Search

In this work we describe a fast and stable algorithm for the computation of the orthogonal moments of an image. Indeed, orthogonal moments are characterized by a high discriminative power, but some of their possible formulations are characterized by a large computational complexity, which limits their real-time application. This paper describes in detail an approach based on recurrence relations, and proposes an optimized Matlab implementation of the corresponding computational procedure, aiming to solve the above limitations and put at the community’s disposal an efficient and easy to use software. In our experiments we evaluate the effectiveness of the recurrence formulation, as well as its performance for the reconstruction task, in comparison to the closed form representation, often used in the literature. The results show a sensible reduction in the computational complexity, together with a greater accuracy in reconstruction. In order to assess and compare the accuracy of the computed moments in texture analysis, we perform classification experiments on six well-known databases of texture images. Again, the recurrence formulation performs better in classification than the closed form representation. More importantly, if computed from the GLCM of the image using the proposed stable procedure, the orthogonal moments outperform in some situations some of the most diffused state-of-the-art descriptors for texture classification. [ABSTRACT FROM AUTHOR]

Defect detection and classification of ceramic tile surface defects occurred in firing units are usually performed by human observations in most factories. In this paper, an automatic image processing system with high accuracy and time efficient approaches is presented. To this end, first, for defect detection, Rotation Invariant Measure of Local Variance (RIMLV) operator from statistical methods is employed for defect edges detection, and cooperatively a Close morphological operator from structural methods is used to fill and smooth detected regions. Then, all the detected defects of one ceramic tile are labeled, and the corresponding geometric features are extracted. Finally, a multi-class support vector machine classifier with winner-takes-all strategy based on statistical pattern recognition theories is employed to identify the defect type. [ABSTRACT FROM AUTHOR]

Image set classification has been widely applied to many real-life scenarios including surveillance videos, multi-view camera networks and personal albums. Compared with single image based classification, it is more promising and therefore has attracted significant research attention in recent years. Traditional (forward) sparse representation (fSR) just makes use of training images to represent query ones. If we can find complementary information from backward sparse representation (bSR) which represents query images with training ones, the performance will be likely to be improved. However, for image set classification, the way to produce additional bases for bSR is a problem concerned as there is no other bases than the query set itself. In this paper, we extend cooperative sparse representation (CoSR) method, which integrates fSR and bSR together, to image set classification. In this process, we propose two schemes, namely ‘Learning Bases’ and ‘Training Sets Division’, to produce the additional dictionary for bSR. And different from previous work, our work considers scene classification as a problem of image set classification, which will provide a new insight for scene classification. Experimental results show that the proposed model can obtain competitive recognition rates for image set classification. By combining information from these two opposite SRs, better results can be achieved. Also the feasibility for the formulation of image set classification on scene classification is validated. [ABSTRACT FROM AUTHOR]

The bag-of-features (BoF) model for image classification has been thoroughly studied over the last decade. Different from the widely used BoF methods which model images with a pre-trained codebook, the alternative codebook-free image modeling method, which we call codebookless model (CLM), attracts little attention. In this paper, we present an effective CLM that represents an image with a single Gaussian for classification. By embedding Gaussian manifold into a vector space, we show that the simple incorporation of our CLM into a linear classifier achieves very competitive accuracy compared with state-of-the-art BoF methods (e.g., Fisher Vector). Since our CLM lies in a high-dimensional Riemannian manifold, we further propose a joint learning method of low-rank transformation with support vector machine (SVM) classifier on the Gaussian manifold, in order to reduce computational and storage cost. To study and alleviate the side effect of background clutter on our CLM, we also present a simple yet effective partial background removal method based on saliency detection. Experiments are extensively conducted on eight widely used databases to demonstrate the effectiveness and efficiency of our CLM method. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel Structure-Constrained Low-Rank and Partial Sparse Representation algorithm for image classification. First, a Structure-Constrained Low-Rank Dictionary Learning (SCLRDL) algorithm is proposed, which imposes both structure and low-rank restriction on the coefficient matrix. Second, under the assumption that the coefficient of test sample is sparse and correlated with the learned representation of training samples, we propose a Low-Rank and Partial Sparse Representation (LRPSR) algorithm which concatenates training samples and test sample to form a data matrix and finds a low-rank and sparse representation of the data matrix over learned dictionary by low-rank matrix recovery technique. Finally, we design a Sample Selection (SS) procedure to accelerate LRPSR. Experimental results on Caltech 101 and Caltech 256 show that our method outperforms most sparse or low-rank based image classification algorithm proposed recently. [ABSTRACT FROM AUTHOR]

