Chin-Chin Lin

A prototype classification method and its use in a hybrid solution for multiclass pattern recognition

In this paper, we propose a prototype classification method that employs a learning process to determine both the number and the location of prototypes. This learning process decides whether to stop adding prototypes according to a certain termination condition, and also adjusts the location of prototypes using either the K-means (KM) or the fuzzy c-means (FCM) clustering algorithms. When the prototype classification method is applied, the support vector machine (SVM) method can be used to post-process the top-rank candidates obtained during the prototype learning or matching process. We apply this hybrid solution to handwriting recognition and address the convergence behavior and runtime consumption of the prototype construction process, and discuss how to combine our prototype classifier with SVM classifiers to form an effective hybrid classifier.

A prototype classification method and its application to handwritten character recognition

We propose a new prototype classification method that can be combined with support vector machines (SVM) (Cortes, C and Vapnik, V, 1995) for recognizing handwritten numerals and Chinese characters. This method employs a learning process for determining both the number and location of prototypes. The possible techniques used in this process for adjusting the location of prototypes include the K-means (KM) algorithm and the fuzzy c-means (FCM) algorithm (Bezdek, J. C., 1981). When the prototype classification method is applied, the SVM method can be used to process top rank candidates obtained in the prototype learning or matching process. We apply this hybrid method to the recognition of handwritten numerals and Chinese characters. Experiment results show that this hybrid method saves great amount of training and testing time when the number of character types is large, and achieves comparable accuracy rates to those achieved by using SVM solely. Our results also show that the proposed method performs better than the nearest neighbor (NN) classification method. These outcomes suggest that the proposed method can serve as an effective solution for large-scale multiclass classification

Caption analysis and recognition for building video indexing systems

Abstract.In this paper, we propose several methods for analyzing and recognizing Chinese video captions, which constitute a very useful information source for video content. Image binarization, performed by combining a global threshold method and a window-based method, is used to obtain clearer images of characters, and a caption-tracking scheme is used to locate caption regions and detect caption changes. The separation of characters from possibly complex backgrounds is achieved by using size and color constraints and by cross examination of multiframe images. To segment individual characters, we use a dynamic split-and-merge strategy. Finally, we propose a character recognition process using a prototype classification method, supplemented by a disambiguation process using support vector machines, to improve recognition outcomes. This is followed by a postprocess that integrates multiple recognition results. The overall accuracy rate for the entire process applied to test video films is 94.11%.

Language identification of character images using machine learning techniques

In this paper, we propose a new approach for identifying the language type of character images. We do this by classifying individual character images to determine the language boundaries in multilingual documents. Two effective methods are considered for this purpose: the prototype classification method and support vector machines (SVM). Due to the large size of our training data set, we further propose a technique to speed up the training process for both methods. Applying the two methods to classifying characters into Chinese, English, and Japanese (including Hiragana and Katakana) has produced very accurate and comparable test results.

Applying a hybrid method to handwritten character recognition

We propose a new prototype learning/matching method that can be combined with support vector machines (SVM) in pattern recognition. This hybrid method has the following merits. One, the learning algorithm for constructing prototypes determines both the number and the location of prototypes. This algorithm terminates within a finite number of iterations and assures that each training sample matches in class types with the nearest prototype. Two, SVM can be used to process top-rank candidates obtained by the prototype learning/matching method so as to save time in both training and testing processes. We apply our method to recognizing handwritten numerals and handwritten Chinese/Hiragana characters. Experiment results show that the hybrid method saves great amount of training and testing time in large-scale tasks and achieves comparable accuracy rates to those achieved by using SVM solely. Our results also show that the hybrid method performs better than the nearest neighbour method.

Accelerating feature-vector matching using multiple-tree and sub-vector methods

We propose two methods to accelerate the matching of an unknown object with known objects, all of which are expressed as feature vectors. The acceleration becomes necessary when the population of known objects is large and a great deal of time would be required to match all of them. Our proposed methods are multiple decision trees and sub-vector matching, both of which use a learning procedure to estimate the optimal values of certain parameters. Online matching with a combination of the two methods is then performed, whereby candidates are matched rapidly without sacrificing the test accuracy. The process is demonstrated by experiments in which we apply the proposed methods to handwriting recognition and language identification. The speed-up factor of our approach is dramatic compared with an alternative approach that eliminates candidates in a deterministic fashion.

Fast vector matching methods and their applications to handwriting recognition

A common practice in pattern recognition is to classify an unknown object by matching its feature vector with all the feature vectors stored in a database. When the number of class types and the set of stored entities are both large, it is essential to speed up the matching process. This can be achieved more effectively by eliminating unlikely candidates, rather than impossible candidates, from the process. We propose two methods for this purpose: one employs multiple trees, while the other employs a sub-vector matching technique. Both approaches use a learning procedure to estimate the optimal value of certain parameters. An online matching is then performed with a combination of the two methods, which matches candidates rapidly without sacrificing accuracy rates. The process is demonstrated by experiments in which we apply the proposed methods to handwriting recognition.

A Gain-Adjusted Fuzzy PI/PD Adaptive Controller Based on the Accumulated Genetic Algorithm

In this paper, a gain-adjusted fuzzy PI/PD (GFPIPD) adaptive controller is proposed. The proposed controller first constructs fuzzy rules for fuzzy PD/PI controller with the fixed weighting. Then the fuzzy rules, which self-learning their parameters for a desired condition, are learned through the accumulated GA. Finally, fuzzy gain-adjusted mechanism is further learned through the accumulated GA for the variations of a measured system dynamics. The proposed GFPIPD controller is tested by the high order systems with time delay and variable system dynamics. The experimental results illustrate the performance of the proposed method

A two-stage classification method for vector pattern matching problems

In this paper, we propose a new method to classify unknown objects into a large number of possible patterns (classes) and thereby solve vector-matching problems. The core of this method is a learning mechanism that reduces a huge amount of training samples into a highly condensed set of templates. When used in a testing process, these templates hold target patterns within the nearest K templates for almost all unknown objects, where K is a small number (2 or 3, for example). This learning mechanism also produces an extremely small set of confusing pairs, in opposition to all N(N-1)/2 possible pairs, where N is the total number of patterns. These pairs are further processed by a disambiguation procedure that improves the overall performance of the pattern classifier. This learning method thus suggests a two-stage online process for classifying unknown objects. The first stage reduces the number of possible candidates to a few candidates and the second stage identifies the target patterns out of these candidates.

Learning of fuzzy decision regions using genetic algorithm

A method for nonparametric learning of complex fuzzy decision regions in n-dimensional feature space is proposed. An n-dimensional fuzzy decision region is approximated by a union of hyperellipsoids. By explicitly parameterizing these hyperellipsoids, the decision region can be determined by estimating the parameters of each hyperellipsoid. The genetic algorithm is applied to estimate the parameters of each region component. With the global optimization ability of GA, the decision region to be learned can be arbitrarily complex including linearly inseparable, nonconvex and disconnected ones.