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

In this paper we introduce a constrained Level Building Algorithm (LBA) in order to reduce the search space of a Large Vocabulary Handwritten Word Recognition (LVHWR) system. A time and a length constraint are introduced to limit the number of frames and the number of levels of the LBA respectively. A regression model that fits the response variables, namely, accuracy and speed, to a non?linear function of the constraints is proposed and a statistical experimental design technique is employed to analyse the effects of the two constraints on the responses. Experimental results prove that the inclusion of these constraints improve the recognition speed of the LVHWR system without changing the recognition rate significantly.

/pdf/a-time-length-constrained-level-building-algorithm-for-large-4icti59kqy.pdf

A Time-Length Constrained Level Building Algorithm for Large Vocabulary Handwritten Word Recognition

This paper proposes a model-based character extraction method. We model a pixel belonging to a character as a double-edge, whose range is defined by the stroke width, and whose intensity is proportional to the local contrast. By extracting such double-edge feature at a predefined stroke width, sharply changing as well as slowly varying backgrounds can be eliminated. A set of morphological operators is designed to extract the double-edge feature at each pixel of the raw image, and the characters are extracted by thresholding these features. A goal directed evaluation of extraction of the courtesy amount from bank cheques reveals the advantages of the proposed method over other existing methods. Visual inspection of legal amount extraction shows further promise in extracting characters from complex backgrounds.

Model-based character extraction from complex backgrounds

Mobile phone usage has become very common. The market continues to grow as more advanced functionalities are incorporated in mobile phones. They possess sufficient computational capability that is needed for the identification and authentication of banknotes. This paper presents a mobile application for the recognition of banknote denominations and detection of counterfeit Nigerian Naira notes using Unity 3D – which is a multiplatform mobile application development system. The system extracted the face value of the banknotes and evaluated its performance using a combination of several KNN distant measures based on a Cascaded Ensemble approach. It was tested on the Android and iOS platforms using a Samsung Galaxy S6 and an iPhone 6 respectively. The experimental results presented a 99.27% recognition rate, a 94.70% detection rate, at an average processing time of 0.02 ms.

Mobile App for Detection of Counterfeit Banknotes

A pattern recognition system mainly contains two functional parts, i.e. feature extraction and pattern classification. The success of such a system depends on not only the effectiveness of each of them, but also their operation in concert. The feature extraction process in a traditional recognition system has two major tasks, namely, to extract deformation invariant signals and to reduce data. When a neural network is used as a pattern classifier, however, an alteration in these basic objectives is needed. In particular, the consideration of data reduction will be replaced by that of the suitability of feature vectors to the neural network. In this paper, feature extraction algorithms in character recognition have been designed based on these principles. The improvements made by these algorithms have been demonstrated in a series of experiments which justify such a change in the fundamental objectives of the feature extraction process when an associative memory classifier is used.

Feature extraction in character recognition with associative memory classifier

We introduce a technique based on diagonal white runs and vertical edges, that divides a document image into columns and blocks which are subsequently classified as text or graphics. A diagonal white run (drun) is a set of adjacent white pixels that are diagonally connected, and a vertical edge consists of the white area between two consecutive druns. This technique was designed as a layout-independent approach. Testing the proposed approach on document images with 14 different types and layouts, written in different languages, shows comparative and promising results.

Ching Y. Suen

Papers

A Time-Length Constrained Level Building Algorithm for Large Vocabulary Handwritten Word Recognition

Model-based character extraction from complex backgrounds

Mobile App for Detection of Counterfeit Banknotes

Feature extraction in character recognition with associative memory classifier

Segmenting document images using diagonal white runs and vertical edges