Dictionary learning (DL) has recently attracted intensive attention due to its representative and discriminative power in various classification tasks. Although much progress has been reported in the existing supervised DL approaches, it is still an open problem that how to build the relationship between dictionary atoms and the class labels in multiclass classification. In this paper, based on the assumption that the relevance of dictionary atoms could be helpful in multiclass classification task, we proposed a class relatedness oriented (CRO) discriminative dictionary learning method for sparse coding. Utilizing the ℓ 1 , ∞ -norm regularization on the coding coefficient matrix, the proposed method can adaptively learn the class relatedness between dictionary atoms and the multiclass labels. Experimental results of face recognition, object classification, and action recognition demonstrate that our proposed method is comparable to many state-of-the-art DDL methods. [ABSTRACT FROM AUTHOR]

Ensemble learning can improve the performance of classification by integrating a set of classifiers, and shows significant potential benefits to the classification of hyperspectral image. However, the ensemble strategy remarkably influences the classification results, which include determining the minimum number of classifiers and assigning advisable weights associated with each classifier. In this paper, we present a novel sparse ensemble learning method with spectral–spatial knowledge for hyperspectral image classification. It considers the ensemble strategy under sparse recovery framework, where the solved non-zero coefficients reveal the importance of the selected classifier, from which a compact and effective ensemble learning system can be derived. Moreover, the spatial information is incorporated into the classification to develop a spectral–spatial joint sparse representation based ensemble learning algorithm for more accurate classification of hyperspectral images. Experimental results on several real hyperspectral images show that the proposed sparse ensemble system can achieve better performance than traditional ensemble learning methods using all classifiers, and it largely improves the efficiency in testing phase. [ABSTRACT FROM AUTHOR]

In this paper, we present a new set of bivariate discrete orthogonal polynomials based on the product of Meixner׳s discrete orthogonal polynomials by Tchebichef׳s, Krawtchouk׳s and Hahn׳s discrete orthogonal polynomials. This set of bivariate discrete orthogonal polynomials is used to define three new types of discrete orthogonal moments as Meixner–Tchebichef moments, Meixner–Krawtchouk moments and Meixner–Hahn moments. We also present an approach to accelerate the computation of these moments by using the image block representation for binary images and image slice representation for gray-scale images. A novel set of Meixner–Tchebichef invariant moments, Meixner–Krawtchouk invariant moments and Meixner–Hahn invariant moments is also derived. These invariant moments are derived algebraically from the geometric invariant moments and their computation is accelerated using an image representation scheme. The proposed algorithms are tested using several well-known computer vision datasets including, moment׳s invariability and pattern recognition. The performance of these invariant moments used as pattern features for a pattern classification is compared with the shape descriptors of Hu, Legendre, Tchebichef–Krawtchouk, Krawtchouk–Hahn and Tchebichef–Hahn invariant moments, the texture descriptors and the color descriptors for four different databases. [ABSTRACT FROM AUTHOR]

Abstract: In remotely sensed Synthetic Aperture Radar (SAR) images, scattering from a target is often the result of a mixture of different mechanisms. For this reason, detection of targets and classification of SAR images may be very difficult and very different from other sensor imagery. Fully polarimetric data offer the possibility to separate the different mechanisms, interpret them and consequently identify the geometry of the targets. To achieve this task, several target decomposition techniques have been proposed in the literature to improve the interpretation of this kind of data. Among these, the physical based techniques are the most considered. This paper proposes a novel approach for target decomposition based on the use of Nonlinear Principal Component Analysis. Different from physical based target decomposition techniques, the proposed method is based on a nonlinear decorrelation of the received polarimetric SAR (POLSAR) signal into few elementary components that could be associated to the different scattering mechanisms present in the image. A comparison of the classification results obtained using different decomposition techniques demonstrates that the proposed approach can be an effective alternative to classical physical based methods. [Copyright &y& Elsevier]

