Showing papers on "Feature extraction published in 2011"
TL;DR: A novel feature similarity (FSIM) index for full reference IQA is proposed based on the fact that human visual system (HVS) understands an image mainly according to its low-level features.
Abstract: Image quality assessment (IQA) aims to use computational models to measure the image quality consistently with subjective evaluations. The well-known structural similarity index brings IQA from pixel- to structure-based stage. In this paper, a novel feature similarity (FSIM) index for full reference IQA is proposed based on the fact that human visual system (HVS) understands an image mainly according to its low-level features. Specifically, the phase congruency (PC), which is a dimensionless measure of the significance of a local structure, is used as the primary feature in FSIM. Considering that PC is contrast invariant while the contrast information does affect HVS' perception of image quality, the image gradient magnitude (GM) is employed as the secondary feature in FSIM. PC and GM play complementary roles in characterizing the image local quality. After obtaining the local quality map, we use PC again as a weighting function to derive a single quality score. Extensive experiments performed on six benchmark IQA databases demonstrate that FSIM can achieve much higher consistency with the subjective evaluations than state-of-the-art IQA metrics.
4,028 citations
20 Jun 2011
TL;DR: This work proposes a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence, and consistently outperformed existing saliency detection methods.
Abstract: Automatic estimation of salient object regions across images, without any prior assumption or knowledge of the contents of the corresponding scenes, enhances many computer vision and computer graphics applications. We introduce a regional contrast based salient object detection algorithm, which simultaneously evaluates global contrast differences and spatial weighted coherence scores. The proposed algorithm is simple, efficient, naturally multi-scale, and produces full-resolution, high-quality saliency maps. These saliency maps are further used to initialize a novel iterative version of GrabCut, namely SaliencyCut, for high quality unsupervised salient object segmentation. We extensively evaluated our algorithm using traditional salient object detection datasets, as well as a more challenging Internet image dataset. Our experimental results demonstrate that our algorithm consistently outperforms 15 existing salient object detection and segmentation methods, yielding higher precision and better recall rates. We also show that our algorithm can be used to efficiently extract salient object masks from Internet images, enabling effective sketch-based image retrieval (SBIR) via simple shape comparisons. Despite such noisy internet images, where the saliency regions are ambiguous, our saliency guided image retrieval achieves a superior retrieval rate compared with state-of-the-art SBIR methods, and additionally provides important target object region information.
3,653 citations
TL;DR: This work proposes a novel dimensionality reduction framework for reducing the distance between domains in a latent space for domain adaptation and proposes both unsupervised and semisupervised feature extraction approaches, which can dramatically reduce thedistance between domain distributions by projecting data onto the learned transfer components.
Abstract: Domain adaptation allows knowledge from a source domain to be transferred to a different but related target domain. Intuitively, discovering a good feature representation across domains is crucial. In this paper, we first propose to find such a representation through a new learning method, transfer component analysis (TCA), for domain adaptation. TCA tries to learn some transfer components across domains in a reproducing kernel Hilbert space using maximum mean miscrepancy. In the subspace spanned by these transfer components, data properties are preserved and data distributions in different domains are close to each other. As a result, with the new representations in this subspace, we can apply standard machine learning methods to train classifiers or regression models in the source domain for use in the target domain. Furthermore, in order to uncover the knowledge hidden in the relations between the data labels from the source and target domains, we extend TCA in a semisupervised learning setting, which encodes label information into transfer components learning. We call this extension semisupervised TCA. The main contribution of our work is that we propose a novel dimensionality reduction framework for reducing the distance between domains in a latent space for domain adaptation. We propose both unsupervised and semisupervised feature extraction approaches, which can dramatically reduce the distance between domain distributions by projecting data onto the learned transfer components. Finally, our approach can handle large datasets and naturally lead to out-of-sample generalization. The effectiveness and efficiency of our approach are verified by experiments on five toy datasets and two real-world applications: cross-domain indoor WiFi localization and cross-domain text classification.
3,195 citations
20 Jun 2011
TL;DR: This work introduces a novel descriptor based on motion boundary histograms, which is robust to camera motion and consistently outperforms other state-of-the-art descriptors, in particular in uncontrolled realistic videos.
