Showing papers in "International Journal of Pattern Recognition and Artificial Intelligence in 2005"
TL;DR: An image clustering method that is based on the particle swarm optimizer (PSO) that is applied to synthetic, MRI and satellite images and shows that the PSO image classifier performs better than state-of-the-art image classifiers in all measured criteria.
Abstract: An image clustering method that is based on the particle swarm optimizer (PSO) is developed in this paper. The algorithm finds the centroids of a user specified number of clusters, where each cluster groups together with similar image primitives. To illustrate its wide applicability, the proposed image classifier has been applied to synthetic, MRI and satellite images. Experimental results show that the PSO image classifier performs better than state-of-the-art image classifiers (namely, K-means, Fuzzy C-means, K-Harmonic means and Genetic Algorithms) in all measured criteria. The influence of different values of PSO control parameters on performance is also illustrated.
283 citations
TL;DR: This paper designs a dependence distribution-based algorithm by extending the ChowLiu algorithm, a widely used CI based algorithm, and presents and proves a sufficient condition for the optimality of Naive Bayes, in which the dependences among attributes exist.
Abstract: Naive Bayes is one of the most efficient and effective inductive learning algorithms for machine learning and data mining. Its competitive performance in classification is surprising, because the conditional independence assumption on which it is based is rarely true in real-world applications. An open question is: what is the true reason for the surprisingly good performance of Naive Bayes in classification? In this paper, we propose a novel explanation for the good classification performance of Naive Bayes. We show that, essentially, dependence distribution plays a crucial role. Here dependence distribution means how the local dependence of an attribute distributes in each class, evenly or unevenly, and how the local dependences of all attributes work together, consistently (supporting a certain classification) or inconsistently (canceling each other out). Specifically, we show that no matter how strong the dependences among attributes are, Naive Bayes can still be optimal if the dependences distribute evenly in classes, or if the dependences cancel each other out. We propose and prove a sufficient and necessary condition for the optimality of Naive Bayes. Further, we investigate the optimality of Naive Bayes under the Gaussian distribution. We present and prove a sufficient condition for the optimality of Naive Bayes, in which the dependences among attributes exist. This provides evidence that dependences may cancel each other out. Our theoretic analysis can be used in designing learning algorithms. In fact, a major class of learning algorithms for Bayesian networks are conditional independence-based (or CI-based), which are essentially based on dependence. We design a dependence distribution-based algorithm by extending the ChowLiu algorithm, a widely used CI based algorithm. Our experiments show that the new algorithm outperforms the ChowLiu algorithm, which also provides empirical evidence to support our new explanation.
209 citations
TL;DR: Assessment of the performance of content-based face image retrieval in different color spaces using a standard algorithm, the Principal Component Analysis (PCA), which has become a popular algorithm in the face recognition community finds that some color configurations help improve face retrieval performance.
Abstract: Content-based face image retrieval is concerned with computer retrieval of face images (of a given subject) based on the geometric or statistical features automatically derived from these images. It is well known that color spaces provide powerful information for image indexing and retrieval by means of color invariants, color histogram, color texture, etc. This paper assesses comparatively the performance of content-based face image retrieval in different color spaces using a standard algorithm, the Principal Component Analysis (PCA), which has become a popular algorithm in the face recognition community. In particular, we comparatively assess 12 color spaces (RGB, HSV, YUV, YCbCr, XYZ, YIQ, L*a*b*, U*V*W*, L*u*v*, I1I2I3, HSI, and rgb) by evaluating seven color configurations for every single color space. A color configuration is defined by an individual or a combination of color component images. Take the RGB color space as an example, possible color configurations are R, G, B, RG, RB, GB and RGB. Experimental results using 600 FERET color images corresponding to 200 subjects and 456 FRGC (Face Recognition Grand Challenge) color images of 152 subjects show that some color configurations, such as YV in the YUV color space and YI in the YIQ color space, help improve face retrieval performance.
133 citations
TL;DR: A framework of face recognition by adding NMF constraint and classifier constraints to matrix factorization to get both intuitive features and good recognition results is proposed and two novel subspace methods are presented.