Facial attractiveness has long been argued upon varied emphases by philosophers, artists, psychologists and biologists. A number of studies empirically investigated how facial attractiveness was influenced by 2D facial characteristics, such as symmetry, averageness and golden ratio. However, few implementations of facial beauty assessment were based on 3D facial features. The purpose of this paper is to propose a novel cluster assessment system for facial attractiveness that is characterized by the incorporation of 3D geometric Moiré features with an adjusted fuzzy neural network (FNN). We first extract 3D facial features from images acquired by a 3dMD scanner. Seven Moiré features are employed to represent a 3D facial image. The FNN classifier, taking the Moiré features as the parameters, is then trained and validated against independently conducted attractiveness ratings. A number of diverse referees were invited and offered their attractiveness ratings over a five-item Likert scale for 100 female facial images. The proposed assessment presents a high accuracy rate of 90%, and the area under curve (AUC) computed from the receiver operating characteristic (ROC) curve is 0.95. The results show that the perceptions of facial attractiveness are essentially consensus among raters, and can be mathematically modeled through supervised learning techniques. The high accuracy achieved proves that the proposed FNN classifier can serve as a general, automated and human-like judgment tool for objective classification of female facial attractiveness, and thus has potential applications to the entertainment industry, cosmetic industry, virtual media, and plastic surgery. [ABSTRACT FROM AUTHOR]

Abstract: Perfusion computed tomography (CT) method has been used to differentiate malignant pulmonary nodules from benign nodules based on the assessment for the change of the CT attenuation value within the pulmonary nodules. Instead of using the change of the CT attenuation value, a set of fractal features based on fractional Brownian motion model is proposed in this paper to automatically distinguish malignant nodules from benign nodules. In a set of 107 CT images from 107 different patients with each image containing a solitary pulmonary nodule, our experimental results obtained from a support vector machine classifier show that the accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and the area under the ROC curve are 83.11%, 90.92%, 71.70%, 80.05%, 87.52%, and 0.8437, respectively, by using the proposed fractal-based feature set. Such a result outperforms the conventional method of using the change of the CT attenuation value as the feature for classification. When combining this conventional method with our proposed fractal-based method, the accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and the area under the ROC curve can be promoted to 88.82%, 93.92%, 82.90%, 87.30%, 90.20%, and 0.9019, respectively. In other words, a high performance of pulmonary nodule classification can be achieved with a single post-contrast CT scan. [Copyright &y& Elsevier]

Abstract: Pattern classification of dermoscopy images is a challenging task of differentiating between benign melanocytic lesions and melanomas. In this paper, a novel pattern classification method based on color symmetry and multiscale texture analysis is developed to assist dermatologists'' diagnosis. Our method aims to classify various tumor patterns using color–texture properties extracted in a perceptually uniform color space. In order to design an optimal classifier and to address the problem of multicomponent patterns, an adaptive boosting multi-label learning algorithm (AdaBoost.MC) is developed. Finally, the class label set of the test pattern is determined by fusing the results produced by boosting based on the maximum a posteriori (MAP) and robust ranking principles. The proposed discrimination model for multi-label learning algorithm is fully automatic and obtains higher accuracy compared to existing multi-label classification methods. Our classification model obtains a sensitivity (SE) of 89.28%, specificity (SP) of 93.75% and an area under the curve (AUC) of 0.986. The results demonstrate that our pattern classifier based on color–texture features agrees with dermatologists'' perception. [Copyright &y& Elsevier]