Abstract: Feature trajectories have shown to be efficient for representing videos. Typically, they are extracted using the KLT tracker or matching SIFT descriptors between frames. However, the quality as well as quantity of these trajectories is often not sufficient. Inspired by the recent success of dense sampling in image classification, we propose an approach to describe videos by dense trajectories. We sample dense points from each frame and track them based on displacement information from a dense optical flow field. Given a state-of-the-art optical flow algorithm, our trajectories are robust to fast irregular motions as well as shot boundaries. Additionally, dense trajectories cover the motion information in videos well. We, also, investigate how to design descriptors to encode the trajectory information. We introduce a novel descriptor based on motion boundary histograms, which is robust to camera motion. This descriptor consistently outperforms other state-of-the-art descriptors, in particular in uncontrolled realistic videos. We evaluate our video description in the context of action classification with a bag-of-features approach. Experimental results show a significant improvement over the state of the art on four datasets of varying difficulty, i.e. KTH, YouTube, Hollywood2 and UCF sports.
2,383 citations
TL;DR: A set of novel features, including multiscale contrast, center-surround histogram, and color spatial distribution, are proposed to describe a salient object locally, regionally, and globally.
Abstract: In this paper, we study the salient object detection problem for images. We formulate this problem as a binary labeling task where we separate the salient object from the background. We propose a set of novel features, including multiscale contrast, center-surround histogram, and color spatial distribution, to describe a salient object locally, regionally, and globally. A conditional random field is learned to effectively combine these features for salient object detection. Further, we extend the proposed approach to detect a salient object from sequential images by introducing the dynamic salient features. We collected a large image database containing tens of thousands of carefully labeled images by multiple users and a video segment database, and conducted a set of experiments over them to demonstrate the effectiveness of the proposed approach.
2,319 citations
Proceedings Article•
14 Jun 2011TL;DR: In this paper, the authors show that the number of hidden nodes in the model may be more important to achieving high performance than the learning algorithm or the depth of the model, and they apply several othe-shelf feature learning algorithms (sparse auto-encoders, sparse RBMs, K-means clustering, and Gaussian mixtures) to CIFAR, NORB, and STL datasets using only single-layer networks.
Abstract: A great deal of research has focused on algorithms for learning features from unlabeled data. Indeed, much progress has been made on benchmark datasets like NORB and CIFAR by employing increasingly complex unsupervised learning algorithms and deep models. In this paper, however, we show that several simple factors, such as the number of hidden nodes in the model, may be more important to achieving high performance than the learning algorithm or the depth of the model. Specifically, we will apply several othe-shelf feature learning algorithms (sparse auto-encoders, sparse RBMs, K-means clustering, and Gaussian mixtures) to CIFAR, NORB, and STL datasets using only singlelayer networks. We then present a detailed analysis of the eect of changes in the model setup: the receptive field size, number of hidden nodes (features), the step-size (“stride”) between extracted features, and the eect of whitening. Our results show that large numbers of hidden nodes and dense feature extraction are critical to achieving high performance—so critical, in fact, that when these parameters are pushed to their limits, we achieve state-of-the-art performance on both CIFAR-10 and NORB using only a single layer of features. More surprisingly, our best performance is based on K-means clustering, which is extremely fast, has no hyperparameters to tune beyond the model structure itself, and is very easy to implement. Despite the simplicity of our system, we achieve accuracy beyond all previously published results on the CIFAR-10 and NORB datasets (79.6% and 97.2% respectively).
2,091 citations
06 Nov 2011
TL;DR: It is demonstrated that a dense model permits superior tracking performance under rapid motion compared to a state of the art method using features; and the additional usefulness of the dense model for real-time scene interaction in a physics-enhanced augmented reality application is shown.
Abstract: DTAM is a system for real-time camera tracking and reconstruction which relies not on feature extraction but dense, every pixel methods. As a single hand-held RGB camera flies over a static scene, we estimate detailed textured depth maps at selected keyframes to produce a surface patchwork with millions of vertices. We use the hundreds of images available in a video stream to improve the quality of a simple photometric data term, and minimise a global spatially regularised energy functional in a novel non-convex optimisation framework. Interleaved, we track the camera's 6DOF motion precisely by frame-rate whole image alignment against the entire dense model. Our algorithms are highly parallelisable throughout and DTAM achieves real-time performance using current commodity GPU hardware. We demonstrate that a dense model permits superior tracking performance under rapid motion compared to a state of the art method using features; and also show the additional usefulness of the dense model for real-time scene interaction in a physics-enhanced augmented reality application.
