Recognition and segmentation of connected characters with selective attention

Fukushima, Kunihiko; Imagawa, Taro

doi:10.1016/s0893-6080(05)80071-1

Cited by 41 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second method was introduced by Frey and Slate (1991): 16 attributes are derived from the image, related to the horizontal/vertical position, width, height, etc. The last method under consideration was designed by Fukushima and Imagawa (1993): features are defined as a collection of 12 different representations in a 4 × 4 square. This is a typical example with several different sources of information and probably complementary.…”

Section: A24 a Handwritten Digit Recognition Problemmentioning

confidence: 99%

Methods for the combination of kernel matrices within a support vector framework

2009

View full text Add to dashboard Cite

The problem of combining different sources of information arises in several situations, for instance, the classification of data with asymmetric similarity matrices or the construction of an optimal classifier from a collection of kernels. Often, each source of information can be expressed as a similarity matrix. In this paper we propose a new class of methods in order to produce, for classification purposes, a single kernel matrix from a collection of kernel (similarity) matrices. Then, the constructed kernel matrix is used to train a Support Vector Machine (SVM). The key ideas within the kernel construction are twofold: the quantification, relative to the classification labels, of the difference of information among the similarities; and the extension of the concept of linear combination of similarity matrices to the concept of functional combination of similarity matrices. The proposed methods have been successfully evaluated and compared with other powerful classifiers and kernel combination techniques on a variety of artificial and real classification problems.

show abstract

Section: A24 a Handwritten Digit Recognition Problemmentioning

confidence: 99%

Methods for the combination of kernel matrices within a support vector framework

2009

View full text Add to dashboard Cite

show abstract

“…For example, Fukushima and Imagawa [20] proposed a model that performs recognition and segmentation simultaneously by employing a search controller that selects a small area of the input image for processing. Their model is based on Fukushima's neocognitron model for pattern recognition, which is a hierarchical multilayer network.…”

Section: Feature-based Analysis Versus Model-based Analysismentioning

confidence: 99%

Computational Scene Analysis

Wang

2007

Challenges for Computational Intelligence

View full text Add to dashboard Cite

Summary.A remarkable achievement of the perceptual system is its scene analysis capability, which involves two basic perceptual processes: the segmentation of a scene into a set of coherent patterns (objects) and the recognition of memorized ones. Although the perceptual system performs scene analysis with apparent ease, computational scene analysis remains a tremendous challenge as foreseen by Frank Rosenblatt. This chapter discusses scene analysis in the field of computational intelligence, particularly visual and auditory scene analysis. The chapter first addresses the question of the goal of computational scene analysis. A main reason why scene analysis is difficult in computational intelligence is the binding problem, which refers to how a collection of features comprising an object in a scene is represented in a neural network. In this context, temporal correlation theory is introduced as a biologically plausible representation for addressing the binding problem. The LEGION network lays a computational foundation for oscillatory correlation, which is a special form of temporal correlation. Recent results on visual and auditory scene analysis are described in the oscillatory correlation framework, with emphasis on real-world scenes. Also discussed are the issues of attention, feature-based versus model-based analysis, and representation versus learning. Finally, the chapter points out that the time dimension and David Marr's framework for understanding perception are essential for computational scene analysis.

show abstract

“…In this model, the states of a module are, in general, dynamically updated taking into account not only its given information processing but also the consistency of its relationship with other modules. Previous research has offered several approaches to interactive MNNs and their real-world applications (e.g., Carpenter and Grossberg 1988 ;Hassoun 1989;Kosko 1989;Tsutsumi 1989Tsutsumi , 1990; Murre et al 1992; Fukushima and Imagawa 1993;Happel and Murre 1994).…”

Section: Introductionmentioning

confidence: 99%

An artificial modular neural network and its basic dynamical characteristics

Ozawa

Tsutsumi

Baba

1998

Biological Cybernetics

View full text Add to dashboard Cite

This work contains a proposition of an artificial modular neural network (MNN) in which every module network exchanges input/output information with others simultaneously. It further studies the basic dynamical characteristics of this network through both computer simulations and analytical considerations. A notable feature of this model is that it has generic representation with regard to the number of composed modules, network topologies, and classes of introduced interactions. The information processing of the MNN is described as the minimization of a total-energy function that consists of partial-energy functions for modules and their interactions, and the activity and weight dynamics are derived from the total-energy function under the Lyapunov stability condition. This concept was realized by Cross-Coupled Hopfield Nets (CCHN) that one of the authors proposed. In this paper, in order to investigate the basic dynamical properties of CCHN, we offer a representative model called Cross-Coupled Hopfield Nets with Local And Global Interactions (CCHN-LAGI) to which two distinct classes of interactions -local and global interactionsare introduced. Through a conventional test for associative memories, it is confirmed that our energy-function-based approach gives us proper dynamics of CCHN-LAGI even if the networks have different modularity. We also discuss the contribution of a single interaction and the joint contribution of the two distinct interactions through the eigenvalue analysis of connection matrices.

show abstract

Recognition and segmentation of connected characters with selective attention

Cited by 41 publications

References 5 publications

Methods for the combination of kernel matrices within a support vector framework

Methods for the combination of kernel matrices within a support vector framework

Computational Scene Analysis

An artificial modular neural network and its basic dynamical characteristics

Contact Info

Product

Resources

About