Product

Resources

About