2,001 citations
14 Jun 2011
TL;DR: A novel convolutional auto-encoder (CAE) for unsupervised feature learning that initializing a CNN with filters of a trained CAE stack yields superior performance on a digit and an object recognition benchmark.
Abstract: We present a novel convolutional auto-encoder (CAE) for unsupervised feature learning. A stack of CAEs forms a convolutional neural network (CNN). Each CAE is trained using conventional on-line gradient descent without additional regularization terms. A max-pooling layer is essential to learn biologically plausible features consistent with those found by previous approaches. Initializing a CNN with filters of a trained CAE stack yields superior performance on a digit (MNIST) and an object recognition (CIFAR10) benchmark.
1,832 citations
11 Mar 2011
TL;DR: The paper presents a methodology for face recognition based on information theory approach of coding and decoding the face image using Principle Component Analysis and recognition using the feed forward back propagation Neural Network.
Abstract: Face is a complex multidimensional visual model and developing a computational model for face recognition is difficult. The paper presents a methodology for face recognition based on information theory approach of coding and decoding the face image. Proposed methodology is connection of two stages - Feature extraction using Principle Component Analysis and recognition using the feed forward back propagation Neural Network. The goal is to implement the system (model) for a particular face and distinguish it from a large number of stored faces with some real-time variations as well. The Eigenface approach uses Principal Component Analysis (PCA) algorithm for the recognition of the images. It gives us efficient way to find the lower dimensional space.
1,727 citations
06 Nov 2011
TL;DR: A simple yet effective method for combining generic object detectors with bottom-up contours to identify object contours is presented and a principled way of combining information from different part detectors and across categories is provided.
Abstract: We study the challenging problem of localizing and classifying category-specific object contours in real world images. For this purpose, we present a simple yet effective method for combining generic object detectors with bottom-up contours to identify object contours. We also provide a principled way of combining information from different part detectors and across categories. In order to study the problem and evaluate quantitatively our approach, we present a dataset of semantic exterior boundaries on more than 20, 000 object instances belonging to 20 categories, using the images from the VOC2011 PASCAL challenge [7].
1,596 citations
TL;DR: DIIVINE is capable of assessing the quality of a distorted image across multiple distortion categories, as against most NR IQA algorithms that are distortion-specific in nature, and is statistically superior to the often used measure of peak signal-to-noise ratio (PSNR) and statistically equivalent to the popular structural similarity index (SSIM).
Abstract: Our approach to blind image quality assessment (IQA) is based on the hypothesis that natural scenes possess certain statistical properties which are altered in the presence of distortion, rendering them un-natural; and that by characterizing this un-naturalness using scene statistics, one can identify the distortion afflicting the image and perform no-reference (NR) IQA. Based on this theory, we propose an (NR)/blind algorithm-the Distortion Identification-based Image Verity and INtegrity Evaluation (DIIVINE) index-that assesses the quality of a distorted image without need for a reference image. DIIVINE is based on a 2-stage framework involving distortion identification followed by distortion-specific quality assessment. DIIVINE is capable of assessing the quality of a distorted image across multiple distortion categories, as against most NR IQA algorithms that are distortion-specific in nature. DIIVINE is based on natural scene statistics which govern the behavior of natural images. In this paper, we detail the principles underlying DIIVINE, the statistical features extracted and their relevance to perception and thoroughly evaluate the algorithm on the popular LIVE IQA database. Further, we compare the performance of DIIVINE against leading full-reference (FR) IQA algorithms and demonstrate that DIIVINE is statistically superior to the often used measure of peak signal-to-noise ratio (PSNR) and statistically equivalent to the popular structural similarity index (SSIM). A software release of DIIVINE has been made available online: http://live.ece.utexas.edu/research/quality/DIIVINE_release.zip for public use and evaluation.
