By Topic

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Issue 4 • Date April 2013

Filter Results

Displaying Results 1 - 22 of 22
  • [Table of contents]

    Publication Year: 2013 , Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (213 KB)  
    Freely Available from IEEE
  • Cover2

    Publication Year: 2013 , Page(s): c2
    Save to Project icon | Request Permissions | PDF file iconPDF (200 KB)  
    Freely Available from IEEE
  • A Globally-Variant Locally-Constant Model for Fusion of Labels from Multiple Diverse Experts without Using Reference Labels

    Publication Year: 2013 , Page(s): 769 - 783
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (1936 KB) |  | HTML iconHTML  

    Researchers have shown that fusion of categorical labels from multiple experts - humans or machine classifiers - improves the accuracy and generalizability of the overall classification system. Simple plurality is a popular technique for performing this fusion, but it gives equal importance to labels from all experts, who may not be equally reliable or consistent across the dataset. Estimation of ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Automatic Iris Occlusion Estimation Method Based on High-Dimensional Density Estimation

    Publication Year: 2013 , Page(s): 784 - 796
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (2877 KB) |  | HTML iconHTML  

    Iris masks play an important role in iris recognition. They indicate which part of the iris texture map is useful and which part is occluded or contaminated by noisy image artifacts such as eyelashes, eyelids, eyeglasses frames, and specular reflections. The accuracy of the iris mask is extremely important. The performance of the iris recognition system will decrease dramatically when the iris mas... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic Caption Generation for News Images

    Publication Year: 2013 , Page(s): 797 - 812
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (1547 KB) |  | HTML iconHTML  

    This paper is concerned with the task of automatically generating captions for images, which is important for many image-related applications. Examples include video and image retrieval as well as the development of tools that aid visually impaired individuals to access pictorial information. Our approach leverages the vast resource of pictures available on the web and the fact that many of them a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Calibration of Ultrawide Fisheye Lens Cameras by Eigenvalue Minimization

    Publication Year: 2013 , Page(s): 813 - 822
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (1434 KB) |  | HTML iconHTML  

    We present a new technique for calibrating ultrawide fisheye lens cameras by imposing the constraint that collinear points be rectified to be collinear, parallel lines to be parallel, and orthogonal lines to be orthogonal. Exploiting the fact that line fitting reduces to an eigenvalue problem in 3D, we do a rigorous perturbation analysis to obtain a practical calibration procedure. Doing experimen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparative Analysis and Fusion of Spatiotemporal Information for Footstep Recognition

    Publication Year: 2013 , Page(s): 823 - 834
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (4334 KB) |  | HTML iconHTML  

    Footstep recognition is a relatively new biometric which aims to discriminate people using walking characteristics extracted from floor-based sensors. This paper reports for the first time a comparative assessment of the spatiotemporal information contained in the footstep signals for person recognition. Experiments are carried out on the largest footstep database collected to date, with almost 20... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Explicit Modeling of Human-Object Interactions in Realistic Videos

    Publication Year: 2013 , Page(s): 835 - 848
    Cited by:  Papers (6)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (3034 KB) |  | HTML iconHTML  

    We introduce an approach for learning human actions as interactions between persons and objects in realistic videos. Previous work typically represents actions with low-level features such as image gradients or optical flow. In contrast, we explicitly localize in space and track over time both the object and the person, and represent an action as the trajectory of the object w.r.t. to the person p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image Denoising Using the Higher Order Singular Value Decomposition

    Publication Year: 2013 , Page(s): 849 - 862
    Cited by:  Papers (10)
    Multimedia
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (3154 KB) |  | HTML iconHTML  

    In this paper, we propose a very simple and elegant patch-based, machine learning technique for image denoising using the higher order singular value decomposition (HOSVD). The technique simply groups together similar patches from a noisy image (with similarity defined by a statistically motivated criterion) into a 3D stack, computes the HOSVD coefficients of this stack, manipulates these coeffici... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Incremental Learning of 3D-DCT Compact Representations for Robust Visual Tracking

    Publication Year: 2013 , Page(s): 863 - 881
    Cited by:  Papers (11)
    Multimedia
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (4567 KB) |  | HTML iconHTML  

    Visual tracking usually requires an object appearance model that is robust to changing illumination, pose, and other factors encountered in video. Many recent trackers utilize appearance samples in previous frames to form the bases upon which the object appearance model is built. This approach has the following limitations: 1) The bases are data driven, so they can be easily corrupted, and 2) it i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Monocular Visual Scene Understanding: Understanding Multi-Object Traffic Scenes

    Publication Year: 2013 , Page(s): 882 - 897
    Cited by:  Papers (11)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (5788 KB) |  | HTML iconHTML  

    Following recent advances in detection, context modeling, and tracking, scene understanding has been the focus of renewed interest in computer vision research. This paper presents a novel probabilistic 3D scene model that integrates state-of-the-art multiclass object detection, object tracking and scene labeling together with geometric 3D reasoning. Our model is able to represent complex object in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiple Target Tracking by Learning-Based Hierarchical Association of Detection Responses

    Publication Year: 2013 , Page(s): 898 - 910
    Cited by:  Papers (6)
    Multimedia
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (4122 KB) |  | HTML iconHTML  

