Tsang Ing Ren

META-DES

Dynamic ensemble selection systems work by estimating the level of competence of each classifier from a pool of classifiers. Only the most competent ones are selected to classify a given test sample. This is achieved by defining a criterion to measure the level of competence of a base classifier, such as, its accuracy in local regions of the feature space around the query instance. However, using only one criterion about the behavior of a base classifier is not sufficient to accurately estimate its level of competence. In this paper, we present a novel dynamic ensemble selection framework using meta-learning. We propose five distinct sets of meta-features, each one corresponding to a different criterion to measure the level of competence of a classifier for the classification of input samples. The meta-features are extracted from the training data and used to train a meta-classifier to predict whether or not a base classifier is competent enough to classify an input instance. During the generalization phase, the meta-features are extracted from the query instance and passed down as input to the meta-classifier. The meta-classifier estimates, whether a base classifier is competent enough to be added to the ensemble. Experiments are conducted over several small sample size classification problems, i.e., problems with a high degree of uncertainty due to the lack of training data. Experimental results show that the proposed meta-learning framework greatly improves classification accuracy when compared against current state-of-the-art dynamic ensemble selection techniques. HighlightsWe propose a novel dynamic ensemble selection framework using meta-learning.We present five sets of meta-features to measure the competence of a classifier.Results demonstrate the proposed framework outperforms current techniques.

Text Line Segmentation Based on Morphology and Histogram Projection

Text extraction is an important phase in document recognition systems. In order to segment text from a page document it is necessary to detect all the possible manuscript text regions. In this article we propose an efficient algorithm to segment handwritten text lines. The text line algorithm uses a morphological operator to obtain the features of the images. Following, a sequence of histogram projection and recovery is proposed to obtain the line segmented region of the text. First, an Y histogram projection is performed which results in the text lines positions. To divide the lines in different regions a threshold is applied. After that, another threshold is used to eliminate false lines. These procedures, however, cause some loss on the text line area. So, a recovery method is proposed to minimize this effect. In order to detect the extreme positions of the text in the horizontal direction, an X histogram projection is applied. Then, as in the Y direction, another threshold is used to eliminate false words. Finally, in order to optimize the area of the manuscript text line, a text selection is carried out. Experimental results using the IAM-database showed that this new approach is robust, fast and produces very good score rates.

A global-ranking local feature selection method for text categorization

In this paper, we propose a filtering method for feature selection called ALOFT (At Least One FeaTure). The proposed method focuses on specific characteristics of text categorization domain. Also, it ensures that every document in the training set is represented by at least one feature and the number of selected features is determined in a data-driven way. We compare the effectiveness of the proposed method with the Variable Ranking method using three text categorization benchmarks (Reuters-21578, 20 Newsgroup and WebKB), two different classifiers (k-Nearest Neighbor and Naive Bayes) and five feature evaluation functions. The experiments show that ALOFT obtains equivalent or better results than the classical Variable Ranking.

Data-driven global-ranking local feature selection methods for text categorization

Bag-of-words is the most used representation method in text categorization. It represents each document as a feature vector where each vector position represents a word. Since all words in the database are considered features, the feature vector can reach tens of thousands of features. Therefore, text categorization relies on feature selection to eliminate meaningless data and to reduce the execution time. In this paper, we propose two filtering methods for feature selection in text categorization, namely: Maximum f Features per Document (MFD), and Maximum f Features per Document – Reduced (MFDR). Both algorithms determine the number of selected features f in a data-driven way using a global-ranking Feature Evaluation Function (FEF). The MFD method analyzes all documents to ensure that each document in the training set is represented in the final feature vector. Whereas MFDR analyzes only the documents with high FEF valued features to select less features therefore avoiding unnecessary ones. The experimental study evaluated the effectiveness of the proposed methods on four text categorization databases (20 Newsgroup, Reuters, WebKB and TDT2) and three FEFs using the Naive Bayes classifier. The proposed methods present better or equivalent results when compared with the ALOFT method, in all cases, and Variable Ranking, in more than 93% of the cases.

