scispace - formally typeset
Search or ask a question

Showing papers by "Stan Z. Li published in 2001"


Book
Stan Z. Li1
01 Jan 2001
TL;DR: This detailed and thoroughly enhanced third edition presents a comprehensive study / reference to theories, methodologies and recent developments in solving computer vision problems based on MRFs, statistics and optimisation.
Abstract: Markov random field (MRF) theory provides a basis for modeling contextual constraints in visual processing and interpretation. It enables systematic development of optimal vision algorithms when used with optimization principles. This detailed and thoroughly enhanced third edition presents a comprehensive study / reference to theories, methodologies and recent developments in solving computer vision problems based on MRFs, statistics and optimisation. It treats various problems in low- and high-level computational vision in a systematic and unified way within the MAP-MRF framework. Among the main issues covered are: how to use MRFs to encode contextual constraints that are indispensable to image understanding; how to derive the objective function for the optimal solution to a problem; and how to design computational algorithms for finding an optimal solution. Easy-to-follow and coherent, the revised edition is accessible, includes the most recent advances, and has new and expanded sections on such topics as: Discriminative Random Fields (DRF) Strong Random Fields (SRF) Spatial-Temporal Models Total Variation Models Learning MRF for Classification (motivation + DRF) Relation to Graphic Models Graph Cuts Belief Propagation Features: Focuses on the application of Markov random fields to computer vision problems, such as image restoration and edge detection in the low-level domain, and object matching and recognition in the high-level domain Presents various vision models in a unified framework, including image restoration and reconstruction, edge and region segmentation, texture, stereo and motion, object matching and recognition, and pose estimation Uses a variety of examples to illustrate how to convert a specific vision problem involving uncertainties and constraints into essentially an optimization problem under the MRF setting Introduces readers to the basic concepts, important models and various special classes of MRFs on the regular image lattice and MRFs on relational graphs derived from images Examines the problems of parameter estimation and function optimization Includes an extensive list of references This broad-ranging and comprehensive volume is an excellent reference for researchers working in computer vision, image processing, statistical pattern recognition and applications of MRFs. It has been class-tested and is suitable as a textbook for advanced courses relating to these areas.

1,694 citations


Proceedings ArticleDOI
01 Dec 2001
TL;DR: A novel method, called local non-negative matrix factorization (LNMF), for learning spatially localized, parts-based subspace representation of visual patterns, which gives a set of bases which not only allows a non-subtractive representation of images but also manifests localized features.
Abstract: In this paper, we propose a novel method, called local non-negative matrix factorization (LNMF), for learning spatially localized, parts-based subspace representation of visual patterns An objective function is defined to impose a localization constraint, in addition to the non-negativity constraint in the standard NMF This gives a set of bases which not only allows a non-subtractive (part-based) representation of images but also manifests localized features An algorithm is presented for the learning of such basic components Experimental results are presented to compare LNMF with the NMF and PCA methods for face representation and recognition, which demonstrates advantages of LNMF

864 citations


Journal ArticleDOI
TL;DR: The performance of the SVMs based face recognition is compared with the standard eigenface approach, and also the more recently proposed algorithm called the nearest feature line (NFL).

324 citations


Proceedings ArticleDOI
01 Dec 2001
TL;DR: This work proposes a new appearance model, called direct appearance model (DAM), without combining from shape and texture as in AAM, which uses texture information directly in the prediction of the shape and in the estimation of position and appearance (hence the name DAM).
Abstract: Active appearance model (AAM), which makes ingenious use of both shape and texture constraints, is a powerful tool for face modeling, alignment and facial feature extraction under shape deformations and texture variations. However, as we show through our analysis and experiments, there exist admissible appearances that are not modeled by AAM and hence cannot be reached by AAM search; also the mapping from the texture subspace to the shape subspace is many-to-one and therefore a shape should be determined entirely by the texture in it. We propose a new appearance model, called direct appearance model (DAM), without combining from shape and texture as in AAM. The DAM model uses texture information directly in the prediction of the shape and in the estimation of position and appearance (hence the name DAM). In addition, DAM predicts the new face position and appearance based on principal components of texture difference vectors, instead of the raw vectors themselves as in AAM. These lead to the following advantages over AAM: (1) DAM subspaces include admissible appearances previously unseen in AAM, (2) convergence and accuracy are improved, and (3) memory requirement is cut down to a large extent. The advantages are substantiated by comparative experimental results.