Abstract: Non-negative Matrix Factorization (NMF) is a part-based image representation method which adds a non-negativity constraint to matrix factorization. NMF is compatible with the intuitive notion of combining parts to form a whole face. In this paper, we propose a framework of face recognition by adding NMF constraint and classifier constraints to matrix factorization to get both intuitive features and good recognition results. Based on the framework, we present two novel subspace methods: Fisher Non-negative Matrix Factorization (FNMF) and PCA Non-negative Matrix Factorization (PNMF). FNMF adds both the non-negative constraint and the Fisher constraint to matrix factorization. The Fisher constraint maximizes the between-class scatter and minimizes the within-class scatter of face samples. Subsequently, FNMF improves the capability of face recognition. PNMF adds the non-negative constraint and characteristics of PCA, such as maximizing the variance of output coordinates, orthogonal bases, etc. to matrix factorization. Therefore, we can get intuitive features and desirable PCA characteristics. Our experiments show that FNMF and PNMF achieve better face recognition performance than NMF and Local NMF.
98 citations
TL;DR: This work proposes a new decision tree induction method called linear discriminant trees (LDT) which uses the best combination of these criteria in terms of accuracy, simplicity and learning time and learns fast, are accurate, and the trees generated are small.
Abstract: We discuss and test empirically the effects of six dimensions along which existing decision tree induction algorithms differ. These are: Node type (univariate versus multivariate), branching factor (two or more), grouping of classes into two if the tree is binary, error (impurity) measure, and the methods for minimization to find the best split vector and threshold. We then propose a new decision tree induction method that we name linear discriminant trees (LDT) which uses the best combination of these criteria in terms of accuracy, simplicity and learning time. This tree induction method can be univariate or multivariate. The method has a supervised outer optimization layer for converting a K > 2-class problem into a sequence of two-class problems and each two-class problem is solved analytically using Fisher's Linear Discriminant Analysis (LDA). On twenty datasets from the UCI repository, we compare the linear discriminant trees with the univariate decision tree methods C4.5 and C5.0, multivariate decision tree methods CART, OC1, QUEST, neural trees and LMDT. Our proposed linear discriminant trees learn fast, are accurate, and the trees generated are small.
64 citations
TL;DR: An algorithm to reduce the training sample size while preserving the original decision boundaries as much as possible is introduced, which tends to obtain classification accuracy close to that of the whole training sample.
Abstract: The excessive computational resources required by the Nearest Neighbor rule are a major concern for a number of specialists and practitioners in the Pattern Recognition community. Many proposals for decreasing this computational burden, through reduction of the training sample size, have been published. This paper introduces an algorithm to reduce the training sample size while preserving the original decision boundaries as much as possible. Consequently, the algorithm tends to obtain classification accuracy close to that of the whole training sample. Several experimental results demonstrate the effectiveness of this method when compared to other reduction algorithms based on similar ideas.
60 citations
TL;DR: This paper derives an approximate EM-like method for selecting the most likely structure of DBN and learning model parameters, and proposes a method for human indoor tracking based on a Dynamic Bayes Network as a probabilistic model for the observations.
Abstract: Visual surveillance in wide areas (e.g. airports) relies on sparsely distributed cameras, that is, cameras that observe nonoverlapping scenes. In this setup, multiobject tracking requires reidentification of an object when it leaves one field of view, and later appears at some other. Although similar association problems are common for multiobject tracking scenarios, in the distributed case one has to cope with asynchronous observations and cannot assume smooth motion of the objects. In this paper, we propose a method for human indoor tracking. The method is based on a Dynamic Bayes Network (DBN) as a probabilistic model for the observations. The edges of the network define the correspondences between observations of the same object. Accordingly, we derive an approximate EM-like method for selecting the most likely structure of DBN and learning model parameters. The presented algorithm is tested on a collection of real-world observations gathered by a system of cameras in an office building.
41 citations
TL;DR: This paper presents work that uses Transductive Latent Semantic Indexing (LSI) for text classification and improves classification accuracy by incorporating the set of test examples in the classification process by using an expanded term-by-document matrix.
