Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

Gradient-based learning applied to document recognition

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

The primary goal of pattern recognition is supervised or unsupervised classification. Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been most intensively studied and used in practice. More recently, neural network techniques and methods imported from statistical learning theory have been receiving increasing attention. The design of a recognition system requires careful attention to the following issues: definition of pattern classes, sensing environment, pattern representation, feature extraction and selection, cluster analysis, classifier design and learning, selection of training and test samples, and performance evaluation. In spite of almost 50 years of research and development in this field, the general problem of recognizing complex patterns with arbitrary orientation, location, and scale remains unsolved. New and emerging applications, such as data mining, web searching, retrieval of multimedia data, face recognition, and cursive handwriting recognition, require robust and efficient pattern recognition techniques. The objective of this review paper is to summarize and compare some of the well-known methods used in various stages of a pattern recognition system and identify research topics and applications which are at the forefront of this exciting and challenging field.

/pdf/statistical-pattern-recognition-a-review-1kz1b0tte4.pdf

Statistical pattern recognition: a review

We develop a common theoretical framework for combining classifiers which use distinct pattern representations and show that many existing schemes can be considered as special cases of compound classification where all the pattern representations are used jointly to make a decision. An experimental comparison of various classifier combination schemes demonstrates that the combination rule developed under the most restrictive assumptions-the sum rule-outperforms other classifier combinations schemes. A sensitivity analysis of the various schemes to estimation errors is carried out to show that this finding can be justified theoretically.

On combining classifiers

From the Publisher:
Pattern recognition has long been studied in relation to many different (and mainly unrelated) applications, such as remote sensing, computer vision, space research, and medical imaging. In this book Professor Ripley brings together two crucial ideas in pattern recognition; statistical methods and machine learning via neural networks. Unifying principles are brought to the fore, and the author gives an overview of the state of the subject. Many examples are included to illustrate real problems in pattern recognition and how to overcome them.This is a self-contained account, ideal both as an introduction for non-specialists readers, and also as a handbook for the more expert reader.

Pattern recognition and neural networks

An efficient low-level word image representation plays a crucial role in general cursive word recognition This paper proposes a novel representation scheme, where a word image can be represented as two sequences of feature vectors in two independent channels, which are extracted from vertical peak points on the upper external contour and at vertical minima on the lower external contour, respectively A data-driven method based on support vector machine is applied to prune and group those extreme points Our experimental results look promising and have indicated the potential of this low-level representation for complete cursive handwriting recognition

Low-Level cursive word representation based on geometric decomposition

Article history: Received: 15 August, 2018 Accepted: 11 October, 2018 Online: 18 October, 2018 This research presents a banknote recognition and counterfeit detection system that proposes a pre-processing approach before creating a new feature set by extracting Speeded-Up Robust Feature, creating image patches from its vertices and then computing the Histogram of Gradient descriptors from cells within the patch boundaries. A feature reduction approach is also designed based on a high correlation and Low variance filter to reduce the feature set by calculating the intra-feature value variability to ascertain the similarity between the elements to prune out highly correlated values and variances using a fixed threshold. For experimental evaluation, additional analysis was conducted using Principal Component Analysis, Bag of words, Low Variance filter, and High Correlation Filter method. Furthermore, the classification was performed using 10-fold crossvalidation based One-Versus-One Support Vector Machine. Additionally, the developed technique was tested on counterfeit banknotes to authenticate genuine and fake currencies. Lastly, point matching method was applied to detect our suggested feature vectors to match images containing multiple notes to distinguish and determine the value of the bills.

/pdf/modified-hog-descriptor-based-banknote-recognition-system-27ffcgndls.pdf

Modified HOG Descriptor-Based Banknote Recognition System

One of the most important script groups, which is based on Arabic alphabet, is the Persian/Farsi script This script is the basis of different languages used in Middle East and Central Asian regions For the development of Farsi handwritten word recognition systems, the CENPARMI group designed and collected a database Based on statistical features, a Hidden Markov Model based recognizer is developed First evaluation of the performance of this recognizer shows promising results

Handwritten Farsi Word Recognition Using Hidden Markov Models

A method called concentration-contour method is presented. It transforms a compound pattern into an integral one where contour analysis can be used. The concentration-contour method consists of four phases: (1) concentration of pattern, (2) extraction of contour, (3) transformation of numerical features, and (4) classification. The diagonal-diagonal regional projection transformation (DDRPT), which converts a compound pattern into an integral object, has been used. A VLSI architecture to implement the concentration-contour approach has been designed. The time complexity of the method is only O(N) compared with O(N/sup 2/) when a uniprocessor is used. >

VLSI architecture for parallel concentration-contour approach

To carry out face transformation, this paper presents new numerical algorithms, which consist of two parts, namely, the harmonic models for changes of face characteristics and the splitting techniques for grayness transition. The main method in this paper is a combination of the finite-volume method (FVM) with Delaunay triangulation to solve the Laplace equations in the harmonic transformation of face images. The advantages of the FVM with Delaunay triangulation are given as follows: 1) easy to formulate the linear algebraic equations; 2) good in retaining the pertinent geometric and physical need; and 3) less central processing unit time needed. Numerical and graphical experiments have been conducted for the face transformation from a female (woman) to a male (man), and vice versa. The computed sequential errors are O(N-(3/2)), where N2 is the division number of a pixel into subpixels. These computed errors coincide with the analysis on the splitting-shooting method (SSM) with piecewise constant interpolation in the previous paper of Li and Bai. In computation, the average absolute errors of restored pixel grayness can be smaller than 2 out of 256 grayness levels. The FVM is as simple as the finite-difference method (FDM) and as flexible as the finite-element method (FEM). Hence, the FVM is particularly useful when dealing with large face images with a huge number of pixels in shape distortion. The numerical transformation of face images in this paper can be used not only in pattern recognition but also in resampling, image morphing, and computer animation.

http://image.cse.nsysu.edu.tw/ServerPaper/59/Face%20transformation%20with%20harmonic%20models%20by%20finite%20volume%20method%20with%20Delaunay%20triangulation.pdf

Ching Y. Suen

Papers

Low-Level cursive word representation based on geometric decomposition

Modified HOG Descriptor-Based Banknote Recognition System

Handwritten Farsi Word Recognition Using Hidden Markov Models

VLSI architecture for parallel concentration-contour approach

Face Transformation With Harmonic Models by the Finite-Volume Method With Delaunay Triangulation