Results 1  10
of
573,030
Graph Transformer Networks for Image Recognition
"... This contribution takes the example of a check reading system to discuss the modeling and estimation issues associated with large scale pattern recognition systems. 1. Problem Decomposition and Model Composition Consider a system that takes the image of a check and returns the check amount. This sys ..."
Abstract
 Add to MetaCart
This contribution takes the example of a check reading system to discuss the modeling and estimation issues associated with large scale pattern recognition systems. 1. Problem Decomposition and Model Composition Consider a system that takes the image of a check and returns the check amount. This system locates the numerical amount, recognizes digits or other symbols, and parses the check amount. Accuracy should remain high despite countless variations in check layout, writing style or amount grammar. From an engineering perspective, one must design components for locating the amount, segmenting characters, recognizing digits, and parsing the amount text. Yet it is very difficult to locate the amount without identifying that it is composed of characters that mostly resemble digits and form a meaningful check amount (not a date or a routing number). Purely sequential approaches do not work. Components must interact, form hypotheses and backtrack erroneous decisions. The orchestration is difficult to design and costly to maintain. From a statistical perspective, one seeks to estimate and compare the posterior probabilities P (Y X) where variable X represents a check image and variable Y represents a check amount. Let us define a suitable parametric model pθ(yx), gather data pairs (xi, yi), and maximize the likelihood ∑ i log pθ(yixi). Such a direct approach leads to problems of unpractical sizes. It is therefore common to manually annotate some pairs (xi, yi) with detailled information such as isolated character images T, character codes C, or sequences S of character codes. One can then model P (CT) and P (Y S) and obtain components such as a character recognizer or an amount parser. The statistical perspective suggests a principled way to orchestrate the interaction of these components: let the global model pθ(yx) be expressed as a composition of submodels such as pθ(ct) and pθ(ys). The submodels are first fit using the detailled data. The resulting parameters are used as a bias when fitting the global model pθ(yx) using the initial data pairs (yixi). This bias can be viewed as a capacity control tool for structural risk minimization
Reading Checks With Multilayer Graph Transformer Networks
, 1997
"... We propose a new machine learning paradigm called Multilayer Graph Transformer Network that extends the applicability of gradientbased learning algorithms to systems composed of modules that take graphs as input and produce graphs as output. A complete check reading system based on this concept is ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
We propose a new machine learning paradigm called Multilayer Graph Transformer Network that extends the applicability of gradientbased learning algorithms to systems composed of modules that take graphs as input and produce graphs as output. A complete check reading system based on this concept
Reading Checks With Multilayer Graph Transformer Networks
, 1997
"... We propose a new machine learning paradigm called Multilayer Graph Transformer Network that extends the applicability of gradientbased learning algorithms to systems composed of modules that take graphs as input and produce graphs as output. A complete check reading system based on this concept is ..."
Abstract
 Add to MetaCart
We propose a new machine learning paradigm called Multilayer Graph Transformer Network that extends the applicability of gradientbased learning algorithms to systems composed of modules that take graphs as input and produce graphs as output. A complete check reading system based on this concept
Global Training of Document Processing Systems using Graph Transformer Networks.
 In Proc. of Computer Vision and Pattern Recognition
, 1997
"... We propose a new machine learning paradigm called Graph Transformer Networks that extends the applicability of gradientbased learning algorithms to systems composed of modules that take graphs as inputs and produce graphs as output. Training is performed by computing gradients of a global objective ..."
Abstract

Cited by 24 (5 self)
 Add to MetaCart
We propose a new machine learning paradigm called Graph Transformer Networks that extends the applicability of gradientbased learning algorithms to systems composed of modules that take graphs as inputs and produce graphs as output. Training is performed by computing gradients of a global
Global Training of Document Processing Systems using Graph Transformer Networks.
"... We propose a new machine learning paradigm called Graph Transformer Networks that extends the applicability of gradientbased learning algorithms to systems composed of modules that take graphs as inputs and produce graphs as output. Training is performed by computing gradients of a global objective ..."
Abstract
 Add to MetaCart
We propose a new machine learning paradigm called Graph Transformer Networks that extends the applicability of gradientbased learning algorithms to systems composed of modules that take graphs as inputs and produce graphs as output. Training is performed by computing gradients of a global
Gradientbased learning applied to document recognition
 Proceedings of the IEEE
, 1998
"... Multilayer neural networks trained with the backpropagation algorithm constitute the best example of a successful gradientbased learning technique. Given an appropriate network architecture, gradientbased learning algorithms can be used to synthesize a complex decision surface that can classify hi ..."
Abstract

Cited by 1533 (84 self)
 Add to MetaCart
of graph transformer networks. A graph transformer network for reading a bank check is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal checks. It is deployed commercially and reads
Factor Graphs and the SumProduct Algorithm
 IEEE TRANSACTIONS ON INFORMATION THEORY
, 1998
"... A factor graph is a bipartite graph that expresses how a "global" function of many variables factors into a product of "local" functions. Factor graphs subsume many other graphical models including Bayesian networks, Markov random fields, and Tanner graphs. Following one simple c ..."
Abstract

Cited by 1791 (69 self)
 Add to MetaCart
A factor graph is a bipartite graph that expresses how a "global" function of many variables factors into a product of "local" functions. Factor graphs subsume many other graphical models including Bayesian networks, Markov random fields, and Tanner graphs. Following one simple
Community detection in graphs
, 2009
"... The modern science of networks has brought significant advances to our understanding of complex systems. One of the most relevant features of graphs representing real systems is community structure, or clustering, i. e. the organization of vertices in clusters, with many edges joining vertices of th ..."
Abstract

Cited by 821 (1 self)
 Add to MetaCart
The modern science of networks has brought significant advances to our understanding of complex systems. One of the most relevant features of graphs representing real systems is community structure, or clustering, i. e. the organization of vertices in clusters, with many edges joining vertices
An algorithm for drawing general undirected graphs
 Information Processing Letters
, 1989
"... Graphs (networks) are very common data structures which are handled in computers. Diagrams are widely used to represent the graph structures visually in many information systems. In order to automatically draw the diagrams which are, for example, state graphs, dataflow graphs, Petri nets, and entit ..."
Abstract

Cited by 698 (2 self)
 Add to MetaCart
Graphs (networks) are very common data structures which are handled in computers. Diagrams are widely used to represent the graph structures visually in many information systems. In order to automatically draw the diagrams which are, for example, state graphs, dataflow graphs, Petri nets
A Framework for Dynamic Graph Drawing
 CONGRESSUS NUMERANTIUM
, 1992
"... Drawing graphs is an important problem that combines flavors of computational geometry and graph theory. Applications can be found in a variety of areas including circuit layout, network management, software engineering, and graphics. The main contributions of this paper can be summarized as follows ..."
Abstract

Cited by 628 (44 self)
 Add to MetaCart
Drawing graphs is an important problem that combines flavors of computational geometry and graph theory. Applications can be found in a variety of areas including circuit layout, network management, software engineering, and graphics. The main contributions of this paper can be summarized
Results 1  10
of
573,030