Abstract: This paper presents work that uses Transductive Latent Semantic Indexing (LSI) for text classification. In addition to relying on labeled training data, we improve classification accuracy by incorporating the set of test examples in the classification process. Rather than performing LSI's singular value decomposition (SVD) process solely on the training data, we instead use an expanded term-by-document matrix that includes both the labeled data as well as any available test examples. We report the performance of LSI on data sets both with and without the inclusion of the test examples, and we show that tailoring the SVD process to the test examples can be even more useful than adding additional training data. This method can be especially useful to combat possible inclusion of unrelated data in the original corpus, and to compensate for limited amounts of data. Additionally, we evaluate the vocabulary of the training and test sets and present the results of a series of experiments to illustrate how the test set is used in an advantageous way.
41 citations
TL;DR: An illumination normalization approach by relighting face images to a canonical illumination based on the harmonic images model is presented, showing that the proposed relighting normalization can significantly improve the performance of a face recognition system when the probes are collected under varying lighting conditions.
Abstract: The performances of the current face recognition systems suffer heavily from the variations in lighting. To deal with this problem, this paper presents an illumination normalization approach by relighting face images to a canonical illumination based on the harmonic images model. Benefiting from the observations that human faces share similar shape, and the albedos of the face surfaces are quasi-constant, we first estimate the nine low-frequency components of the illumination from the input facial image. The facial image is then normalized to the canonical illumination by re-rendering it using the illumination ratio image technique. For the purpose of face recognition, two kinds of canonical illuminations, the uniform illumination and a frontal flash with the ambient lights, are considered, among which the former encodes merely the texture information, while the latter encodes both the texture and shading information. Our experiments on the CMU-PIE face database and the Yale B face database have shown that the proposed relighting normalization can significantly improve the performance of a face recognition system when the probes are collected under varying lighting conditions.
32 citations
TL;DR: This work proposes a class of enhancement techniques suitable for scenes captured by fixed cameras that ensures the fidelity of important features and robustly incorporates background contexts, while avoiding traditional problems such as aliasing, ghosting and haloing.
Abstract: We propose a class of enhancement techniques suitable for scenes captured by fixed cameras. The basic idea is to increase the information density in a set of low quality images by extracting the context from a higher-quality image captured under different illuminations from the same viewpoint. For example, a night-time surveillance video can be enriched with information available in daytime images. We also propose a new image fusion approach to combine images with sufficiently different appearance into a seamless rendering. Our method ensures the fidelity of important features and robustly incorporates background contexts, while avoiding traditional problems such as aliasing, ghosting and haloing. We show results on indoor as well as outdoor scenes.
30 citations
TL;DR: A novel version of regression SVM (Support Vector Machines) that is based on the least-squares error is described, and it is shown that the solution of this optimization problem can be obtained easer than expected.
Abstract: This paper describes a novel version of regression SVM (Support Vector Machines) that is based on the least-squares error. We show that the solution of this optimization problem can be obtained eas...
TL;DR: A new regularization technique to deal with the small sample size (S3) problem in linear discriminant analysis (LDA) based face recognition and develops a one-parameter regularization on the within-class scatter matrix, which is suitable for parameter reduction.
Abstract: This paper presents a new regularization technique to deal with the small sample size (S3) problem in linear discriminant analysis (LDA) based face recognition. Regularization on the within-class scatter matrix Sw has been shown to be a good direction for solving the S3 problem because the solution is found in full space instead of a subspace. The main limitation in regularization is that a very high computation is required to determine the optimal parameters. In view of this limitation, this paper re-defines the three-parameter regularization on the within-class scatter matrix , which is suitable for parameter reduction. Based on the new definition of , we derive a single parameter (t) explicit expression formula for determining the three parameters and develop a one-parameter regularization on the within-class scatter matrix. A simple and efficient method is developed to determine the value of t. It is also proven that the new regularized within-class scatter matrix approaches the original within-class scatter matrix Sw as the single parameter tends to zero. A novel one-parameter regularization linear discriminant analysis (1PRLDA) algorithm is then developed. The proposed 1PRLDA method for face recognition has been evaluated with two public available databases, namely ORL and FERET databases. The average recognition accuracies of 50 runs for ORL and FERET databases are 96.65% and 94.00%, respectively. Comparing with existing LDA-based methods in solving the S3 problem, the proposed 1PRLDA method gives the best performance.