Abstract: As an important problem in image understanding, salient object detection is essential for image classification, object recognition, as well as image retrieval. In this paper, we propose a new approach to detect salient objects from an image by using content-sensitive hypergraph representation and partitioning. Firstly, a polygonal potential Region-Of-Interest (p-ROI) is extracted through analyzing the edge distribution in an image. Secondly, the image is represented by a content-sensitive hypergraph. Instead of using fixed features and parameters for all the images, we propose a new content-sensitive method for feature selection and hypergraph construction. In this method, the most discriminant color channel which maximizes the difference between p-ROI and the background is selected for each image. Also the number of neighbors in hyperedges is adjusted automatically according to the image content. Finally, an incremental hypergraph partitioning is utilized to generate the candidate regions for the final salient object detection, in which all the candidate regions are evaluated by p-ROI and the best match one will be the selected as final salient object. Our approach has been extensively evaluated on a large benchmark image database. Experimental results show that our approach can not only achieve considerable improvement in terms of commonly adopted performance measures in salient object detection, but also provide more precise object boundaries which is desirable for further image processing and understanding. [Copyright &y& Elsevier]

Abstract: In this paper, we approach the removal of back-to-front interferences from scans of double-sided documents as a blind source separation problem, and extend our previous linear mixing model to a more effective nonlinear mixing model. We consider the front and back ideal images as two individual patterns overlapped in the observed recto and verso scans, and apply an unsupervised constrained maximum likelihood technique to separate them. Through several real examples, we show that the results obtained by this approach are much better than the ones obtained through data decorrelation or independent component analysis. As compared to approaches based on segmentation/classification, which often aim at cleaning a foreground text by removing all the textured background, one of the advantages of our method is that cleaning does not alter genuine features of the document, such as color or other structures it may contain. This is particularly interesting when the document has a historical importance, since its readability can be improved while maintaining the original appearance. [Copyright &y& Elsevier]

Abstract: Image-to-class (I2C) distance is a novel measure for image classification and has successfully handled datasets with large intra-class variances. However, due to the lack of a training phase, the performance of this distance is easily affected by irrelevant local features that may hurt the classification accuracy. Besides, the success of this I2C distance relies heavily on the large number of local features in the training set, which requires expensive computation cost for classifying test images. On the other hand, if there are small number of local features in the training set, it may result in poor performance. In this paper, we propose a distance learning method to improve the classification accuracy of this I2C distance as well as two strategies for accelerating its NN search. We first propose a large margin optimization framework to learn the I2C distance function, which is modeled as a weighted combination of the distance from every local feature in an image to its nearest-neighbor (NN) in a candidate class. We learn these weights associated with local features in the training set by constraining the optimization such that the I2C distance from image to its belonging class should be less than that to any other class. We evaluate the proposed method on several publicly available image datasets and show that the performance of I2C distance for classification can significantly be improved by learning a weighted I2C distance function. To improve the computation cost, we also propose two methods based on spatial division and hubness score to accelerate the NN search, which is able to largely reduce the on-line testing time while still preserving or even achieving a better classification accuracy. [Copyright &y& Elsevier]

Abstract: In this paper, we present an adaptive method for the binarization of historical manuscripts and degraded document images. The proposed approach is based on maximum likelihood (ML) classification and uses a priori information and the spatial relationship on the image domain. In contrast with many conventional methods that use a decision based on thresholding, the proposed method performs a soft decision based on a probabilistic model. The main idea is that, from an initialization map (under-binarization) containing only the darkest part of the text, the method is able to recover the main text in the document image, including low-intensity and weak strokes. To do so, fast and robust local estimation of text and background features is obtained using grid-based modeling and inpainting techniques; then, the ML classification is performed to classify pixels into black and white classes. The advantage of the proposed method is that it preserves weak connections and provides smooth and continuous strokes, thanks to its correlation-based nature. Performance is evaluated both subjectively and objectively against standard databases. The proposed method outperforms the state-of-the-art methods presented in the DIBCO’09 binarization contest, although those other methods provide performance close to it. [Copyright &y& Elsevier]

Abstract: This paper shows how to improve holistic face analysis by assigning importance factors to different facial regions (termed as face relevance maps). We propose a novel supervised learning algorithm for generating face relevance maps to improve the discriminating capability of existing methods. We have successfully applied the developed technique to face identification based on the Eigenfaces and Fisherfaces methods, and also to gender classification based on principal geodesic analysis (PGA). We demonstrate how to iteratively learn the face relevance map using labelled data. Experimental results confirm the effectiveness of the developed approach. [Copyright &y& Elsevier]