09 May 2011
TL;DR: This work describes a new visual fiducial system that uses a 2D bar code style “tag”, allowing full 6 DOF localization of features from a single image, incorporating a fast and robust line detection system, a stronger digital coding system, and greater robustness to occlusion, warping, and lens distortion.
Abstract: While the use of naturally-occurring features is a central focus of machine perception, artificial features (fiducials) play an important role in creating controllable experiments, ground truthing, and in simplifying the development of systems where perception is not the central objective. We describe a new visual fiducial system that uses a 2D bar code style “tag”, allowing full 6 DOF localization of features from a single image. Our system improves upon previous systems, incorporating a fast and robust line detection system, a stronger digital coding system, and greater robustness to occlusion, warping, and lens distortion. While similar in concept to the ARTag system, our method is fully open and the algorithms are documented in detail.
06 Nov 2011
TL;DR: A hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling, relying on a novel inference scheme that ensures each layer reconstructs the input, rather than just the output of the layer directly beneath, as is common with existing hierarchical approaches.
Abstract: We present a hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling. When trained on natural images, the layers of our model capture image information in a variety of forms: low-level edges, mid-level edge junctions, high-level object parts and complete objects. To build our model we rely on a novel inference scheme that ensures each layer reconstructs the input, rather than just the output of the layer directly beneath, as is common with existing hierarchical approaches. This makes it possible to learn multiple layers of representation and we show models with 4 layers, trained on images from the Caltech-101 and 256 datasets. When combined with a standard classifier, features extracted from these models outperform SIFT, as well as representations from other feature learning methods.
09 Jun 2011
TL;DR: Ilastik as mentioned in this paper is an easy-to-use tool which allows the user without expertise in image processing to perform segmentation and classification in a unified way, based on labels provided by the user through a convenient mouse interface.
Abstract: Segmentation is the process of partitioning digital images into meaningful regions. The analysis of biological high content images often requires segmentation as a first step. We propose ilastik as an easy-to-use tool which allows the user without expertise in image processing to perform segmentation and classification in a unified way. ilastik learns from labels provided by the user through a convenient mouse interface. Based on these labels, ilastik infers a problem specific segmentation. A random forest classifier is used in the learning step, in which each pixel's neighborhood is characterized by a set of generic (nonlinear) features. ilastik supports up to three spatial plus one spectral dimension and makes use of all dimensions in the feature calculation. ilastik provides realtime feedback that enables the user to interactively refine the segmentation result and hence further fine-tune the classifier. An uncertainty measure guides the user to ambiguous regions in the images. Real time performance is achieved by multi-threading which fully exploits the capabilities of modern multi-core machines. Once a classifier has been trained on a set of representative images, it can be exported and used to automatically process a very large number of images (e.g. using the CellProfiler pipeline). ilastik is an open source project and released under the BSD license at www.ilastik.org.
20 Jun 2011
TL;DR: This paper presents an extension of the Independent Subspace Analysis algorithm to learn invariant spatio-temporal features from unlabeled video data and discovered that this method performs surprisingly well when combined with deep learning techniques such as stacking and convolution to learn hierarchical representations.
Abstract: Previous work on action recognition has focused on adapting hand-designed local features, such as SIFT or HOG, from static images to the video domain. In this paper, we propose using unsupervised feature learning as a way to learn features directly from video data. More specifically, we present an extension of the Independent Subspace Analysis algorithm to learn invariant spatio-temporal features from unlabeled video data. We discovered that, despite its simplicity, this method performs surprisingly well when combined with deep learning techniques such as stacking and convolution to learn hierarchical representations. By replacing hand-designed features with our learned features, we achieve classification results superior to all previous published results on the Hollywood2, UCF, KTH and YouTube action recognition datasets. On the challenging Hollywood2 and YouTube action datasets we obtain 53.3% and 75.8% respectively, which are approximately 5% better than the current best published results. Further benefits of this method, such as the ease of training and the efficiency of training and prediction, will also be discussed. You can download our code and learned spatio-temporal features here: http://ai.stanford.edu/∼wzou/
TL;DR: Results showed that the best RCSP methods can outperform CSP by nearly 10% in median classification accuracy and lead to more neurophysiologically relevant spatial filters and enable us to perform efficient subject-to-subject transfer.