TL;DR: This paper considers hexagonal arrays on triangular grids and introduces hexagonal local picture languages and hexagonal tiling systems defining hexagonal recognizable picture languages, and proves that recognizable hexagonal picture languages are characterized as projections of xyz-local picture languages.
Abstract: In this paper we consider hexagonal arrays on triangular grids and introduce hexagonal local picture languages and hexagonal tiling systems defining hexagonal recognizable picture languages, motivated by an analogous study of rectangular arrays by Giammarresi and Restivo. We also introduce hexagonal Wang tiles to define hexagonal Wang systems (HWS) as a formalism to describe hexagonal picture languages. It is noticed that the family of hexagonal picture languages defined by hexagonal Wang systems and the family recognized by hexagonal tiling systems coincide. Analogous to hv-domino systems describing rectangular arrays, we define xyz-domino systems and prove that recognizable hexagonal picture languages are characterized as projections of xyz-local picture languages.
TL;DR: This article describes some of the important currently used methods for solving classification problems, focusing on feature selection and extraction as parts of the overall classification task, and proposes that the next major step is the elaboration of a theory of how the methods ofselection and extraction interact during the classification process for particular problem domains.
Abstract: In this article, we describe some of the important currently used methods for solving classification problems, focusing on feature selection and extraction as parts of the overall classification task. We then go on to discuss likely future directions for research in this area, in the context of the other articles from this special issue. We propose that the next major step is the elaboration of a theory of how the methods of selection and extraction interact during the classification process for particular problem domains, along with any learning that may be part of the algorithms. Preferably this theory should be tested on a set of well-established benchmark challenge problems. Using this theory, we will be better able to identify the specific combinations that will achieve best classification performance for new tasks.
TL;DR: This work develops an efficient technique to transform a multiclass recognition problem into a minimal binary classification problem using the Minimal Classification Method (MCM), which requires only log2 N classifications whereas the other methods require much more.
Abstract: In this work, we develop an efficient technique to transform a multiclass recognition problem into a minimal binary classification problem using the Minimal Classification Method (MCM). The MCM requires only log2 N classifications whereas the other methods require much more. For the classification, we use Support Vector Machine (SVM) based binary classifiers since they have superior generalization performance. Unlike the prevalent one-versus-one strategy (the bottom-up one-versus-one strategy is called tournament method) that separates only two classes at each classification, the binary classifiers in our method have to separate two groups of multiple classes. As a result, the probability of generalization error increases. This problem is alleviated by utilizing error correcting codes, which results only in a marginal increase in the required number of classifications. However, in comparison to the tournament method, our method requires only 50% of the classifications and still similar performance can be attained. The proposed solution is tested with the Columbia Object Image Library (COIL). We also test the performance under conditions of noise and occlusion.
TL;DR: A new framework is presented that adapts the SVM with neural networks and analyzes the source of misclassification in guiding the authors' preprocessing for optimization in multiclass classification.
Abstract: The support vector machine (SVM) has recently attracted growing interest in pattern classification due to its competitive performance. It was originally designed for two-class classification, and many researchers have been working on extensions to multiclass. In this paper, we present a new framework that adapts the SVM with neural networks and analyze the source of misclassification in guiding our preprocessing for optimization in multiclass classification. We perform experiments on the ORL database and the results show that our framework can achieve high recognition rates.
TL;DR: The conjugate and natural gradient rules to efficiently implement the maximization of the harmony function, i.e. the BYY harmony learning, on Gaussian mixture are proposed and demonstrated to work well and converge more quickly than the general gradient ones.
