International Journal of Pattern Recognition and Artificial Intelligence

In pattern recognition applications, with the aim of increasing efficiency, it is useful to represent the elements by attributed graphs (which consider their structural properties). Under this structural representation of the elements some graph matching problems need a common labeling between the vertices of a set of graphs. Computing this common labeling is a NP-Complete problem. Nevertheless, some methodologies have been presented which obtain a sub-optimal solution in polynomial time. The drawback of these methods is that they rely on pairwise labeling computations, causing the methodologies not to consider the global information during the entire process. To solve this problem, we present a methodology which generates the common labeling by matching all graph nodes to a virtual node set. The method has been tested using three independent datasets, one synthetic and two real. Experimental results show that the presented method obtains better performance than the most popular common labeling algorithm with the same computational cost.

Many machine learning algorithms require the features to be categorical. Hence, they require all numeric-valued data to be discretized into intervals. In this paper, we present a new discretization method based on the receiver operating characteristics (ROC) Curve (AUC) measure. Maximum area under ROC curve-based discretization (MAD) is a global, static and supervised discretization method. MAD uses the sorted order of the continuous values of a feature and discretizes the feature in such a way that the AUC based on that feature is to be maximized. The proposed method is compared with alternative discretization methods such as ChiMerge, Entropy-Minimum Description Length Principle (MDLP), Fixed Frequency Discretization (FFD), and Proportional Discretization (PD). FFD and PD have been recently proposed and are designed for Naïve Bayes learning. ChiMerge is a merging discretization method as the MAD method. Evaluations are performed in terms of M-Measure, an AUC-based metric for multi-class classification, and accuracy values obtained from Naïve Bayes and Aggregating One-Dependence Estimators (AODE) algorithms by using real-world datasets. Empirical results show that MAD is a strong candidate to be a good alternative to other discretization methods.

Feature ranking is a fundamental preprocess for feature selection, before performing any data mining task. Essentially, when there are too many features in the problem, dimensionality reduction through discarding weak features is highly desirable. In this paper, we have developed an efficient feature ranking algorithm for selecting the more relevant features prior to derivation of classification predictors. Regardless the ranking criteria which rely on the training error of a predictor based on a feature, our approach is distance-based, employing only the statistical distribution of classes in each feature. It uses a scoring function as ranking criterion to evaluate the correlation measure between each feature and the classes. This function comprises three measures for each class: the statistical between-class distance, the interclass overlapping measure, and an estimate of class impurity. In order to compute the statistical parameters, used in these measures, a normalized form of histogram, obtained for each class, is employed as its a priori probability density. Since the proposed algorithm examines each feature individually, it provides a fast and cost-effective method for feature ranking. We have tested the effectiveness of our approach on some benchmark data sets with high dimensions. For this purpose, some top-ranked features are selected and are used in some rule-based classifiers as the target data mining task. Comparing with some popular feature ranking methods, the experimental results show that our approach has better performance as it can identify the more relevant features eventuate to lower classification error.

Detection of double compression in digital multimedia is considered to reveal the history of multimedia signal processing, which is very useful in digital forensics. In this paper, distributions of quantized DCT coefficients are analyzed in depth after double MPEG-2 compression with constant bit rate (CBR) mode, and a new algorithm is presented to detect double MPEG-2 compression based on convex patterns in the distribution of quantized DCT coefficients. In order to demonstrate the practical value of our proposed algorithm, two digital video cameras (DV) and two MPEG-2 software coders are utilized to simulate the general process of double MPEG-2 compression. Experiment results show that the proposed scheme can effectively detect doubly MPEG-2 compressed videos with CBR mode and the target output bit rate can vary in a large range.

In this paper, we propose a novel automatic image annotation model by mining the web. In our approach, the terms or words appearing in the associated text are extracted and filtered as labels or annotations for the corresponding web images. Sure, much noise exists in those selected labels. In order to reduce the influence caused by the noisy labels, for each label or potential word, we improve web image-word relationships using Mixture Gaussian Distribution Model. By doing so, the relationships between words and images are re-weighted both in terms of sematic relevance and in terms of visual feature similarity. In fact, all the words associated to an image are not semantically independent. We use co-occurrences between two words to describe their semantic relevance. Thus, we further use a method, called Word Promotion, to co-enhance the weights of all the words associated to a given image based on their co-occurrences. Our experiments are conducted in several ways and the results show that our annotation method can achieve a satisfactory performance in respects of system scalability and sematic evolution.

