Results 1 -
9 of
9
Artificial Neural Networks for Document Analysis and Recognition
- IEEE TPAMI
, 2003
"... Artificial neural networks have been extensively applied to document analysis and recogni-tion. Most efforts have been devoted to the recognition of isolated handwritten and printed characters with widely recognized successful results. However, many other document pro-cessing tasks like pre-processi ..."
Abstract
-
Cited by 33 (5 self)
- Add to MetaCart
(Show Context)
Artificial neural networks have been extensively applied to document analysis and recogni-tion. Most efforts have been devoted to the recognition of isolated handwritten and printed characters with widely recognized successful results. However, many other document pro-cessing tasks like pre-processing, layout analysis, character segmentation, word recognition, and signature verification have been effectively faced with very promising results. This paper surveys most significant problems in the area of off-line document image processing where connectionist-based approaches have been applied. Similarities and differences between ap-proaches belonging to different categories are discussed. A particular emphasis is given on the crucial role of the prior knowledge for the conception of both appropriate architectures and learning algorithms. Finally, the paper provides a critical analysis on the reviewed approaches and depicts most promising research guidelines in the field. In particular, a sec-ond generation of connectionist-based models are foreseen which are based on appropriate graphical representations of the learning environment.
A class-modular feedforward neural network for handwriting recognition”, Pattern Recognition 35
, 2002
"... Since the conventional feedforward neural networks for character recognition have been designed to classify a large number of classes with one large networkstructure, inevitably it poses the very complex problem of determining the optimal decision boundaries for all the classes involved in a high-di ..."
Abstract
-
Cited by 32 (1 self)
- Add to MetaCart
(Show Context)
Since the conventional feedforward neural networks for character recognition have been designed to classify a large number of classes with one large networkstructure, inevitably it poses the very complex problem of determining the optimal decision boundaries for all the classes involved in a high-dimensional feature space. Limitations also exist in several aspects of the training and recognition processes. This paper introduces the class modularity concept to the feedforward neural networkclassi"er to overcome such limitations. In the class-modular concept, the original K-classi"cation problem is decomposed into K 2-classi"cation subproblems. A modular architecture is adopted which consists of K subnetworks, each responsible for discriminating a class from the other K!1 classes. The primary purpose of this paper is to prove the e!ectiveness of class-modular neural networks in terms of their convergence and recognition power. Several cases have been studied, including the recognition of handwritten numerals (10 classes), English capital letters (26 classes), touching numeral pairs (100 classes), and Korean characters in postal addresses (352 classes). The test results con"rmed the superiority of the class-modular neural networkand the interesting aspects on further investigations
Detection of Courtesy Amount Block on Bank Checks
- Journal of Electronic Imaging
, 1995
"... This paper presents a multi-staged technique for locating the courtesy amount block on bank checks. In the case of a check processing system, many of the proposed methods are not acceptable, due to the the presence of many fonts and text sizes, as well as the short length of many text strings. This ..."
Abstract
-
Cited by 11 (3 self)
- Add to MetaCart
(Show Context)
This paper presents a multi-staged technique for locating the courtesy amount block on bank checks. In the case of a check processing system, many of the proposed methods are not acceptable, due to the the presence of many fonts and text sizes, as well as the short length of many text strings. This paper will describe particular methods chosen to implement a Courtesy Amount Block Locator (CABL). First, the connected components in the image are identified. Next, strings are constructed on the basis of proximity and horizontal alignment of characters. Finally a set of rules and heuristics are applied to these strings to choose the correct one. The chosen string is only reported if it passes a verification test, which includes an attempt to recognize the currency sign. Keywords: check analysis and processing, block detection, courtesy amount recognition, image processing, heuristics rules, segmentation 1 Introduction Trillions of dollars change hands each year in the form of handwritten ...
A Modular Neural Network Architecture with Additional Generalization Abilities for Large Input Vectors
, 1997
"... This paper proposes a two layer modular neural system. The basic building blocks of the architecture are multilayer Perceptrons trained with the Backpropagation algorithm. Due to the proposed modular architecture the number of weight connections is less than in a fully connected multilayer Perceptro ..."