Abstract: Under the Bayesian Ying–Yang (BYY) harmony learning theory, a harmony function has been developed on a BI-directional architecture of the BYY system for Gaussian mixture with an important feature that, via its maximization through a general gradient rule, a model selection can be made automatically during parameter learning on a set of sample data from a Gaussian mixture. This paper further proposes the conjugate and natural gradient rules to efficiently implement the maximization of the harmony function, i.e. the BYY harmony learning, on Gaussian mixture. It is demonstrated by simulation experiments that these two new gradient rules not only work well, but also converge more quickly than the general gradient ones.
TL;DR: The experimental results on synthetic and real EEG time-series show that substantially improved classification accuracy can be achieved by semi-supervised classification algorithms, based on hidden Markov models, to classify sequences.
Abstract: Using unlabeled data to help supervised learning has become an increasingly attractive methodology and proven to be effective in many applications. This paper applies semi-supervised classification algorithms, based on hidden Markov models, to classify sequences. For model-based classification, semi-supervised learning amounts to using both labeled and unlabeled data to train model parameters. We examine three different strategies of using labeled and unlabeled data in the model training process. These strategies differ in how and when labeled and unlabeled data contribute to the model training process. We also compare regular semi-supervised learning, where there are separate unlabeled training data and unlabeled test data, with transductive learning where we do not differentiate between unlabeled training data and unlabeled test data. Our experimental results on synthetic and real EEG time-series show that substantially improved classification accuracy can be achieved by these semi-supervised learning strategies. The effect of model complexity on semi-supervised learning is also studied in our experiments.
TL;DR: This paper introduced a novel method that focuses on segmenting the brain MR Image that is important for neural diseases by modifying the objective function by compensating its immediate neighborhood effect using Gaussian smooth method for decreasing the influence of the inhomogeneity and increasing the segmenting accuracy.
Abstract: The accurate and effective algorithm for segmenting image is very useful in many fields, especially in medical images. In this paper we introduced a novel method that focuses on segmenting the brain MR Image that is important for neural diseases. Because of many noises embedded in the acquiring procedure, such as eddy currents, susceptibility artifacts, rigid body motion and intensity inhomogeneity, segmenting the brain MR image is a difficult work. In this algorithm, we overcame the inhomogeneity shortage, by modifying the objective function by compensating its immediate neighborhood effect using Gaussian smooth method for decreasing the influence of the inhomogeneity and increasing the segmenting accuracy. Using simulate image and clinical MRI data, experiments show that our proposed algorithm is effective.
TL;DR: It is shown that a network trained with an original data set and one trained with a linear transformation of the original data will go through the same training dynamics, as long as they start from equivalent states.
Abstract: In the neural network literature, many preprocessing techniques, such as feature de-correlation, input unbiasing and normalization, are suggested to accelerate multilayer perceptron training. In this paper, we show that a network trained with an original data set and one trained with a linear transformation of the original data will go through the same training dynamics, as long as they start from equivalent states. Thus preprocessing techniques may not be helpful and are merely equivalent to using a different weight set to initialize the network. Theoretical analyses of such preprocessing approaches are given for conjugate gradient, back propagation and the Newton method. In addition, an efficient Newton-like training algorithm is proposed for hidden layer training. Experiments on various data sets confirm the theoretical analyses and verify the improvement of the new algorithm.
TL;DR: A novel wavelet domain HMM using blocks to strike a delicate balance between improving spatial adaptability of contextual HMM (CHMM) and modeling a more reliable HMM is proposed.
Abstract: This paper presents a new framework for signal denoising based on wavelet-domain hidden Markov models (HMMs). The new framework enables us to concisely model the statistical dependencies and non-Gaussian statistics encountered in real-world signals, and enables us to get a more reliable and local model using blocks. Wavelet-domain HMMs are designed with the intrinsic properties of wavelet transform and provide powerful yet tractable probabilistic signal models. In this paper, we propose a novel wavelet domain HMM using blocks to strike a delicate balance between improving spatial adaptability of contextual HMM (CHMM) and modeling a more reliable HMM. Each wavelet coefficient is modeled as a Gaussian mixture model, and the dependencies among wavelet coefficients in each subband are described by a context structure, then the structure is modified by blocks which are connected areas in a scale conditioned on the same context. Before denoising a signal, efficient Expectation Maximization (EM) algorithms are developed for fitting the HMMs to observational signal data. Parameters of trained HMM are used to modify wavelet coefficients according to the rule of minimizing the mean squared error (MSE) of the signal. Then, reverse wavelet transformation is utilized to modified wavelet coefficients. Finally, experimental results are given. The results show that block hidden Markov model (BHMM) is a powerful yet simple tool in signal denoising.