Abstract: In some classification problems there is prior information about the joint relevance of groups of features. This knowledge can be encoded in a network whose nodes correspond to features and whose edges connect features that should be either both excluded or both included in the predictive model. In this paper, we introduce a novel network-based sparse Bayesian classifier (NBSBC) that makes use of the information about feature dependencies encoded in such a network to improve its prediction accuracy, especially in problems with a high-dimensional feature space and a limited amount of available training data. Approximate Bayesian inference is efficiently implemented in this model using expectation propagation. The NBSBC method is validated on four real-world classification problems from different domains of application: phonemes, handwritten digits, precipitation records and gene expression measurements. A comparison with state-of-the-art methods (support vector machine, network-based support vector machine and graph lasso) show that NBSBC has excellent predictive performance. It has the best accuracy in three of the four problems analyzed and ranks second in the modeling of the precipitation data. NBSBC also yields accurate and robust rankings of the individual features according to their relevance to the solution of the classification problem considered. The accuracy and stability of these estimates is an important factor in the good overall performance of this method. [Copyright &y& Elsevier]

Abstract: This paper formulates pixel labelling as a series of two-category classification. Unlike existing techniques, which assign a determinate label to each pixel, we assign a label set to each pixel and shrink the label set step by step. Determinate labelling is achieved within (n is size of label set) steps. In each step, we bisect the label set into two subsets and discard the one with higher cost of assigning it to the pixel. Simultaneous labelling of an image is carried out by minimizing an energy function that can be minimized via graph cut algorithm. Based on the bisection approach, we propose a bitwise algorithm for pixel labelling, which set one bit of each pixel''s label in each step. We apply the proposed algorithm to stereo matching and image restoration. Experimental results demonstrate that both good performance and high efficiency are achieved. [Copyright &y& Elsevier]

Abstract: Accurate grading for hepatocellular carcinoma (HCC) biopsy images is important to prognosis and treatment planning. In this paper, we propose an automatic system for grading HCC biopsy images. In preprocessing, we use a dual morphological grayscale reconstruction method to remove noise and accentuate nuclear shapes. A marker-controlled watershed transform is applied to obtain the initial contours of nuclei and a snake model is used to segment the shapes of nuclei smoothly and precisely. Fourteen features are then extracted based on six types of characteristics for HCC classification. Finally, we propose a SVM-based decision-graph classifier to classify HCC biopsy images. Experimental results show that 94.54% of classification accuracy can be achieved by using our SVM-based decision-graph classifier while 90.07% and 92.88% of classification accuracy can be achieved by using k-NN and SVM classifiers, respectively. [Copyright &y& Elsevier]

Abstract: Techniques for understanding video object motion activity are becoming increasingly important with the widespread adoption of CCTV surveillance systems. Motion trajectories provide rich spatiotemporal information about an object''s activity. This paper presents a novel technique for clustering and classification of motion. In the proposed motion learning system, trajectories are treated as time series and modelled using modified DFT (discrete fourier transform)-based coefficient feature space representation. A framework (iterative HSACT-LVQ (hierarchical semi-agglomerative clustering-learning vector quantization)) is proposed for learning of patterns in the presence of significant number of anomalies in training data. A novel modelling technique, referred to as m-Mediods, is also proposed that models the class containing n members with m Mediods. Once the m-Mediods-based model for all the classes have been learnt, the classification of new trajectories and anomaly detection can be performed by checking the closeness of said trajectory to the models of known classes. A mechanism based on agglomerative approach is proposed for anomaly detection. Our proposed techniques are validated using variety of simulated and complex real life trajectory data sets. [Copyright &y& Elsevier]