168 citations


Proceedings ArticleDOI
07 Jul 2001
TL;DR: Experimental results show that fusion of evidences from multi-views can produce better results than using the result from a single view, and that this kernel machine based approach for learning nonlinear mappings for multi-view face detection and pose estimation yields high detection and low false alarm rates.
Abstract: Face images are subject to changes in view and illumination. Such changes cause data distribution to be highly nonlinear and complex in the image space. It is desirable to learn a nonlinear mapping from the image space to a low dimensional space such that the distribution becomes simpler tighter and therefore more predictable for better modeling effaces. In this paper we present a kernel machine based approach for learning such nonlinear mappings. The aim is to provide an effective view-based representation for multi-view face detection and pose estimation. Assuming that the view is partitioned into a number of distinct ranges, one nonlinear view-subspace is learned for each (range of) view from a set of example face images of that view (range), by using kernel principal component analysis (KPCA). Projections of the data onto the view-subspaces are then computed as view-based nonlinear features. Multi-view face detection and pose estimation are performed by classifying a face into one of the facial views or into the nonface class, by using a multi-class kernel support vector classifier (KSVC). Experimental results show that fusion of evidences from multi-views can produce better results than using the result from a single view; and that our approach yields high detection and low false alarm rates in face detection and good accuracy in pose estimation, in comparison with the linear counterpart composed of linear principal component analysis (PCA) feature extraction and Fisher linear discriminant based classification (FLDC).

127 citations


Proceedings ArticleDOI
01 Jan 2001
TL;DR: Experiments on a database composed of clips of 14870 seconds in total length show that the average accuracy rate for the SVM method is much better than that of the traditional Euclidean distance based (nearest neighbor) method.
Abstract: Audio exists at everywhere, but is often out-of-order. It is necessary to arrange them into regularized classes in order to use them more easily. It is also useful, especially in video content analysis, to segment an audio stream according to audio types. In this paper, we present our work in applying support vector machines (SVMs) in audio segmentation and classification. Five audio classes are considered: silence, music, background sound, pure speech, and non-pure speech which includes speech over music and speech over noise. A SVM learns optimal class boundaries from training data to best separate between two classes. A sound clip is segmented by classifying each sub-clip of one second into one of these five classes. Experiments on a database composed of clips of 14870 seconds in total length show that the average accuracy rate for the SVM method is much better than that of the traditional Euclidean distance based (nearest neighbor) method.

123 citations


Proceedings Article
Chao Huang1, Tao Chen, Stan Z. Li, Eric Chang, Jian-Lai Zhou 
01 Jan 2001
TL;DR: Two powerful multivariate statistical analysis methods, namely, principal component analysis (PCA) and independent componentAnalysis (ICA), are introduced as tools for analysis of speaker variability and extraction of low dimensional feature representation.
Abstract: Analysis and modeling of speaker variability, such as gender, accent, age, speech rate, and phones realizations, are important issues in speech recognition. It is known that existing feature representations describing speaker variations can be of very high dimension. In this paper, we introduce two powerful multivariate statistical analysis methods, namely, principal component analysis (PCA) and independent component analysis (ICA), as tools for analysis of such variability and extraction of low dimensional feature representation. Our findings are the following: (1) the first two principal components correspond to the gender and accent, respectively. The result that the second component corresponding to the accent has never been reported before, to the best of our knowledge. (2) It is shown that ICA based features yield better classification performance than PCA ones. Using 2dimensional ICA representation, we achieved about 6.1% and 13.3% error rate in gender and accent classification, respectively, for 980 speakers.

