Evaluating NN and HMM classifiers for handwritten word recognition

Oliveira, J.J. de; Carvalho, João; Freitas, Cinthia Obladen de Almendra; Sabourin, Robert

doi:10.1109/sibgra.2002.1167145

Cited by 8 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding varieties of different data sets used, our results are comparable with the works in [12] or [13]. In his work, De Oliveira in [13] used a HMM and then ANN classifiers for recognition of month names, and achieved a recognition rate of 75.9% and 81.8% respectively.…”

Section: Other Methods and Related Worksupporting

confidence: 78%

See 1 more Smart Citation

A View-Based T¿eplitz-Matrix-Supported System for Word Recognition without Segmentation

Tabędzki

Saeed

2006

Sixth International Conference on Intelligent Systems Design and Applications

View full text Add to dashboard Cite

In this paper, new modifications and experiments for word recognition and classification are presented. The algorithm is based on recognizing the whole words without separating them into letters. The whole word is treated and analyzed as an image. The method is based on the modification of a novel view-based word recognition algorithm -an approach that was successfully used by the authors' in previous works.This method shows how to recognize words without segmentation. The top and bottom views of the word are analyzed in order to create the feature vector. Then the feature vector is processed by the aid of Töeplitz matrices. The obtained series of Töeplitz matrix minimal eigenvalues are used for classification. The results are promising.

show abstract

Section: Other Methods and Related Worksupporting

confidence: 78%

“…In his work, De Oliveira in [13] used a HMM and then ANN classifiers for recognition of month names, and achieved a recognition rate of 75.9% and 81.8% respectively. Much larger database was used by Lavrenko et al in their work concerning handwritten words recognition in historical documents [14].…”

Section: Other Methods and Related Workmentioning

confidence: 99%

A View-Based T¿eplitz-Matrix-Supported System for Word Recognition without Segmentation

Tabędzki

Saeed

2006

Sixth International Conference on Intelligent Systems Design and Applications

View full text Add to dashboard Cite

show abstract

“…To reduce this variability slant and baseline skew normalization algorithms were applied [2], using inclinated projection profiles and shear transformation.…”

Section: Preprocessingmentioning

confidence: 99%

“…Next, a smoothing procedure is applied to eliminate histogram discontinuities. The Upper (UL) and Lower (LL) Lines are the ones above and below CL, respectively, with 70% of the maximum histogram value [2]. The central region of the word, is defined as the area located between the UL and LL lines.…”

Section: Perceptual Featuresmentioning

confidence: 99%

“…Further difficulty is added by the fact that the vowels (a, e, i, o) exhibit low discriminatory power in the human reading process [1]. The same lexicon has been studied in other works [2,3,4,5], with system performance always being limited by the confusions indicated in Figure 1. In this work, we utilize an approach based on multiple classifiers, projected to avoid the intrinsic difficulties of the lexicon.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Handwritten recognition with multiple classifiers for restricted lexicon

Oliveira

Kapp

Freitas

et al.

Proceedings. 17th Brazilian Symposium on Computer Graphics and Image Processing

Self Cite

View full text Add to dashboard Cite

This paper presents a multiple classifier system applied to the handwritten word recognition (HWR) problem. The goal is to analyse the influence of different global classifiers taken isolatedly as well as combined in a particular HWR task. The application proposed is the recognition of the Portuguese handwritten names of the months. The strategy takes advantage of the complementary mechanisms of three different classifiers: Conventional Neural Network, Class-Modular Neural Network and Hidden Markov Models, yielding a multiple classifier that is more efficient than either individual technique. The recognition rates obtained vary from 75.9% using the stand alone HMM classifier to 96.0% considering the classifiers combination.

show abstract

Techniques for Enhancing Pervasive Learning in Standard Natural Classroom

Zhou

Shen

et al.

Hybrid Learning and Education

View full text Add to dashboard Cite

Evaluating NN and HMM classifiers for handwritten word recognition

Cited by 8 publications

References 7 publications

A View-Based T¿eplitz-Matrix-Supported System for Word Recognition without Segmentation

A View-Based T¿eplitz-Matrix-Supported System for Word Recognition without Segmentation

Handwritten recognition with multiple classifiers for restricted lexicon

Techniques for Enhancing Pervasive Learning in Standard Natural Classroom

Contact Info

Product

Resources

About