Abstract: A novel set of moment invariants based on the Krawtchouk moments are introduced in this paper. These moment invariants are computed over a finite number of image intensity slices, extracted by applying an innovative image representation scheme, the image slice representation (ISR) method. Based on this technique an image is decomposed to a several non-overlapped intensity slices, which can be considered as binary slices of certain intensity. This image representation gives the advantage to accelerate the computation of image''s moments since the image can be described in a number of homogenous rectangular blocks, which permits the simplification of the computation formulas. The moments computed over the extracted slices seem to be more efficient than the corresponding moments of the same order that describe the whole image, in recognizing the pattern under processing. The proposed moment invariants are exhaustively tested in several well known computer vision datasets, regarding their rotation, scaling and translation (RST) invariant recognition performance, by resulting to remarkable outcomes. [Copyright &y& Elsevier]

Abstract: Fractal dimension (FD) is a useful feature for texture segmentation, shape classification, and graphic analysis in many fields. The box-counting approach is one of the frequently used techniques to estimate the FD of an image. This paper presents an efficient box-counting-based method for the improvement of FD estimation accuracy. A new model is proposed to assign the smallest number of boxes to cover the entire image surface at each selected scale as required, thereby yielding more accurate estimates. The experiments using synthesized fractional Brownian motion images, real texture images, and remote sensing images demonstrate this new method can outperform the well-known differential boxing-counting (DBC) method. [Copyright &y& Elsevier]

Abstract: This paper presents a new fingerprint singular point detection method that is type-distinguishable and applicable to various fingerprint images regardless of their resolutions. The proposed method detects singular points by analyzing the shapes of the local directional fields of a fingerprint image. Using the predefined rules, all types of singular points (upper core, lower core, and delta points) can be extracted accurately and delineated in terms of the type of singular points. In case of arch-type fingerprints there exists no singular point, but reference points for arch-type fingerprints are required to be detected for registration. Therefore, we propose a new reference point detection method for arch-type fingerprints as well. The result of the experiments on the two public databases (FVC2000 2a, FVC2002 2a) with different resolutions demonstrates that the proposed method has high accuracy in locating each types of singular points and detecting the reference points of arch-type fingerprints without regard to their image resolutions. [Copyright &y& Elsevier]

Face detection from cluttered images is challenging due to the wide variability of face appearances and the complexity of image backgrounds. This paper proposes a classification-based method for locating frontal faces in cluttered images. To improve the detection performance, we extract gradient direction features from local window images as the input of the underlying two-class classifier. The gradient direction representation provides better discrimination ability than the image intensity, and we show that the combination of gradient directionality and intensity outperforms the gradient feature alone. The underlying classifier is a polynomial neural network (PNN) on a reduced feature subspace learned by principal component analysis (PCA). The incorporation of the residual of subspace projection into the PNN was shown to improve the classification performance. The classifier is trained on samples of face and non-face images to discriminate between the two classes. The superior detection performance of the proposed method is justified in experiments on a large number of images. [Copyright &y& Elsevier]

Repeatability of many genetic analysis experiments can be improved by the application of signal processing and image-processing tools. Most of the experiments in genetics result in some sort of digital signal or image patterns that are subjectively analyzed by the geneticists. This paper presents an example project where image-processing techniques are applied for automation of most of the routine processes of agarose gel image analysis. Result of applying this program has shown that the time taken for the analysis has been reduced by about 70% and the result is reproducible. [Copyright &y& Elsevier]

In this paper, we present a constrained linear discriminant analysis (CLDA) approach to hyperspectral image detection and classification as well as its real-time implementation. The basic idea of CLDA is to design an optimal transformation matrix which can maximize the ratio of inter-class distance to intra-class distance while imposing the constraint that different class centers after transformation are along different directions such that different classes can be better separated. The solution turns out to be a constrained version of orthogonal subspace projection (OSP) implemented with a data whitening process. The CLDA approach can be applied to solve both detection and classification problems. In particular, by introducing color for display the classification is achieved with a single classified image where a pre-assigned color is used to display a specified class. The real-time implementation is also developed to meet the requirement of on-line image analysis when the immediate data assessment is critical. The experiments using HYDICE data demonstrate the strength of CLDA approach in discriminating the targets with subtle spectral difference. [Copyright &y& Elsevier]