Sciweavers

14 search results - page 2 / 3
» Diagonal Based Feature Extraction for Handwritten Alphabets ...
Sort
View
DAS
2006
Springer
13 years 8 months ago
Segmentation of On-Line Handwritten Japanese Text Using SVM for Improving Text Recognition
Abstract. This paper describes a method of producing segmentation point candidates for on-line handwritten Japanese text by a support vector machine (SVM) to improve text recogniti...
Bilan Zhu, Junko Tokuno, Masaki Nakagawa
NIPS
1997
13 years 6 months ago
Hybrid NN/HMM-Based Speech Recognition with a Discriminant Neural Feature Extraction
In thispaper, we present a novelhybridarchitecture forcontinuousspeech recognition systems. It consists of a continuous HMM system extended by an arbitrary neural network that is ...
Daniel Willett, Gerhard Rigoll
ICPR
2004
IEEE
14 years 6 months ago
An Efficient Three-Stage Classifier for Handwritten Digit Recognition
This paper proposes an efficient three-stage classifier for handwritten digit recognition based on NN (Neural Network) and SVM (Support Vector Machine) classifiers. The classifica...
Dejan Gorgevik, Dusan Cakmakov
ESANN
2004
13 years 6 months ago
Face Recognition Using Recurrent High-Order Associative Memories
A novel face recognition approach is proposed, based on the use of compressed discriminative features and recurrent neural classifiers. Low-dimensional feature vectors are extract...
Iulian B. Ciocoiu
ICPR
2000
IEEE
13 years 9 months ago
A New Segmentation Approach for Handwritten Digits
This article deals with a new segmentation approach applied to unconstrained handwritten digits. The novelty of the proposed algorithm is based on the combination of two types of ...
Luiz E. Soares de Oliveira, Edouard Lethelier, Fl&...