Efficient distance-based per-pixel texture classification with Gabor wavelet filters

This paper proposes an efficient solution to the problem of per-pixel classification of textured images with multichannel Gabor wavelet filters based on a selection scheme that automatically determines a subset of prototypes that characterize each texture class. Results with Brodatz compositions and outdoor images, and comparisons with alternative classification techniques are presented.     

Learning prototypes and distances: A prototype reduction technique based on nearest neighbor error minimization

A prototype reduction algorithm is proposed, which simultaneously trains both a reduced set of prototypes and a suitable local metric for these prototypes. Starting with an initial selection of a small number of prototypes, it iteratively adjusts both the position (features) of these prototypes and the corresponding local-metric weights. The resulting prototypes/metric combination minimizes a suitable estimation of the classification error probability. Good performance of this algorithm is assessed through experiments with a number of benchmark data sets and with a real task consisting in the verification of images of human faces.     

A training sample sequence planning method for pattern recognition problems

In solving pattern recognition problems, many classification methods, such as the nearest-neighbor (NN) rule, need to determine prototypes from a training set. To improve the performance of these classifiers in finding an efficient set of prototypes, this paper introduces a training sample sequence planning method. In particular, by estimating the relative nearness of the training samples to the decision boundary, the approach proposed here incrementally increases the number of prototypes until the desired classification accuracy has been reached. This approach has been tested with a NN classification method and a neural network training approach. Studies based on both artificial and real data demonstrate that higher classification accuracy can be achieved with fewer prototypes.     

Self-generating prototypes for pattern classification

Prototype classifiers are a type of pattern classifiers, whereby a number of prototypes are designed for each class so as they act as representatives of the patterns of the class. Prototype classifiers are considered among the simplest and best performers in classification problems. However, they need careful positioning of prototypes to capture the distribution of each class region and/or to define the class boundaries. Standard methods, such as learning vector quantization (LVQ), are sensitive to the initial choice of the number and the locations of the prototypes and the learning rate. In this article, a new prototype classification method is proposed, namely self-generating prototypes (SGP). The main advantage of this method is that both the number of prototypes and their locations are learned from the training set without much human intervention. The proposed method is compared with other prototype classifiers such as LVQ, self-generating neural tree (SGNT) and K-nearest neighbor (K-NN) as well as Gaussian mixture model (GMM) classifiers. In our experiments, SGP achieved the best performance in many measures of performance, such as training speed, and test or classification speed. Concerning number of prototypes, and test classification accuracy, it was considerably better than the other methods, but about equal on average to the GMM classifiers. We also implemented the SGP method on the well-known STATLOG benchmark, and it beat all other 21 methods (prototype methods and non-prototype methods) in classification accuracy.     

Being bored? Recognising natural interest by extensive audiovisual integration for real-life application

Automatic detection of the level of human interest is of high relevance for many technical applications, such as automatic customer care or tutoring systems. However, the recognition of spontaneous interest in natural conversations independently of the subject remains a challenge. Identification of human affective states relying on single modalities only is often impossible, even for humans, since different modalities contain partially disjunctive cues. Multimodal approaches to human affect recognition generally are shown to boost recognition performance, yet are evaluated in restrictive laboratory settings only. Herein we introduce a fully automatic processing combination of Active–Appearance–Model-based facial expression, vision-based eye-activity estimation, acoustic features, linguistic analysis, non-linguistic vocalisations, and temporal context information in an early feature fusion process. We provide detailed subject-independent results for classification and regression of the Level of Interest using Support-Vector Machines on an audiovisual interest corpus (AVIC) consisting of spontaneous, conversational speech demonstrating “theoretical” effectiveness of the approach. Further, to evaluate the approach with regards to real-life usability a user-study is conducted for proof of “practical” effectiveness.     