    We propose a hierarchical association approach to multiple target tracking from a single camera by progressively linking detection responses into longer track fragments (i.e., tracklets). Given frame-by-frame detection results, a conservative dual-threshold method that only links very similar detection responses between consecutive frames is adopted to generate initial tracklets with minimum ident... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimizing Nondecomposable Loss Functions in Structured Prediction

    Publication Year: 2013 , Page(s): 911 - 924
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (1719 KB) |  | HTML iconHTML  

    We develop an algorithm for structured prediction with nondecomposable performance measures. The algorithm learns parameters of Markov Random Fields (MRFs) and can be applied to multivariate performance measures. Examples include performance measures such as $(F_{beta })$ score (natural language processing), intersection over union (object category segmentation), Precision/Recall at k (search engi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Orientation Field Estimation for Latent Fingerprint Enhancement

    Publication Year: 2013 , Page(s): 925 - 940
    Cited by:  Papers (13)
    Multimedia
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (7670 KB) |  | HTML iconHTML  

    Identifying latent fingerprints is of vital importance for law enforcement agencies to apprehend criminals and terrorists. Compared to live-scan and inked fingerprints, the image quality of latent fingerprints is much lower, with complex image background, unclear ridge structure, and even overlapping patterns. A robust orientation field estimation algorithm is indispensable for enhancing and recog... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust Visual Tracking Using an Adaptive Coupled-Layer Visual Model

    Publication Year: 2013 , Page(s): 941 - 953
    Cited by:  Papers (15)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (3442 KB) |  | HTML iconHTML  

    This paper addresses the problem of tracking objects which undergo rapid and significant appearance changes. We propose a novel coupled-layer visual model that combines the target's global and local appearance by interlacing two layers. The local layer in this model is a set of local patches that geometrically constrain the changes in the target's appearance. This layer probabilistically adapts to... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spectral 6DOF Registration of Noisy 3D Range Data with Partial Overlap

    Publication Year: 2013 , Page(s): 954 - 969
    Cited by:  Papers (4)
    Multimedia
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (3232 KB) |  | HTML iconHTML  

    We present Spectral Registration with Multilayer Resampling (SRMR) as a 6 Degrees Of Freedom (DOF) registration method for noisy 3D data with partial overlap. The algorithm is based on decoupling 3D rotation from 3D translation by a corresponding resampling process of the spectral magnitude of a 3D Fast Fourier Transform (FFT) calculation on discretized 3D range data. The registration of all 6DOF ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Support Vector Shape: A Classifier-Based Shape Representation

    Publication Year: 2013 , Page(s): 970 - 982
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (1692 KB) |  | HTML iconHTML  

    We introduce a novel implicit representation for 2D and 3D shapes based on Support Vector Machine (SVM) theory. Each shape is represented by an analytic decision function obtained by training SVM, with a Radial Basis Function (RBF) kernel so that the interior shape points are given higher values. This empowers support vector shape (SVS) with multifold advantages. First, the representation uses a s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D Stochastic Completion Fields for Mapping Connectivity in Diffusion MRI

    Publication Year: 2013 , Page(s): 983 - 995
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (811 KB) |  | HTML iconHTML  

    The 2D stochastic completion field algorithm, introduced by Williams and Jacobs [1], [2], uses a directional random walk to model the prior probability of completion curves in the plane. This construct has had a powerful impact in computer vision, where it has been used to compute the shapes of likely completion curves between edge fragments in visual imagery. Motivated by these developments, we e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Visual Saliency Based on Scale-Space Analysis in the Frequency Domain

    Publication Year: 2013 , Page(s): 996 - 1010
    Cited by:  Papers (33)
    Multimedia
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (4307 KB) |  | HTML iconHTML  

    We address the issue of visual saliency from three perspectives. First, we consider saliency detection as a frequency domain analysis problem. Second, we achieve this by employing the concept of nonsaliency. Third, we simultaneously consider the detection of salient regions of different size. The paper proposes a new bottom-up paradigm for detecting visual saliency, characterized by a scale-space ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Wang-Landau Monte Carlo-Based Tracking Methods for Abrupt Motions

    Publication Year: 2013 , Page(s): 1011 - 1024
    Cited by:  Papers (6)
    Save to Project icon | Request Permissions | Click to expandAbstract | PDF file iconPDF (2364 KB) |  | HTML iconHTML  

    We propose a novel tracking algorithm based on the Wang-Landau Monte Carlo (WLMC) sampling method for dealing with abrupt motions efficiently. Abrupt motions cause conventional tracking methods to fail because they violate the motion smoothness constraint. To address this problem, we introduce the Wang-Landau sampling method and integrate it into a Markov Chain Monte Carlo (MCMC)-based tracking fr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • [Back inside cover]

    Publication Year: 2013 , Page(s): c3
    Save to Project icon | Request Permissions | PDF file iconPDF (200 KB)  
    Freely Available from IEEE
  • [Back cover]

    Publication Year: 2013 , Page(s): c4
    Save to Project icon | Request Permissions | PDF file iconPDF (213 KB)  
    Freely Available from IEEE

Aims & Scope

The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is published monthly. Its editorial board strives to present most important research results in areas within TPAMI's scope.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
David A. Forsyth
University of Illinois
e-mail: daf@illinois.edu