Abstract: One of the most popular feature extraction algorithms for brain-computer interfaces (BCI) is common spatial patterns (CSPs). Despite its known efficiency and widespread use, CSP is also known to be very sensitive to noise and prone to overfitting. To address this issue, it has been recently proposed to regularize CSP. In this paper, we present a simple and unifying theoretical framework to design such a regularized CSP (RCSP). We then present a review of existing RCSP algorithms and describe how to cast them in this framework. We also propose four new RCSP algorithms. Finally, we compare the performances of 11 different RCSP (including the four new ones and the original CSP), on electroencephalography data from 17 subjects, from BCI competition datasets. Results showed that the best RCSP methods can outperform CSP by nearly 10% in median classification accuracy and lead to more neurophysiologically relevant spatial filters. They also enable us to perform efficient subject-to-subject transfer. Overall, the best RCSP algorithms were CSP with Tikhonov regularization and weighted Tikhonov regularization, both proposed in this paper.
TL;DR: A neural network scheme for pixel classification and computes a 7-D vector composed of gray-level and moment invariants-based features for pixel representation that is suitable for retinal image computer analyses such as automated screening for early diabetic retinopathy detection.
Abstract: This paper presents a new supervised method for blood vessel detection in digital retinal images. This method uses a neural network (NN) scheme for pixel classification and computes a 7-D vector composed of gray-level and moment invariants-based features for pixel representation. The method was evaluated on the publicly available DRIVE and STARE databases, widely used for this purpose, since they contain retinal images where the vascular structure has been precisely marked by experts. Method performance on both sets of test images is better than other existing solutions in literature. The method proves especially accurate for vessel detection in STARE images. Its application to this database (even when the NN was trained on the DRIVE database) outperforms all analyzed segmentation approaches. Its effectiveness and robustness with different image conditions, together with its simplicity and fast implementation, make this blood vessel segmentation proposal suitable for retinal image computer analyses such as automated screening for early diabetic retinopathy detection.
01 Nov 2011
TL;DR: As a typical application of the LBP approach, LBP-based facial image analysis is extensively reviewed, while its successful extensions, which deal with various tasks of facial imageAnalysis, are also highlighted.
Abstract: Local binary pattern (LBP) is a nonparametric descriptor, which efficiently summarizes the local structures of images. In recent years, it has aroused increasing interest in many areas of image processing and computer vision and has shown its effectiveness in a number of applications, in particular for facial image analysis, including tasks as diverse as face detection, face recognition, facial expression analysis, and demographic classification. This paper presents a comprehensive survey of LBP methodology, including several more recent variations. As a typical application of the LBP approach, LBP-based facial image analysis is extensively reviewed, while its successful extensions, which deal with various tasks of facial image analysis, are also highlighted.
TL;DR: The problem of detecting if an image has been forged is investigated; in particular, attention has been paid to the case in which an area of an image is copied and then pasted onto another zone to create a duplication or to cancel something that was awkward.
Abstract: One of the principal problems in image forensics is determining if a particular image is authentic or not. This can be a crucial task when images are used as basic evidence to influence judgment like, for example, in a court of law. To carry out such forensic analysis, various technological instruments have been developed in the literature. In this paper, the problem of detecting if an image has been forged is investigated; in particular, attention has been paid to the case in which an area of an image is copied and then pasted onto another zone to create a duplication or to cancel something that was awkward. Generally, to adapt the image patch to the new context a geometric transformation is needed. To detect such modifications, a novel methodology based on scale invariant features transform (SIFT) is proposed. Such a method allows us to both understand if a copy-move attack has occurred and, furthermore, to recover the geometric transformation used to perform cloning. Extensive experimental results are presented to confirm that the technique is able to precisely individuate the altered area and, in addition, to estimate the geometric transformation parameters with high reliability. The method also deals with multiple cloning.
20 Jun 2011
TL;DR: A novel Probabilistic Relative Distance Comparison (PRDC) model is introduced, which differs from most existing distance learning methods in that it aims to maximise the probability of a pair of true match having a smaller distance than that of a wrong match pair, which makes the model more tolerant to appearance changes and less susceptible to model over-fitting.