Unsupervised texture segmentation using Gabor filters

This paper presents a texture segmentation algorithm inspired by the multi-channel filtering theory for visual information processing in the early stages of human visual system. The channels are characterized by a bank of Gabor filters that nearly uniformly covers the spatial-frequency domain, and a systematic filter selection scheme is proposed, which is based on reconstruction of the input image from the filtered images. Texture features are obtained by subjecting each (selected) filtered image to a nonlinear transformation and computing a measure of “energy” in a window around each pixel. A square-error clustering algorithm is then used to integrate the feature images and produce a segmentation. A simple procedure to incorporate spatial information in the clustering process is proposed. A relative index is used to estimate the “true” number of texture categories.     

Efficient bottom-up hybrid hierarchical clustering techniques for protein sequence classification

Hybrid hierarchical clustering techniques which combine the characteristics of different partitional clustering techniques or partitional and hierarchical clustering techniques are interesting. In this paper, efficient bottom-up hybrid hierarchical clustering (BHHC) techniques have been proposed for the purpose of prototype selection for protein sequence classification. In the first stage, an incremental partitional clustering technique such as leader algorithm (ordered leader no update (OLNU) method) which requires only one database (db) scan is used to find a set of subcluster representatives. In the second stage, either a hierarchical agglomerative clustering (HAC) scheme or a partitional clustering algorithm—‘K-medians’ is used on these subcluster representatives to obtain a required number of clusters. Thus, this hybrid scheme is scalable and hence would be suitable for clustering large data sets and we also get a hierarchical structure consisting of clusters and subclusters and the representatives of which are used for pattern classification. Even if more number of prototypes are generated, classification time does not increase much as only a part of the hierarchical structure is searched. The experimental results (classification accuracy (CA) using the prototypes obtained and the computation time) of the proposed algorithms are compared with that of the hierarchical agglomerative schemes, K-medians and nearest neighbour classifier (NNC) methods. The proposed methods are found to be computationally efficient with reasonably good CA.     

用组合不变量进行模式识别的一种新方法

用与目标的位置、大小、方向和其他变化无关的特征来识别目标是模式识别领域的一个热点。现存的基于不变特征的二维模式识别方法在目标被模糊了情况下都无法精确识别。本文提出了一种可解决上述问题的新的模式识别方法。该方法用组合不变量作为图像特征,以加权规格化互相关作为分类技术。在分类过程中,使用每一类的所有原型的第k个特征的类内标准方差的均值作为加权因子以提高识别率。对头像的数字试验证实了组合不变量特征对图像的平移、伸缩、旋转和模糊变换的不变性和该模式识别方法的可行性。     

Recognizing image “style” and activities in video using local features and naive Bayes

The goal of this paper is to offer a framework for classification of images and video according to their “type”, or “style”––a problem which is hard to define, but easy to illustrate; for example, identifying an artist by the style of his/her painting, or determining the activity in a video sequence. The paper offers a simple classification paradigm based on local properties of spatial or spatio-temporal blocks. The learning and classification are based on the naive Bayes classifier. A few experimental results are presented.     

Learning graph prototypes for shape recognition

This paper presents some new approaches for computing graph prototypes in the context of the design of a structural nearest prototype classifier. Four kinds of prototypes are investigated and compared: set median graphs, generalized median graphs, set discriminative graphs and generalized discriminative graphs. They differ according to (i) the graph space where they are searched for and (ii) the objective function which is used for their computation. The first criterion allows to distinguish set prototypes which are selected in the initial graph training set from generalized prototypes which are generated in an infinite set of graphs. The second criterion allows to distinguish median graphs which minimize the sum of distances to all input graphs of a given class from discriminative graphs, which are computed using classification performance as criterion, taking into account the inter-class distribution. For each kind of prototype, the proposed approach allows to identify one or many prototypes per class, in order to manage the trade-off between the classification accuracy and the classification time.Each graph prototype generation/selection is performed through a genetic algorithm which can be specialized to each case by setting the appropriate encoding scheme, fitness and genetic operators.An experimental study performed on several graph databases shows the superiority of the generation approach over the selection one. On the other hand, discriminative prototypes outperform the generative ones. Moreover, we show that the classification rates are improved while the number of prototypes increases. Finally, we show that discriminative prototypes give better results than the median graph based classifier.     