82 citations


Proceedings ArticleDOI
01 Oct 2001
TL;DR: A novel method for extracting features for the class of images represented by the positive images provided by subjective RF is proposed, using Principal Component Analysis (PCA) to reduce both noise contained in the original image features and dimensionality of feature spaces.
Abstract: In the past few years, relevance feedback (RF) has been used as an effective solution for content-based image retrieval (CBIR). Although effective, the RF-CBIR framework does not address the issue of feature extraction for dimension reduction and noise reduction. In this paper, we propose a novel method for extracting features for the class of images represented by the positive images provided by subjective RF. Principal Component Analysis (PCA) is used to reduce both noise contained in the original image features and dimensionality of feature spaces. The method increases the retrieval speed and reduces the memory significantly without sacrificing the retrieval accuracy.

79 citations


Proceedings ArticleDOI
08 Dec 2001
TL;DR: Experiments are presented which show that face detection performance is comparable to state-of-the-art face detection systems.
Abstract: This paper describes a face detection approach via learning local features. The key idea is that local features, being manifested by a collection of pixels in a local region, are learnt from the training set instead of arbitrarily defined. The learning procedure consists of two steps. First, a modified version of NMF (non-negative matrix factorization), namely local NMF (LNMF), is applied to obtain an overcomplete set of local features. Second, a learning algorithm based on AdaBoost is used to select a small number of local features and yields extremely efficient classifiers. Experiments are presented which show that face detection performance is comparable to state-of-the-art face detection systems.

55 citations


Journal ArticleDOI
TL;DR: In this paper, a set of Fe37Al specimens was oxidised for various periods of time, under thermal cycling conditions, to investigate the scale spallation properties, and the oxide products were examined using X-ray diffraction, scanning electron microscopy and atomic force microscopy.

44 citations


Proceedings ArticleDOI
07 Jul 2001
TL;DR: A pairwise classification framework for face recognition is developed, in which a C class face recognition problem is divided into a set of C(C-1)/2 two class problems, and it is shown that 20 features are enough to achieve a relatively high recognition accuracy.
Abstract: We develop a pairwise classification framework for face recognition, in which a C class face recognition problem is divided into a set of C(C-1)/2 two class problems. Such a problem decomposition not only leads to a set of simpler classification problems to be solved, thereby increasing overall classification accuracy, but also provides a framework for independent feature selection for each pair of classes. A simple feature ranking strategy is used to select a small subset of the features for each pair of classes. Furthermore, we evaluate two classification methods under the pairwise comparison framework: the Bayes classifier and the AdaBoost. Experiments on a large face database with 1079 face images of 137 individuals indicate that 20 features are enough to achieve a relatively high recognition accuracy, which demonstrates the effectiveness of the pairwise recognition framework.

Proceedings ArticleDOI
07 Jul 2001
TL;DR: This paper proposes a method for view-based unsupervised learning of object appearances, and is to the best of the knowledge the first devoted research on view- based clustering of images.
Abstract: In 3D object detection and recognition, an object of interest is subject to changes in view as well as in illumination and shape. For image classification purpose, it is desirable to derive a representation in which intrinsic characteristics of the object are captured in a low dimensional space while effects due to artifacts are reduced. In this paper, we propose a method for view-based unsupervised learning of object appearances. First, view-subspaces are learned from a view-unlabeled data set of multi-view appearances, using independent subspace analysis (ISA). A learned view-subspace provides a representation of appearances at that view, regardless of illumination effect. A measure, called view-subspace activity, is calculated thereby to provide a metric for view-based classification. View-based clustering is then performed by using maximum view-subspace activity (MVSA) criterion. This work is to the best of our knowledge the first devoted research on view-based clustering of images.