Abstract: Matching people across non-overlapping camera views, known as person re-identification, is challenging due to the lack of spatial and temporal constraints and large visual appearance changes caused by variations in view angle, lighting, background clutter and occlusion. To address these challenges, most previous approaches aim to extract visual features that are both distinctive and stable under appearance changes. However, most visual features and their combinations under realistic conditions are neither stable nor distinctive thus should not be used indiscriminately. In this paper, we propose to formulate person re-identification as a distance learning problem, which aims to learn the optimal distance that can maximises matching accuracy regardless the choice of representation. To that end, we introduce a novel Probabilistic Relative Distance Comparison (PRDC) model, which differs from most existing distance learning methods in that, rather than minimising intra-class variation whilst maximising intra-class variation, it aims to maximise the probability of a pair of true match having a smaller distance than that of a wrong match pair. This makes our model more tolerant to appearance changes and less susceptible to model over-fitting. Extensive experiments are carried out to demonstrate that 1) by formulating the person re-identification problem as a distance learning problem, notable improvement on matching accuracy can be obtained against conventional person re-identification techniques, which is particularly significant when the training sample size is small; and 2) our PRDC outperforms not only existing distance learning methods but also alternative learning methods based on boosting and learning to rank.
TL;DR: A new method for the detection of P300 waves is presented, based on a convolutional neural network (CNN), which provides a new way for analyzing brain activities due to the receptive field of the CNN models.
Abstract: A Brain-Computer Interface (BCI) is a specific type of human-computer interface that enables the direct communication between human and computers by analyzing brain measurements. Oddball paradigms are used in BCI to generate event-related potentials (ERPs), like the P300 wave, on targets selected by the user. A P300 speller is based on this principle, where the detection of P300 waves allows the user to write characters. The P300 speller is composed of two classification problems. The first classification is to detect the presence of a P300 in the electroencephalogram (EEG). The second one corresponds to the combination of different P300 responses for determining the right character to spell. A new method for the detection of P300 waves is presented. This model is based on a convolutional neural network (CNN). The topology of the network is adapted to the detection of P300 waves in the time domain. Seven classifiers based on the CNN are proposed: four single classifiers with different features set and three multiclassifiers. These models are tested and compared on the Data set II of the third BCI competition. The best result is obtained with a multiclassifier solution with a recognition rate of 95.5 percent, without channel selection before the classification. The proposed approach provides also a new way for analyzing brain activities due to the receptive field of the CNN models.
06 Nov 2011
TL;DR: This paper proposes to construct the dictionary by using both observed and unobserved, hidden data, and shows that the effects of the hidden data can be approximately recovered by solving a nuclear norm minimization problem, which is convex and can be solved efficiently.
Abstract: Low-Rank Representation (LRR) [16, 17] is an effective method for exploring the multiple subspace structures of data. Usually, the observed data matrix itself is chosen as the dictionary, which is a key aspect of LRR. However, such a strategy may depress the performance, especially when the observations are insufficient and/or grossly corrupted. In this paper we therefore propose to construct the dictionary by using both observed and unobserved, hidden data. We show that the effects of the hidden data can be approximately recovered by solving a nuclear norm minimization problem, which is convex and can be solved efficiently. The formulation of the proposed method, called Latent Low-Rank Representation (LatLRR), seamlessly integrates subspace segmentation and feature extraction into a unified framework, and thus provides us with a solution for both subspace segmentation and feature extraction. As a subspace segmentation algorithm, LatLRR is an enhanced version of LRR and outperforms the state-of-the-art algorithms. Being an unsupervised feature extraction algorithm, LatLRR is able to robustly extract salient features from corrupted data, and thus can work much better than the benchmark that utilizes the original data vectors as features for classification. Compared to dimension reduction based methods, LatLRR is more robust to noise.
01 Nov 2011
TL;DR: Methods for video structure analysis, including shot boundary detection, key frame extraction and scene segmentation, extraction of features including static key frame features, object features and motion features, video data mining, video annotation, and video retrieval including query interfaces are analyzed.
Abstract: Video indexing and retrieval have a wide spectrum of promising applications, motivating the interest of researchers worldwide. This paper offers a tutorial and an overview of the landscape of general strategies in visual content-based video indexing and retrieval, focusing on methods for video structure analysis, including shot boundary detection, key frame extraction and scene segmentation, extraction of features including static key frame features, object features and motion features, video data mining, video annotation, video retrieval including query interfaces, similarity measure and relevance feedback, and video browsing. Finally, we analyze future research directions.