In this paper, we propose an efficient active contour model for multiphase image segmentation in a variational level set formulation. By incorporating the globally convex segmentation idea and the split Bregman method into the multiphase formulation of the local and global intensity fitting energy model, our new model improved the original local and global intensity fitting energy model in the following aspects. First, we propose a new energy functional using the globally convex segmentation method to guarantee fast convergence. Second, we incorporate information from the edge into the energy functional by using a non-negative edge detector function to detect boundaries more easily. Third, instead of a constant value to control the influence of the local and global intensity fitting terms, we use a weight function varying with the locations of the image to balance the weights between the local and the global fitting terms dynamically. Lastly, the special structure of our energy functional enables us to apply the split Bregman method to minimize the energy much more efficiently. We have applied our model to synthetic images and real brain MR images with promising results. Experimental results demonstrate the efficiency and superiority of our model.

Iris recognition is one of the most reliable personal identification methods. This paper presents a novel algorithm for iris recognition encompassing iris segmentation, fusion of statistical and co-occurrence features extracted from the curvelet and ridgelet transformed images. In this work, the pupil and iris boundaries are detected by using the equation of circle from three points on its circumference. Using Canny edge detection, the iris radius value is empirically chosen based on rigorous experimentation. Eyelash removal is done by using a horizontal 1-D rank filter. Iris normalization is done by mapping the detected iris region from the polar domain to the rectangular domain and the multi-resolution transforms such as curvelet and ridgelet transforms are applied for multi-resolutional feature extraction. The classification is done using Manhattan distance (M_d) and multiclass classifier with logistic function and the two results are compared. Here, the benchmark database CASIA-IRIS-V3 (Interval) is used for identification and recognition. It is observed that the ridgelet transform increases the iris recognition rate.

Local binary pattern (LBP) operator offers an efficient way to recognize face under varying illumination, while it has the drawback of abandoning some important texture features. Local multiple patterns (LMP) has alleviated the problem by a hierarchical model. However, the LMP method can bring out the rapid expansion of feature dimension, so a special feature encoding method is adopted by this paper. Meanwhile, we find that the LMP features of different layers can be used to recognize face independently so that it would preserve more abundant recognition information. Most importantly, the contribution of the LMP features from different layers is blurry under varying illumination. We propose a fuzzy framework to fuse the recognition result of different layers and use adaptive weights to calculate contribution rates of different layers under varying illumination. Experimental results demonstrate that the proposed method outperforms other state-of-the-art methods on four databases such as Yale B, Extended Yale B, CMU PIE and Outdoor.

The processing of blood vessels is an indispensable part in complicated surgeries of livers and hearts as the development of medical image technologies, which requires an automatic segmentation system over CT images of organs. However, the vascular pattern of livers in CT images suffers from low contrast to background so that the existing segmentation technologies are not able to extract the blood vessels completely. In the paper, we propose a new algorithm to extract the blood vessels of livers based on the adaptive multi-scale segmentation. First, we prove that the background histogram of normal scale blood vessels obeys the Gaussian distribution in CT images, and obtain the vascular distribution function from the vascular signal segmented from the background with a local optimal threshold. Second, Hessian matrix is employed to enhance the thin blood vessels before the extraction, and a complete and clear segmentation system for blood vessels is constructed by combining the major and thin blood vessels via filtering. Experimental results show the effectiveness of the proposed method, which is able to extract more complete blood vessels for 3D system, and assist the clinical liver surgeries efficiently.

This paper describes the sequence of construction of a cell nuclei classification model by the analysis, the characterization and the classification of shape and texture. We describe first the elaboration of dedicated shape indexes and second the construction of the associated classification submodel. Then we present a new method of texture characterization, based on the construction and the analysis of statistical matrices encoding the texture. The various characterization techniques developed in this paper are systematically compared to previous approaches. In particular, we paid special attention to the results obtained by a versatile classification method using a large range of descriptors dedicated to the characterization of shapes and textures. Finally, the last classifier built with our methods achieved 88% of classification out of the 94% possible.