Proceedings ArticleDOI
01 Jan 2001
TL;DR: A recently proposed algorithm in machine learning called AdaBoost for content-based audio classification and retrieval is evaluated, which is a kind of large margin classifiers and is efficient for on-line learning.
Abstract: In this paper, we evaluate a recently proposed algorithm in machine learning called AdaBoost for content-based audio classification and retrieval. AdaBoost is a kind of large margin classifiers and is efficient for on-line learning. Our focus is to evaluate its classification and retrieval accuracy as compared with other methods. The Muscle Fish audio database of 409 sounds is used for the evaluation with perceptual and cepstral features.

Proceedings ArticleDOI
01 Dec 2001
TL;DR: This paper presents a novel framework for pose invariant face detection through multi-view face distribution modeling aimed to learn a set of low-dimensional subspaces from an originally nonlinear distribution by using the mixtures of probabilistic PCA.
Abstract: Modeling subspaces of a distribution of interest in high dimensional spaces is a challenging problem in pattern analysis. In this paper, we present a novel framework for pose invariant face detection through. multi-view face distribution modeling. The approach is aimed to learn a set of low-dimensional subspaces from an originally nonlinear distribution by using the mixtures of probabilistic PCA. From the experiments, we found the learned PPCA models are of low dimensionality and exhibit high local linearity, and consequently offer an efficient representation for visual recognition. The model is then used to extract features and select "representative" negative training samples. Multi-view face detection is performed in the derived feature space by classifying each face into one of the view classes or into the nonface class, by using a multi-class SVM array classifier. The classification results from each view are fused together and yields the final classification results. The experimental results demonstrate the performance superiority of our proposed framework while performing multi-view face detection.

Proceedings ArticleDOI
Li Zhao1, Wei Qi, Stan Z. Li, Shiqiang Yang, Hong-Jiang Zhang 
07 May 2001
TL;DR: This work improved the original NFL method by adding constraints on the feature lines and shows that the improved NFL method is better than the traditional classification methods such as nearest neighbor (NN) and nearest center (NC).
Abstract: Shot-based classification and retrieval is very important for video database organization and access. We present a new approach: 'nearest feature line - NFL' used in shot retrieval. We look at key-frames in a shot as feature points to represent the shot in feature space. Lines connecting the feature points are further used to approximate the variations in the whole shot. The similarity between the query image and the shots in video database are measured by calculating the distance between the query image and the feature lines in feature space. To make it more suited to video data, we improved the original NFL method by adding constraints on the feature lines. Experimental results show that our improved NFL method is better than the traditional classification methods such as nearest neighbor (NN) and nearest center (NC).

Proceedings ArticleDOI
07 May 2001
TL;DR: Experimental results on the Brodatz texture database indicate that a significantly better retrieval performance can be achieved as compared to the traditional Euclidean distance-based approach.
Abstract: A new metric is proposed for texture image retrieval, which is based on the signed distance of the images in the database to a boundary chosen by the query. This novel metric has three advantages: (1) the boundary distance measures are relatively insensitive to the sample distributions; (2) the same retrieval results can be obtained with respect to different (but visually similar) queries; (3) retrieval performance can be improved. The boundaries are obtained by using a statistical learning algorithm called support vector machine (SVM), and hence the boundaries can be simply represented by some vectors and their combination coefficients. Experimental results on the Brodatz texture database indicate that a significantly better retrieval performance can be achieved as compared to the traditional Euclidean distance-based approach. This technique can be further developed to learn pattern similarities among different texture classes and used in relevance feedback.

Proceedings ArticleDOI
07 Oct 2001
TL;DR: A new algorithm is proposed to extract the facial features and estimate the control points for facial image warping using the principle component analysis (PCA) based statistic face model.
Abstract: A new algorithm is proposed to extract the facial features and estimate the control points for facial image warping using the principle component analysis (PCA) based statistic face model. In this algorithm, first a full-face model consisting the contour points and the control points is built. Based on a number of manually marked training samples, the prior distribution of the full-face model can be obtained by using the PCA. Given an input face image, first the contour points are obtained by using the Bayesian shape model (BSM), and then the control points are estimated from the contour points. Finally, the extracted face path is normalized using the piece-wise affine triangle warping algorithm. Experimental results illustrate the effectiveness of the proposed algorithm.