An ensemble classifier for offline cursive character recognition using multiple feature extraction techniques

This paper presents a novel approach for cursive character recognition by using multiple feature extraction algorithms and a classifier ensemble. Several feature extraction techniques, using different approaches, are extracted and evaluated. Two techniques, Modified Edge Maps and Multi Zoning, are proposed. The former one presents the best overall result. Based on the results, a combination of the feature sets is proposed in order to achieve high recognition performance. This combination is motivated by the observation that the feature sets are both, independent and complementary. The ensemble is performed by combining the outputs generated by the classifier in each feature set separately. Both fixed and trained combination rules are evaluated using the C-Cube database. A trained combination scheme using a MLP network as combiner achieves the best results which is also the best results for the C-Cube database by a good margin.

Lateral Inhibition Pyramidal Neural Network for Image Classification

The human visual system is one of the most fascinating and complex mechanisms of the central nervous system that enables our capacity to see. It is through the visual system that we are able to accomplish from the most simple task such as object recognition to the most complex visual interpretation, understanding and perception. Inspired by this sophisticated system, two models based on the properties of the human visual system are proposed. These models are designed based on the concepts of receptive and inhibitory fields. The first model is a pyramidal neural network with lateral inhibition, called lateral inhibition pyramidal neural network. The second proposed model is a supervised image segmentation system, called segmentation and classification based on receptive fields. This work shows that the combination of these two models is beneficial, and the results obtained are better than that of other state-of-the-art methods.

A method for dynamic ensemble selection based on a filter and an adaptive distance to improve the quality of the regions of competence

Dynamic classifier selection systems aim to select a group of classifiers that is most adequate for a specific query pattern. This is done by defining a region around the query pattern and analyzing the competence of the classifiers in this region. However, the regions are often surrounded by noise which can difficult the classifier selection. This fact makes the performance of most dynamic selection systems no better than static selections. In this paper we demonstrate that the performance of dynamic selection systems end up limited by the quality of the regions extracted. Thereafter, we propose a new dynamic classifier selection system that improves the regions of competence in order to achieve higher recognition rates. Results obtained from several classification databased show the proposed method not only significantly increase the recognition performance, but also decreases the computational cost.

Weighted Modular Image Principal Component Analysis for face recognition

This paper proposes two feature extraction techniques that minimizes the effects of distortions generated by variations in illumination, rotation and, head pose in automatic face recognition systems. The proposed techniques are Modular IMage Principal Component Analysis (MIMPCA) and weighted Modular Image Principal Component Analysis (wMIMPCA). Both techniques are based on PCA and they use the modular image decomposition to minimize local variation. Also, the covariance matrix is calculated directly from the original image matrix. This strategy generates a smaller matrix compared with traditional PCA and reduces the computational effort. wMIMPCA assumes that parts of the face are more discriminatory than others, so a Genetic Algorithm is used to obtain weights for each region in the face image. The proposed techniques are compared with Modular PCA and two-dimensional PCA using three well-known databases, showing better results.

Financial time series prediction using exogenous series and combined neural networks

Time series forecasting have been a subject of interest in several different areas of research such as: meteorology, demography, health, computer and finance. Since it can be applied to various practical problems in real world, techniques to predict time series have been a topic of increasing research activities, especially in the financial sector that has a great interest in the forecast of the stock market. In this article, we are interested in the forecast of the time series related to the Brazilian oil company, Petrobras (PETR4). A methodology based on information obtained from exogenous series was used in combination with a neural network to predict the PETR4 stock series. Exogenous series were selected by analyzing the correlation between the series with the Petrobras stocks series. In this way, the prediction was obtained by not just using the previous values of the series but also by using information external to the PETR4 series. The values of the selected series were used as features for a prediction stage based on combined neural networks. To evaluate the performance of the system classical measurements were used, however we also introduce a new performance index called Sum of the Losses and Gains (SLG).

A fingerprint spoof detection based on MLP and SVM

We introduce a fingerprint spoof detection technique based on MLP and SVM that combines several features. The proposed technique is evaluated on two scenarios: (i) when an impostor can perform consecutive attempts to be considered authentic; and, (ii) when the system deals with fingerprints from elderly people. In order to analyze these scenarios, a database was developed. The results show that the proposed combination of features increases the system performance in at least 33.56% and that the average error increases as more attempts for acceptance are allowed. The SVM classifier presents better performance in almost all the tested configurations. However, MLP is more accurate with biometrics from elderly people.