Optimal Conjunctive Granulometric Bandpass Filters

A conjunctive homothetic granulometry is an intersection of openings by independently scaled structuring elements. Like classical Euclidean granulometries, conjunctive granulometries possess size distributions and pattern spectra; however, they are based on intersections of openings by scaled structuring elements instead of unions of such openings. For a disjunctive granulometry, which is a union of openings, a grain (or part thereof) is passed if there exists a translate of at least one structuring element that is a subset of the grain; for a conjunctive granulometry, there must exist a translate of each structuring element that is a subset of the grain. Like disjunctive granulometries, they possess size distributions; however, unlike disjunctive granulometries, their pattern spectra are not probability densities. An optimal granulometric bandpass filter passes image components so as to minimize the expected area of the symmetric difference between the filtered and ideal images. This paper provides an analytic formulation of optimal conjunctive granulometric bandpass filters. The theory provides one of the few areas of nonlinear image processing in which three of the basic components of linear optimization apply: (1) there is an analytic expression determining the optimal filter; (2) there is an explicit error formula; (3) and there is a closed-form representation of the optimal filter based on a decomposition of the observed random image. These correspond to the Wiener-Hopf equation, mean-square-error formula, and filter representation via an integral canonical representation of the observed image in linear filtering.     

Adaptive nearest neighbor pattern classification

A variant of nearest-neighbor (NN) pattern classification and supervised learning by learning vector quantization (LVQ) is described. The decision surface mapping method (DSM) is a fast supervised learning algorithm and is a member of the LVQ family of algorithms. A relatively small number of prototypes are selected from a training set of correctly classified samples. The training set is then used to adapt these prototypes to map the decision surface separating the classes. This algorithm is compared with NN pattern classification, learning vector quantization, and a two-layer perceptron trained by error backpropagation. When the class boundaries are sharply defined (i.e., no classification error in the training set), the DSM algorithm outperforms these methods with respect to error rates, learning rates, and the number of prototypes required to describe class boundaries.     

False positive reduction in urinary particle recognition

The identification of non-cell objects in biological images is not a trivial task largely due to the difficulty in describing their characteristics in recognition systems. In order to better reduce the false positive rate caused by the presence of non-cell particles, we propose a novel approach using a local jet context features scheme combined with a two-tier object classification system. The newly proposed feature scheme, namely local jet context feature, integrates part of global features with the “local jet” features. The scheme aims to effectively describe the particle characteristics that are invariant to shift and rotation, and hence help to retain the critical shape information. The proposed two-tier particle classification strategy consists of a pre-recognition stage first and later a further filtering phase. Using the local jet context features coupled with a multi-class SVM classifier, the pre-recognition stage intends to assign the particles to their corresponding classes as many as possible. To further reduce the false positive particles, next a decision tree classifier based on shape-centered features is applied. Our experimental study shows that through the proposed two-tier classification strategy, we are able to achieve 85% of identification accuracy and 80% of F₁ value in urinary particle recognition. The experiment results demonstrate that the proposed local jet context features are capable to discriminate particles in terms of shape and texture characteristics. Overall, the two-tier classification stage is found to be effective in reducing the false positive rate caused by non-cell particles.     

Passive steganalysis based on higher order image statistics of curvelet transform

Steganographic techniques accomplish covert communication by embedding secret messages into innocuous digital images in ways that are imperceptible to the human eye. This paper presents a novel passive steganalysis strategy in which the task is approached as a pattern classification problem. A critical part of the steganalyser design depends on the selection of informative features. This paper is aimed at proposing a novel attack with improved performance indices with the following implications: 1) employing higher order statistics from a curvelet sub-band image representation that offers better discrimination ability for detecting stego anomalies in images, as compared to other conventional wavelet transforms; 2) increasing the sensitivity and specificity of the system by the feature reduction phase; 3) realizing the system using an efficient classification engine, a neuro-C4.5 classifier, which provides better classification rate. An extensive experimental evaluation on a database containing 5600 clean and stego images shows that the proposed scheme is a state-of-the-art steganalyser that outperforms other previous steganalytic methods.     