Proceedings ArticleDOI
13 Jul 2001
TL;DR: A nonlinear mapping by which multi-view face patterns in the input space are mapped into invariant points in a low dimensional feature space is investigated and the Gaussian face distribution is explored and supported by experiments.
Abstract: We investigate into a nonlinear mapping by which multi-view face patterns in the input space are mapped into invariant points in a low dimensional feature space. The invariance to both illumination and view is achieved in two-stages. First, a nonlinear mapping from the input space to a low dimensional feature space is learned from multi-view face examples to achieve illumination invariance. The illumination invariant feature points of face patterns across views are on a curve parameterized by the view parameter, and the view parameter of a face pattern can be estimated from the location of the feature point on the curve by using least squares fit. Then the second nonlinear mapping, which is from the illumination invariant feature space to another feature space of the same dimension, is performed to achieve invariance to both illumination and view. This amounts to do a normalization based on the view estimate. By the two stage nonlinear mapping, multi-view face patterns are mapped to a zero mean Gaussian distribution in the latter feature space. Properties of the nonlinear mappings and the Gaussian face distribution are explored and supported by experiments.

Journal ArticleDOI
TL;DR: In this article, the effect of mechanical deformation on the texture evolution during powder-in-tube (PIT) processing remains unclear, especially on the microstructural level, and the micro and meso-texture characteristics of PIT-processed (Bi, Pb)2Sr2Ca2Cu3O10 (Bi2223) superconductor tapes were investigated.
Abstract: Grain boundary misorientation is known to limit the critical current density of bulk high temperature superconductors. However, the effect of mechanical deformation on the texture evolution during powder-in-tube (PIT) processing remains unclear, especially on the microstructural level. In the present work, the micro- and meso-texture characteristics of PIT-processed (Bi, Pb)2Sr2Ca2Cu3O10 (Bi2223) superconductor tapes were investigated. The results for micro-texture show that a/b-axes texture does exist in PIT-processed tapes. From the meso-texture studies, it was found that a majority of the grain boundaries were formed by grains with a non-parallel c-axis. These grain boundaries generally have low mismatch angles of up to ~10°. High-angle misorientation boundaries ranging up to 45° are generally c-axis twist boundaries. Furthermore, about 40% of the grain boundaries could be coupled strongly.

Proceedings ArticleDOI
Stan Z. Li1, Jie Yan, Xinwen Hou, Ze Yu Li, Hong-Jiang Zhang 
07 Jul 2001
TL;DR: An invariant signature representation for appearances of 3-D object under varying view and illumination, and a method for learning the signature from multi-view appearance examples are proposed and shown that the face object can be effectively, modeled compactly in a 10-D nonlinear feature space.
Abstract: In this paper, we propose an invariant signature representation for appearances of 3-D object under varying view and illumination, and a method for learning the signature from multi-view appearance examples. The signature, a nonlinear feature, provides a good basis for 3-D object detection and pose estimation due to its following properties. (I) Its location in the signature feature space is a simple function of the view and is insensitive or invariant to illumination. (2) It changes continuously as the view changes, so that the object appearances at all possible views should constitute a known simple curve segment (manifold) in the feature space. (3) The coordinates of rite object appearances in the feature space are correlated in a known way according to a predefined function of the view. The first two properties provide a basis for object detection and the third for view (pose) estimation. To compute the signature representation from input, we present a nonlinear regression method for learning a nonlinear mapping from the input (e.g. image) space to the feature space. The ideas of the signature representation and the learning method are illustrated with experimental results for the object of human face. It is shown that the face object can be effectively, modeled compactly in a 10-D nonlinear feature space. The 10-D signature presents excellent insensitivity to changes in illumination for any view. The correlation of the signature coordinates is well determined by the predefined parametric function. Applications of the proposed method in face detection and pose estimation are demonstrated.