TL;DR: The adaptive compensation-curve scheme is proposed to compensate and enhance the brightness of backlight images, and the experimental and comparison results clearly show the superiority of the proposed technique.
Abstract: This paper presents a new algorithm for detection and compensation of backlight images. The proposed technique attacks the weakness of the conventional backlight image processing methods such as over-saturation, losing contrast and so on. The proposed algorithm consists of two operation phases: detection and compensation phases. In the detection phase, we use the spatial position characteristic and histogram of backlight image to obtain two image indices, which can determine the backlight degree of an image. Fuzzy logic is then used to integrate these two indices into a final backlight index determining the final backlight degree of an image precisely. Second, in the compensation phase, to solve the over-saturation problem that exists usually in conventional image compensation methods, we propose the adaptive compensation-curve scheme to compensate and enhance the brightness of backlight images. The luminance of a backlight image is adjusted according to the compensation curve, which is adapted dynamically according to the backlight degree indicated by the backlight index estimated in the detection phase. The performance of the proposed technique is tested on 100 backlight images covering various kinds of backlight conditions and degrees. The experimental and comparison results clearly show the superiority of the proposed technique.
TL;DR: A novel subspace approach in determining the optimal projection is developed that effectively solves the small sample size problem and eliminates the possibility of losing discriminative information.
Abstract: Fisher Linear Discriminant Analysis (LDA) has been successfully used as a data discriminantion technique for face recognition. This paper has developed a novel subspace approach in determining the optimal projection. This algorithm effectively solves the small sample size problem and eliminates the possibility of losing discriminative information. Through the theoretical derivation, we compared our method with the typical PCA-based LDA methods, and also showed the relationship between our new method and perturbation-based method. The feasibility of the new algorithm has been demonstrated by comprehensive evaluation and comparison experiments with existing LDA-based methods.
TL;DR: A novel approach to image texture classification, which involves a model of artificial organisms i.e. Artificial Crawlers (ACrawlers) and a series of evolution curves representing the features of the texture, and the feasibility and effectiveness of the proposed method have been demonstrated.
Abstract: This paper presents a novel approach to image texture classification, which involves a model of artificial organisms i.e. Artificial Crawlers (ACrawlers) and a series of evolution curves representing the features of the texture. The distributed ACrawlers locally interact with their living environment, i.e. textured regions, and each ACrawler acts according to a set of homogenous rules for isotropic motion, energy absorption and colony formation, etc. The ACrawlers evolve through natural selection, which produces the specific curves of agent evolution, habitant settlement and colony formation as well as the scale distribution of all colonies. The feasibility and effectiveness of the proposed method have been demonstrated by experiments.
TL;DR: This three-stage hybrid post-processing system reduces the misclassification and rejection rates common in the single character recognition phase and improves absolute recognition rates by 12%.
Abstract: This paper presents a post-processing system for improving the recognition rate of a Handwritten Chinese Character Recognition (HCCR) device. This three-stage hybrid post-processing system reduces the misclassification and rejection rates common in the single character recognition phase. The proposed system is novel in two respects: first, it reduces the misclassification rate by applying a dictionary-look-up strategy that bind the candidate characters into a word-lattice and appends the linguistic-prone characters into the candidate set; second, it identifies promising sentences by employing a distant Chinese word BI-Gram model with a maximum distance of three to select plausible words from the word-lattice. These sentences are then output as the upgraded result. Compared with one of our previous works in single Chinese character recognition, the proposed system improves absolute recognition rates by 12%.
