IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE T PATTERN ANAL)

Publications in this journal

• Source

  Available from: uchicago.edu

  Article: Multiple-Aperture Photography for High Dynamic Range and Post-Capture Refocusing

  Samuel W Hasinoff, Kiriakos N Kutulakos
  [show abstract] [hide abstract]
  ABSTRACT: In this article we present multiple-aperture photography, a new method for analyzing sets of images captured with different aperture settings, with all other camera parameters fixed. Using an image restoration framework, we show that we can simultaneously account for defocus, high dynamic range exposure (HDR), and noise, all of which are confounded according to aperture. Our formulation is based on a layered decomposition of the scene that models occlusion effects in detail. Recovering such a scene representation allows us to adjust the camera parameters in post-capture, to achieve changes in focus setting or depth of field—with all results available in HDR. Our method is designed to work with very few input images: we demonstrate results from real sequences obtained using the three-image "aperture bracketing" mode found on consumer digital SLR cameras.
  IEEE Transactions on Pattern Analysis and Machine Intelligence ; 1.
• Source

  Available from: uni-duisburg.de

  Article: Knowledge-based image retrieval

  Thorsten Hermes, Christoph Klauck, Jutta Krey, Jinyou Zhang
  [show abstract] [hide abstract]
  ABSTRACT: In order to retrieve a set of intended images from an image archive, human beings think of special contents with respect to the searched scene, like a country side picture or a technical drawing. The necessity of a semantics-based retrieval language leads to a content-based analysis and retrieval of images. From this point of view, our project IRIS (Image Retrieval for Information Systems) develops and combines methods and techniques of computer vision and knowledge representation in a new way in order to automatically generate textual content descriptions of images. IRIS retrieves the images using the text retrieval system SearchManager for AIX. This paper introduces the architecture of the system, presents the methods of feature extrac-tion with respect to color, texture, and contour segmentation. It concentrates on the discussion of formalization knowledge for modeling concepts and object recognition, and gives rst evaluation results concerning the retrieval eectiveness in terms of precision and recall. The system is implemented on the system IBM RS/6000 using AIX and has already been tested with an image archive comprising 1200.
  IEEE Transactions on Pattern Analysis and Machine Intelligence ;
• Article: Locally Orderless Registration.

  Sune Darkner, Jon Sporring
  [show abstract] [hide abstract]
  ABSTRACT: This paper presents a unifying approach for calculating a wide range of popular, but seemingly very different, similarity measures. Our domain is the registration of n-dimensional images sampled on a regular grid, and our approach is well suited for gradient-based optimization algorithms. Our approach is based on local intensity histograms and built upon the technique of Locally Orderless Images. Histograms by Locally Orderless Images are well posed and offer explicit control over the three inherent and unavoidable scales: the spatial resolution, intensity levels, and spatial extent of local histograms. Through Locally Orderless Images, we offer new insight into the relations between these scales. We demonstrate our unification by developing a Locally Orderless Registration algorithm for two quite different similarity measures, namely, Normalized Mutual Information and Sum of Squared Differences, and we compare these variations both theoretically and empirically. Finally, using our algorithm, we explain the empirically observed differences between two popular joint density estimation techniques used in registration: Parzen Windows and Generalized Partial Volume.
  IEEE Transactions on Pattern Analysis and Machine Intelligence 06/2013; 35(6):1437-1450.
• Article: Segmentation, Inference and Classification of Partially Overlapping Nanoparticles

  Chiwoo Park, Jianhua Huang, Yu Ding
  IEEE Transactions on Pattern Analysis and Machine Intelligence 03/2013; 35(3).
• Article: Learning Hierarchical Features for Scene Labeling

  Clement Farabet, Camille Couprie, Laurent Najman, Yann LeCun
  IEEE Transactions on Pattern Analysis and Machine Intelligence 01/2013;
• Article: A Bag-of-Features Framework to Classify Time Series

  Mustafa Gokce Baydogan, George Runger, Eugene Tuv
  [show abstract] [hide abstract]
  ABSTRACT: Time series classification is an important task with many challenging applications. A nearest-neighbor classifier with dynamic time warping (DTW) distance is a strong solution in this context. On the other hand, feature-based approaches have been proposed as both classifiers and to provide insight into the series, but these approaches have problems handling translations and dilations in local patterns. Considering these shortcomings, we present a framework to classify time series based on a bag-of-features representation (TSBF). Multiple subsequences selected from random locations and of random lengths are partitioned into shorter intervals to capture the local information. Consequently, features computed from these subsequences measure properties at different locations and dilations when viewed from the original series. This provides a feature-based approach that can handle warping (although differently from DTW). Moreover, a supervised learner (that handles mixed data types, different units, etc.) integrates location information into a compact codebook through class probability estimates. Additionally, relevant global features can easily supplement the codebook. TSBF is compared to nearest-neighbor classifiers and other alternatives (bag-of-words strategies, sparse spatial sample kernels, shapelets). Our experimental results show that TSBF provides better results than competitive methods on benchmark datasets from the UCR time series database.
  IEEE Transactions on Pattern Analysis and Machine Intelligence 01/2013; PP:1-1.
• Article: Low Rank Matrix Approximation with Manifold Regularization.

  Zhenyue Zhang, Keke Zhao
  [show abstract] [hide abstract]
  ABSTRACT: This paper proposes a new model of low-rank matrix factorization that incorporates manifold regularization to the matrix factorization. Superior to the graph-regularized nonnegative matrix factorization, this new regularization model has globally optimal and closed form solutions. A direct algorithm (for data with small number of points) and an alternate iterative algorithm with inexact inner iteration (for large scale data) are proposed to solve the new model. A convergence analysis establishes the global convergence of the iterative algorithm. Efficiency and precision of the algorithm are demonstrated numerically through applications to six real-world data sets on clustering and classification. Performance comparison with existing algorithms shows the effectiveness of the proposed method for low-rank factorization in general.
  IEEE Transactions on Pattern Analysis and Machine Intelligence 12/2012;
• Article: Towards a Theory of Statistical Tree-Shape Analysis.