Journal ArticleDOI
TL;DR: In this paper, the electron backscattered diffraction technique was employed to map the crystallographic orientation distribution, determine the misorientation of grain boundaries and also map the misoriented distribution in Bi2223 superconductor tapes.
Abstract: It is believed that grain boundaries act as weak links in limiting the critical current density (Jc) of bulk high-Tc superconductors. The weak-link problem can be greatly reduced by elimination or minimization of large-angle grain boundaries. It has been reported that the distribution of the Jc in (Bi, Pb)2Sr2Ca2Cu3O10+x (Bi2223) superconductor tapes presents a parabolic relationship in the transverse cross section of the tapes, with the lowest currents occurring at the centre of the tapes. It was proposed that the Jc distribution is strongly dependent on the local crystallographic orientation distribution of the Bi2223 oxides. However, the local three-dimensional crystallographic orientation distribution of Bi2223 crystals in (Bi, Pb)2Sr2Ca2Cu3O10+x superconductor tapes has not yet been experimentally determined. In this work, the electron backscattered diffraction technique was employed to map the crystallographic orientation distribution, determine the misorientation of grain boundaries and also map the misorientation distribution in Bi2223 superconductor tapes. Through crystallographic orientation mapping, the relationship between the crystallographic orientation distribution, the boundary misorientation distribution and the fabrication parameters may be understood. This can be used to optimize the fabrication processes thus increasing the critical current density in Bi2223 superconductor tapes.

Journal ArticleDOI
01 Apr 2001
TL;DR: A belief networks method for rule mining, which takes the advantage of belief networks as the directed acyclic graph language and their function for numerical representation of probabilistic dependencies among the variables in the database, so that it can overcome the drawbacks of existing data mining methods.
Abstract: Some existing data mining methods, such as classification trees, neural networks and association rules, have the drawbacks that the user's prior knowledge cannot be easily specified and incorporated into the knowledge discovery process, and the rules mined from databases lack quantitative analyses. In this paper, we propose a belief networks method for rule mining, which takes the advantage of belief networks as the directed acyclic graph language and their function for numerical representation of probabilistic dependencies among the variables in the database, so that it can overcome the drawbacks. Since belief networks provide a natural representation for capturing causal relationship among a set of variables, our proposed method can mine more general correlation rules which can capture the relationship of more than two attribute variables. The potential application of the proposed method is demonstrated through the detailed case studies on benchmark databases.

Proceedings ArticleDOI
13 Jul 2001
TL;DR: In this paper, view-specific basis components can be learned from multi-view face examples in an unsupervised way by using ICA, ISA and TICA; whereas the components learned by using principal component analysis reveal little view-related information.
Abstract: Multi-view face detection and recognition has been a challenging problem. The challenge is due to the fact that the distribution of multi-view faces in a feature space is more dispersed and more complicated than that of frontal faces. This paper presents an investigation into several view-subspace representations of multi-view faces: learning by using independent component analysis (ICA), independent subspace analysis (ISA) and topographic independent component analysis (TICA). It is shown that view-specific basis components can be learned from multi-view face examples in an unsupervised way by using ICA, ISA and TICA; whereas the components learned by using principal component analysis reveal little view-related information. The learned results provide sensible basis for constructing view-subspaces for multi-view faces. Comparative experiments demonstrate distinctive properties of ICA, ISA and TICA results, and the suitability of the results as representations of multi-view faces.

