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

This paper presents a novel approach to recognize images based on nonlinear wavelet approximation. The mathematical theory on nonlinear wavelet approximation is introduced, which shows that nonlinear approximation contains much more information of the original image than linear approximation. Based on this theory, a scheme to obtain the basic information of images with less data is provided. Experiments on face recognition produce effective matching rates.

Image Recognition Based on Nonlinear Wavelet Approximation

The objective of facial beauty prediction, which is a significant yet challenging problem in the domains of computer vision and machine learning, is to develop a human-like model that automatically evaluates facial attractiveness. Using deep learning methods to enhance facial beauty prediction is a promising and important area. This study provides a new framework for simultaneous facial attractiveness assessment, gender recognition as well as ethnicity identification using deep Convolutional Neural Networks (CNNs). Specifically, a deep residual network originally trained on massive face datasets is utilized which is capable of learning high-level and robust features from face images. Furthermore, a multi-task learning algorithm that operates on the effective features, exploits the synergy among the tasks. Said differently, a multi-task learning scheme is employed by our model to learn optimal shared features for these correlated tasks in an end-to-end manner. Interestingly, prediction correlation of 0.94 is achieved by our method for the SCUT-FBP5500 benchmark dataset (spanning 5500 facial images), which would certainly support the efficacy of our proposed model. This would also indicate significant improvement in accuracy over the other state-of-the-art methods.

Facial Beauty Prediction Using Transfer and Multi-task Learning Techniques.

We present a statistical hypothesis testing method for handwritten word segmentation algorithms. Our proposed method can be used along with any word segmentation algorithm in order to detect over-segmented or under-segmented errors or to adapt the word segmentation algorithm to new data in an unsupervised manner. The main idea behind the proposed approach is to learn the geometrical distribution of words within a sentence using a Markov chain or a Hidden Markov Model (HMM). In the former, we assume all the necessary information is observable, where in the latter, we assume the minimum observable variables are the bounding boxes of the words, and the hidden variables are the part of speech information. Our experimental results on a benchmark database show that not only we can achieve a lower over-segmentation and under-segmentation error rate, but also a higher correct segmentation rate as a result of the proposed hypothesis testing.

Statistical Hypothesis Testing for Handwritten Word Segmentation Algorithms

Mandarin was synthesized using a computer-controlled speech synthesizer. The four tones and the neutral one in the unstressed syllable were constructed by varying the pitch of the phoneme string. A passage and a list of single syllables were generated for an experiment. It was shown that subjects could hear the synthesized passage with an encouraging intelligibility score of over 70% after less than an hour of exposure to the sounds. The results also showed that the quality of the voice could be further improved by proper manipulation of the pitch.

Computer synthesis of Mandarin

An algorithm is presented of extracting features from Chinese characters. These features consist of the Fourier spectrum of projections obtained from multiple-layers of annular partitions. This method takes into consideration the square shape of Chinese characters to that the extracted features contain the significant information of the different parts of the character, and are insensitive to rotation and linear displacement. For the experiments, 97 similar Chinese characters were selected from the most frequently used characters. These characters were divided into 34 groups according to similarity in shape. Three different fonts of Chinese characters (Song, Kai and Bold face) were used. Four additional symbols were also included to study the effects of character symmetry on the proposed algorithm. Experimental results indicate that for any displacement and for rotations in the range of (-180 degrees , +180 degrees ), this method can separate without exception all similar Chinese characters including the complex ones. >

Ching Y. Suen

Papers

Image Recognition Based on Nonlinear Wavelet Approximation

Facial Beauty Prediction Using Transfer and Multi-task Learning Techniques.

Statistical Hypothesis Testing for Handwritten Word Segmentation Algorithms

Computer synthesis of Mandarin

Multi-layer projections for the classification of similar Chinese characters