20 Jun 2011
TL;DR: This paper proposes a model based approach, which detects humans using a 2-D head contour model and a 3-DHead surface model and proposes a segmentation scheme to segment the human from his/her surroundings and extract the whole contours of the figure based on the authors' detection point.
Abstract: Conventional human detection is mostly done in images taken by visible-light cameras. These methods imitate the detection process that human use. They use features based on gradients, such as histograms of oriented gradients (HOG), or extract interest points in the image, such as scale-invariant feature transform (SIFT), etc. In this paper, we present a novel human detection method using depth information taken by the Kinect for Xbox 360. We propose a model based approach, which detects humans using a 2-D head contour model and a 3-D head surface model. We propose a segmentation scheme to segment the human from his/her surroundings and extract the whole contours of the figure based on our detection point. We also explore the tracking algorithm based on our detection result. The methods are tested on our database taken by the Kinect in our lab and present superior results.
TL;DR: The details of the multitask CSP algorithm are outlined, results on two data sets are shown and a clear improvement can be seen, especially when the number of training trials is relatively low.
Abstract: Motor-imagery-based brain-computer interfaces (BCIs) commonly use the common spatial pattern filter (CSP) as preprocessing step before feature extraction and classification. The CSP method is a supervised algorithm and therefore needs subject-specific training data for calibration, which is very time consuming to collect. In order to reduce the amount of calibration data that is needed for a new subject, one can apply multitask (from now on called multisubject) machine learning techniques to the preprocessing phase. Here, the goal of multisubject learning is to learn a spatial filter for a new subject based on its own data and that of other subjects. This paper outlines the details of the multitask CSP algorithm and shows results on two data sets. In certain subjects a clear improvement can be seen, especially when the number of training trials is relatively low.
TL;DR: This paper proposes an output-associative fusion framework that incorporates correlations and covariances between the emotion dimensions and shows that on average, BLSTM-NNs outperform SVR due to their ability to learn past and future context, and the proposed system is well able to reproduce the valence and arousal ground truth obtained from human coders.
Abstract: Past research in analysis of human affect has focused on recognition of prototypic expressions of six basic emotions based on posed data acquired in laboratory settings. Recently, there has been a shift toward subtle, continuous, and context-specific interpretations of affective displays recorded in naturalistic and real-world settings, and toward multimodal analysis and recognition of human affect. Converging with this shift, this paper presents, to the best of our knowledge, the first approach in the literature that: 1) fuses facial expression, shoulder gesture, and audio cues for dimensional and continuous prediction of emotions in valence and arousal space, 2) compares the performance of two state-of-the-art machine learning techniques applied to the target problem, the bidirectional Long Short-Term Memory neural networks (BLSTM-NNs), and Support Vector Machines for Regression (SVR), and 3) proposes an output-associative fusion framework that incorporates correlations and covariances between the emotion dimensions. Evaluation of the proposed approach has been done using the spontaneous SAL data from four subjects and subject-dependent leave-one-sequence-out cross validation. The experimental results obtained show that: 1) on average, BLSTM-NNs outperform SVR due to their ability to learn past and future context, 2) the proposed output-associative fusion framework outperforms feature-level and model-level fusion by modeling and learning correlations and patterns between the valence and arousal dimensions, and 3) the proposed system is well able to reproduce the valence and arousal ground truth obtained from human coders.
20 Jun 2011
TL;DR: This work fuses two popular representations of street-level image data — facade-aligned and viewpoint-aligned — and shows that they contain complementary information that can be exploited to significantly improve the recall rates on the city scale.
Abstract: With recent advances in mobile computing, the demand for visual localization or landmark identification on mobile devices is gaining interest. We advance the state of the art in this area by fusing two popular representations of street-level image data — facade-aligned and viewpoint-aligned — and show that they contain complementary information that can be exploited to significantly improve the recall rates on the city scale. We also improve feature detection in low contrast parts of the street-level data, and discuss how to incorporate priors on a user's position (e.g. given by noisy GPS readings or network cells), which previous approaches often ignore. Finally, and maybe most importantly, we present our results according to a carefully designed, repeatable evaluation scheme and make publicly available a set of 1.7 million images with ground truth labels, geotags, and calibration data, as well as a difficult set of cell phone query images. We provide these resources as a benchmark to facilitate further research in the area.