Journal ArticleDOI
TL;DR: In this paper, the phase transformation process of Bi-Sr-Ca-Cu-O (BSCCO) tapes processed by cryogenic, 77 K and room temperature pressing was investigated.
Abstract: The current investigation studies the phase transformation process of Bi-Sr-Ca-Cu-O (BSCCO) tapes processed by cryogenic, 77 K and room temperature pressing. The work specifically examined the effect of deformation on the phase content and transformation kinetics of the BSCCO tapes. The results showed that cryogenic pressing produced tapes with a higher Bi2223 phase content at lower deformation ratios than room temperature pressed tapes. However, the phase transformation profiles for both tapes were similar. A minimum phase content was observed in the profiles that was characteristic to each process. The minimum occurred between 30-40% deformation for the cryogenically pressed tapes and between 50-60% for the room temperature pressed tapes. The peculiar profiles were suggested to be the result of two competing mechanisms that reduced the free energy of the systems. It was suggested that these two mechanisms were either Bi2212 re-crystallization or Bi2223 phase formation. The differences observed between the two processes were attributed to the amount and way in which the deformation energy was transferred to the tape.

Proceedings ArticleDOI
22 Aug 2001
TL;DR: Experiments on a database composed of clips of 14870 seconds in total length show that the average accuracy rate for the SVM method is much better than that of the traditional Euclidean distance based (nearest neighbor) method.
Abstract: Audio exists at everywhere, but is often out-of-order It is necessary to arrange them into regularized classes in order to use them more easily It is also useful, especially in video content analysis, to segment an audio stream according to audio types In this paper, we present our work in applying support vector machines (SVMs) in audio segmentation and classification Five audio classes are considered: silence, music, background sound, pure speech, and non-pure speech which includes speech over music and speech over noise A SVM learns optimal class boundaries from training data to best separate between two classes A sound clip is segmented by classifying each sub-clip of one second into one of these five classes Experiments on a database composed of clips of 14870 seconds in total length show that the average accuracy rate for the SVM method is much better than that of the traditional Euclidean distance based (nearest neighbor) method

Proceedings ArticleDOI
Stan Z. Li1, XiaoGuang Lv, Hong-Jiang Zhang, QingDong Fu, Yimin Cheng 
07 May 2001
TL;DR: A method for learning a representation from a set of un-labeled images containing the appearances of the object viewed from various poses and in various illuminations for appearance based multi-view object detection and recognition is proposed.
Abstract: In 3D object detection and recognition, the object of interest in an image is subject to changes in view-point as well as illumination. It is benefit for the detection and recognition if a representation can be derived to account for view and illumination changes in an effective and meaningful way. In this paper, we propose a method for learning such a representation from a set of un-labeled images containing the appearances of the object viewed from various poses and in various illuminations. Topographic Independent Component Analysis (TICA) is applied for the unsupervised learning to produce an emergent result, that is a topographic map of basis components. The map is topographic in the following sense: the basis components as the units of the map are ordered in the 2D map such that components of similar viewing angle are group in one axis and changes in illumination are accounted for in the other axis. This provides a meaningful set of basis vectors that may be used to construct view subspaces for appearance based multi-view object detection and recognition.

Journal ArticleDOI
TL;DR: In this article, the intrinsic grain alignment characteristics of Bi-Sr-Ca-Cu-O tapes were studied and it was reported that the critical current density of superconducting tapes can be improved using cryogenic processing.
Abstract: It was reported that the critical current density of superconducting tapes can be improved using cryogenic processing. The present paper studies the intrinsic grain alignment characteristics of cryogenically pressed and room-temperature-pressed Bi-Sr-Ca-Cu-O tapes. The grain alignment mechanisms of the two processed tapes were found to be different. The cryogenically pressed tapes showed a step-like increase in grain alignment at approximately 30% deformation, while the increase in grain alignment for the room-temperature-pressed tapes was gradual. The results indicate that the behaviour is reproducible and independent of annealing time and therefore, intrinsic to the deformation steps of each process. The effects of deformation on the alignment are suggested to occur due to two factors: (1) the point at which fracturing of the grains occurs and (2) rotation or movement of these grains into the preferred alignment. The differences observed between the two processes are due to the combined effects of these two factors. The significance of this study is that better grain alignment can be achieved in cryogenically pressed tapes at lower deformation ratios.