Multi-level pixel-based texture classification through efficient prototype selection via normalized cut

This paper presents a new efficient technique for supervised pixel-based classification of textured images. A prototype selection algorithm that relies on the normalized cut criterion is utilized for automatically determining a subset of prototypes in order to characterize each texture class at the local level based on the outcome of a multichannel Gabor filter bank. Then, a simple minimum distance classifier fed with the previously determined prototypes is used to classify every image pixel into one of the given texture classes. Multi-sized evaluation windows following a top-down approach are used during classification in order to improve accuracy near frontiers of regions of different texture. Results with standard Brodatz, VisTex and MeasTex compositions and with complex real images are presented and discussed. The proposed technique is also compared with alternative texture classifiers.     

基于模糊模型相似测量的小类别数汉字及数字识别

文章提出了一种基于模糊相似测量的小类别数多字体汉字及数字识别方法.该方法通过模糊逻辑处理,直接将字符的二值化图像转换成基于非线性加权相似函数的模糊样板,然后通过分类模糊模型的统计,相似性测量样板的分级组合和基于规则的分类进行识别.实验表明,该方法用于小类别数多字体汉字及数字识别的效果良好.     

Self-organization of conceptual generalities and pattern-directed learning

Human expert decision makers can be characterized by their ability to perceive a hypothetical conceptual generality or pattern that is underlying a given collection of objects. The conventional cluster analysis is unable to generate such patterns since its clustering process is far from what the human experts actually do. That is, human experts form some concepts inductively from individual observations based on the conceptual “meaning” which the objects have. In this paper, by introducing an idea of prototype theory from a psychological domain with respect to human concept formation, an algorithm for human classification process is proposed. Based on this, the role of human generalization capability in his classification process is discussed with respect to the background semantic knowledge. The algorithm can be roughly divided into two phases; inductive prototype formation from training examples in a bottom-up fashion, and pattern-directed clustering of the instances being affected by the acquired concepts in a top-down fashion. Using a schematically-modelled example, the algorithm is illustrated with its implemented results. Our modelling method for the human classification process can be utilized for conceptual clustering that classifies a number of unknown objects into a distinguished group being affected by pre-acquired concepts.     

Automated and Precise Event Detection Method for Big Data in Biomedical Imaging with Support Vector Machine

This paper proposes a machine learning based method which can detect certain events automatically and precisely in biomedical imaging. We detect one important and not well-defined event, which is called flash, in fluorescence images of Escherichia coli. Given a time series of images, first we propose a scheme to transform the event detection on region of interest (ROI) in images to a classification problem. Then with supervised human labeling data, we develop a feature selection technique to utilize support vector machine (SVM) to solve this classification problem. To reduce the time in training SVM model, a parallel version of SVM training is implemented. On ten stacks of fluorescence images labeled by experts, each of which owns one hundred 512 ·512 images with in total 4906 ROIs and 72056 labeled events, event detection with proposed method takes 19 seconds, while human labeling roughly costs 60 hours. With human labeling as the standard, the accuracy of our method achieves an F-value of about 0.81. This method is much faster than human detection and expects to be more precise with bigger data. It also can be expanded to a series of event detection with similar properties and improve efficiency of detection greatly.     

基于模糊模型相似测量的字符无监督分类法

该文提出一种基于模糊模型相似测量的文本分析系统的字符预分类方法 ,用于对字符的无监督分类 ,以提高整个字符识别系统的速度、正确性和鲁棒性 .作者在字符印刷结构归类的基础上 ,采用模板匹配方法将各类字符分别转换成基于一非线性加权相似函数的模糊样板集合 .模糊字符的无监督分类是字符匹配的一种自然范例并发展了加权模糊相似测量的研究 .该文讨论了该模糊模型的特性、模糊样板匹配的规则 ,并用于加快字符分类处理 ,经过字符分类 ,在字符识别时由于只需针对较小的模糊样板集合而变得容易和快速