06 Nov 2011
TL;DR: A simple modification to localize the soft-assignment coding is proposed, which surprisingly achieves comparable or even better performance than existing sparse or local coding schemes while maintaining its computational advantage.
Abstract: In object recognition, soft-assignment coding enjoys computational efficiency and conceptual simplicity. However, its classification performance is inferior to the newly developed sparse or local coding schemes. It would be highly desirable if its classification performance could become comparable to the state-of-the-art, leading to a coding scheme which perfectly combines computational efficiency and classification performance. To achieve this, we revisit soft-assignment coding from two key aspects: classification performance and probabilistic interpretation. For the first aspect, we argue that the inferiority of soft-assignment coding is due to its neglect of the underlying manifold structure of local features. To remedy this, we propose a simple modification to localize the soft-assignment coding, which surprisingly achieves comparable or even better performance than existing sparse or local coding schemes while maintaining its computational advantage. For the second aspect, based on our probabilistic interpretation of the soft-assignment coding, we give a probabilistic explanation to the magic max-pooling operation, which has successfully been used by sparse or local coding schemes but still poorly understood. This probability explanation motivates us to develop a new mix-order max-pooling operation which further improves the classification performance of the proposed coding scheme. As experimentally demonstrated, the localized soft-assignment coding achieves the state-of-the-art classification performance with the highest computational efficiency among the existing coding schemes.
TL;DR: Two-stage feature selection and feature extraction is used to improve the performance of text categorization and the proposed model is able to achieve high categorization effectiveness as measured by precision, recall and F-measure.
Abstract: Text categorization is widely used when organizing documents in a digital form. Due to the increasing number of documents in digital form, automated text categorization has become more promising in the last ten years. A major problem of text categorization is its large number of features. Most of those are irrelevant noise that can mislead the classifier. Therefore, feature selection is often used in text categorization to reduce the dimensionality of the feature space and to improve performance. In this study, two-stage feature selection and feature extraction is used to improve the performance of text categorization. In the first stage, each term within the document is ranked depending on their importance for classification using the information gain (IG) method. In the second stage, genetic algorithm (GA) and principal component analysis (PCA) feature selection and feature extraction methods are applied separately to the terms which are ranked in decreasing order of importance, and a dimension reduction is carried out. Thereby, during text categorization, terms of less importance are ignored, and feature selection and extraction methods are applied to the terms of highest importance; thus, the computational time and complexity of categorization is reduced. To evaluate the effectiveness of dimension reduction methods on our purposed model, experiments are conducted using the k-nearest neighbour (KNN) and C4.5 decision tree algorithm on Reuters-21,578 and Classic3 datasets collection for text categorization. The experimental results show that the proposed model is able to achieve high categorization effectiveness as measured by precision, recall and F-measure.
TL;DR: This paper proposes a novel, nonparametric approach for object recognition and scene parsing using a new technology the authors name label transfer, which is easy to implement, has few parameters, and embeds contextual information naturally in the retrieval/alignment procedure.
Abstract: While there has been a lot of recent work on object recognition and image understanding, the focus has been on carefully establishing mathematical models for images, scenes, and objects. In this paper, we propose a novel, nonparametric approach for object recognition and scene parsing using a new technology we name label transfer. For an input image, our system first retrieves its nearest neighbors from a large database containing fully annotated images. Then, the system establishes dense correspondences between the input image and each of the nearest neighbors using the dense SIFT flow algorithm [28], which aligns two images based on local image structures. Finally, based on the dense scene correspondences obtained from SIFT flow, our system warps the existing annotations and integrates multiple cues in a Markov random field framework to segment and recognize the query image. Promising experimental results have been achieved by our nonparametric scene parsing system on challenging databases. Compared to existing object recognition approaches that require training classifiers or appearance models for each object category, our system is easy to implement, has few parameters, and embeds contextual information naturally in the retrieval/alignment procedure.