Abstract
-
Cited by 10 (3 self)
- Add to MetaCart
This paper proposes a two layer modular neural system. The basic building blocks of the architecture are multilayer Perceptrons trained with the Backpropagation algorithm. Due to the proposed modular architecture the number of weight connections is less than in a fully connected multilayer Perceptron. The modular network is designed to combine two different approaches of generalization known from connectionist and logical neural networks; this enhances the generalization abilities of the network. The architecture introduced here is especially useful in solving problems with a large number of input attributes. 1 Introduction The multilayer Perceptron (MLP) trained by the Backpropagation (BP) algorithm has been used to solve real-world problems in prediction, recognition, and optimization. If the input dimension is small the network can be trained very quickly. However for large input spaces the performance of the BP algorithm decreases [3]. In many cases it becomes difficult to find a ...
Modularity - A Concept For New Neural Network Architectures
, 1998
"... This paper focuses on the powerful concept of modularity. It is descried how this concept is deployed in natural neural networks on an architectural as well as on a functional level. Furthermore different approaches for modular neural networks are discussed. Based on this a two layer modular neural ..."
Abstract
-
Cited by 4 (0 self)
- Add to MetaCart
(Show Context)
This paper focuses on the powerful concept of modularity. It is descried how this concept is deployed in natural neural networks on an architectural as well as on a functional level. Furthermore different approaches for modular neural networks are discussed. Based on this a two layer modular neural system is introduced. The basic building blocks of the architecture are multilayer Perceptrons (MLP) trained with the Backpropagation algorithm. This modular network is designed to combine two different approaches of generalization known from connectionist and logical neural networks; this enhances the generalization abilities of the network. Experiments described in this paper show that the architecture is especially useful in solving problems with a large number of input attributes. MODULARITY Modularity is a very important concept in nature. Modularity can be defined as subdivision of a complex object into simpler objects. The subdivision is determined either by the structure or...
A Modular Neural Network Architecture with Additional Generalization Abilities for Large Input Vectors
- Third International Conference on Artificial Neural Networks and Genetic Algorithms (ICANNGA 97). Norwich/England
, 1997
"... This paper proposes a twolayer modular neural system. The basic building blocks of the architecture are multilayer Perceptrons trained with the Backpropagation algorithm. Due to the proposed modular architecture the number of weight connections is less than in a fully connected multilayer Perceptro ..."
Abstract
- Add to MetaCart
This paper proposes a twolayer modular neural system. The basic building blocks of the architecture are multilayer Perceptrons trained with the Backpropagation algorithm. Due to the proposed modular architecture the number of weight connections is less than in a fully connected multilayer Perceptron. The modular network is designed to combine two different approaches of generalization known from connectionist and logical neural networks# this enhances the generalization abilities of the network. The architecture introduced here is especially useful in solving problems with a large number of input attributes. 1
License Plate Recognition using Multi-cluster and Multilayer Neural Networks
"... Vehicle license plat recognition has been a much studied research area in many countries. Due to the different types of license plates being used, the require-ment of an automatic license plate recognition sys-temr is rather different for each country. In this pa-per, an automatic license plate reco ..."
Abstract
- Add to MetaCart
(Show Context)
Vehicle license plat recognition has been a much studied research area in many countries. Due to the different types of license plates being used, the require-ment of an automatic license plate recognition sys-temr is rather different for each country. In this pa-per, an automatic license plate recognition system is proposed for Malaysian vehicles with standard license plates based on image processing, feature extraction and neural networks. The image-processing library is developed in-house which we referred to as Vi-sion System Development Platform (VSDP). Multi-Cluster approach is applied to locate the license plate at the right position while Kirsch Edge feature extrac-tion technique is used to extract features from the li-cense plates characters which are then used as inputs to the neural network classifier. The neural network model is the standard multilayered perceptron trained using the back-propagation algorithm. The prototyped system has an accuracy of more than 91%, however, suggestions to further improve the system are dts-cussed in this paper based on the analysis of the error.