TL;DR: This paper presents a novel approach to machine learning that automates the very labor-intensive and therefore time-heavy and expensive process of manually cataloging and cataloging business data for personalized recommendation.
Abstract: Personalized recommendation needs powerful Web Intelligence (WI) technologies to manage, analyze and employ various business data on the Web for e-business intelligence. This paper presents a novel...
TL;DR: A new statistical method to reconstruct the writing order of a handwritten signature from a two-dimensional static image is presented, which shows that about one-eighth of the reconstructed writing sequences are the same as the actual writing sequences.
Abstract: Online features have been proven to be more robust information for handwriting recognition than an offline static image due to dynamic aspects, such as the writing sequence of strokes. The estimation of temporal information from a static image becomes an important issue. This paper presents a new statistical method to reconstruct the writing order of a handwritten signature from a two-dimensional static image. The reconstruction process consists of two phases, namely the training phase and the testing phase. In the training phase, the writing order with other attributes, such as length and direction, are extracted and analyzed from a set of training online handwritten signatures. A Universal Writing Model (UWM), which consists of a set of distribution functions, is then constructed. In the testing phase, the UWM is applied to reconstruct the writing order of an offline signature. 300 offline signatures with ground truth are used for evaluation. Experimental results show that about one-eighth of the reconstructed writing sequences are the same as the actual writing sequences.
TL;DR: A novel, fast algorithm for accurate detection of the shape of targets around a mobile robot using a single rotating sonar element that can be used during the period when the robot stays in a fixed position.
Abstract: This paper presents a novel, fast algorithm for accurate detection of the shape of targets around a mobile robot using a single rotating sonar element. The rotating sonar yields an image built up by the reflections of an ultrasonic beam directed at different scan angles. The image is then interpreted with an image-understanding approach based on texture analysis. Several important tasks are performed in this way, such as noise removal, echo correction and restoration. All these processes are obtained by estimating and restoring the degree of texture continuity. Texture analysis, in fact, allows us to look at the image on a large scale thus giving the possibility to infer the overall behavior of the reflection process. The algorithm has been integrated in a mobile robot. However, the algorithm is not suitable for working during the mobile robot movement, rather it can be used during the period when the robot stays in a fixed position.
TL;DR: This paper demonstrates a novel method of combining multiple classifiers to address the task of recognizing handwritten Chinese characters, using the conventional approach that is based on the Bayesian principle and the improved weighted combination, employing shared and distinct representations.
Abstract: Combining multiple classifiers is a new method that achieves a substantial gain in performance in many areas of pattern recognition. This paper demonstrates a novel method (based on statistics) of combining multiple classifiers to address the task of recognizing handwritten Chinese characters. Fusion strategies are discussed to provide a basis for the architecture of the combined classifiers. The weights of these fusion strategies are assigned via a genetic algorithm (GA). These fusion strategies are then tested using our online system for handwritten Chinese character recognition. In addition, different combinatory approaches are tested for comparison purposes. These include the conventional approach that is based on the Bayesian principle and the improved weighted combination, employing shared and distinct representations. Our experimental results demonstrate the effectiveness of these combinatory approaches.
TL;DR: This paper introduces a novel concept, called DoN (Degree of Nonrigidity), and develops an approach for estimating the approximate average shape and motion of the object, which reasonably solves the ambiguity problem in nonrigid recovery.
Abstract: With a monocular view, the nonrigid recovery of 3D motion and time-varying shapes of a deforming object may be impossible without any prior information, because ambiguous, multiple solutions exist for motion and shapes which produce the same projection image. In this paper, as a preceding step to the nonrigid recovery of a deforming object, we develop an approach for estimating the approximate average shape and motion of the object. This reasonably solves the ambiguity problem in nonrigid recovery. By investigating the internal structures of nonrigid objects, we introduce a novel concept, called DoN (Degree of Nonrigidity). Based on this, we propose an iterative certainty reweighted factorization method. In addition, we refine and improve the method by reformulating it in a robust manner to cope with outliers existing in the tracked features. Finally, we present some experimental results on both synthetic data and a real video sequence.