  Aasa Feragen, Pechin Lo, Marleen de Bruijne, Mads Nielsen, Francois Lauze
  [show abstract] [hide abstract]
  ABSTRACT: In order to develop statistical methods for shapes with a tree-structure, we construct a shape space framework for tree-shapes and study metrics on the shape space. This shape space has singularities, which correspond to topological transitions in the represented trees. We study two closely related metrics on the shape space, TED and QED. QED is a quotient Euclidean distance arising naturally from the shape space formulation, while TED is the classical tree edit distance. Using Gromov's metric geometry we gain new insight into the geometries defined by TED and QED. We show that the new metric QED has nice geometric properties which are needed for statistical analysis: geodesics always exist, and are generically locally unique. Following this we can also show existence and generic local uniqueness of average trees for QED. TED, while having some algorithmic advantages, does not share these advantages. Along with the theoretical framework we provide experimental proof-of-concept results on synthetic data trees as well as small airway trees from pulmonary CT scans. This way, we illustrate that our framework has promising theoretical and qualitative properties necessary to build a theory of statistical tree-shape analysis.
  IEEE Transactions on Pattern Analysis and Machine Intelligence 12/2012;
• Source

  Available from: ArXiv

  Article: Hierarchical Object Parsing from Structured Noisy Point Clouds.

  Adrian Barbu
  [show abstract] [hide abstract]
  ABSTRACT: Object parsing and segmentation from point clouds are challenging tasks because the relevant data is available only as thin structures along object boundaries or other features, and is corrupted by large amounts of noise. To handle this kind of data, flexible shape models are desired that can accurately follow the object boundaries. Popular models such as Active Shape and Active Appearance models lack the necessary flexibility for this task, while recent approaches such as the Recursive Compositional Models make model simplifications in order to obtain computational guarantees. This paper investigates a hierarchical Bayesian model of shape and appearance in a generative setting. The input data is explained by an object parsing layer, which is a deformation of a hidden PCA shape model with Gaussian prior. The paper also introduces a novel efficient inference algorithm that uses informed data-driven proposals to initialize local searches for the hidden variables. Applied to the problem of object parsing from structured point clouds such as edge detection images, the proposed approach obtains state of the art parsing errors on two standard datasets without using any intensity information.
  IEEE Transactions on Pattern Analysis and Machine Intelligence 12/2012;
• Article: Deep hierarchies in the primate visual cortex: what can we learn for computer vision?

  Norbert Kruger, Peter Janssen, Sinan Kalkan, Markus Lappe, Ales Leonardis, Justus Piater, Antonio J. Rodriguez-Sanchez, Laurenz Wiskott
  [show abstract] [hide abstract]
  ABSTRACT: Computational modeling of the primate visual system yields insights of potential relevance to some of the challenges that computer vision is facing, such as object recognition and categorization, motion detection and activity recognition or vision-based navigation and manipulation. This article reviews some functional principles and structures that are generally thought to underlie the primate visual cortex, and attempts to extract biological principles that could further advance computer vision research. Organized for a computer vision audience, we present functional principles of the processing hierarchies present in the primate visual system considering recent discoveries in neurophysiology. The hierarchal processing in the primate visual system is characterized by a sequence of different levels of processing (in the order of ten) that constitute a deep hierarchy in contrast to the flat vision architectures predominantly used in today’s mainstream computer vision. We hope that the functional description of the deep hierarchies realized in the primate visual system provides valuable insights for the design of computer vision algorithms, fostering increasingly productive interaction between biological and computer vision research.
  IEEE Transactions on Pattern Analysis and Machine Intelligence 12/2012;
• Article: A Minimal Solution for the Extrinsic Calibration of a Camera and a Laser-Rangefinder

  F. Vasconcelos, J. Barreto, U. Nunes
  [show abstract] [hide abstract]
  ABSTRACT: This paper presents a new algorithm for the extrinsic calibration of a perspective camera and an invisible 2D laser-rangefinder (LRF). The calibration is achieved by freely moving a checkerboard pattern in order to obtain plane poses in camera coordinates and depth readings in the LRF reference frame. The problem of estimating the rigid displacement between the two sensors is formulated as one of registering a set of planes and lines in the 3D space. It is proven for the first time that the alignment of three plane-line correspondences has at most eight solutions that can be determined by solving a standard p3p problem and a linear system of equations. This leads to a minimal closed-form solution for the extrinsic calibration that can be used as hypothesis generator in a RANSAC paradigm. Our calibration approach is validated through simulation and real experiments that show the superiority with respect to the current state-of-the-art method requiring a minimum of five input planes.
  IEEE Transactions on Pattern Analysis and Machine Intelligence 11/2012; 34(11):2097 - 2107.
• Article: Recognizing Gestures by Learning Local Motion Signatures of HOG Descriptors.

  Mohamed-Bécha Kaâniche, François Brémond
  [show abstract] [hide abstract]
  ABSTRACT: We introduce a new gesture recognition framework based on learning local motion signatures (LMSs) of HOG descriptors introduced by [1]. Our main contribution is to propose a new probabilistic learning-classification scheme based on a reliable tracking of local features. After the generation of these LMSs computed on one individual by tracking Histograms of Oriented Gradient (HOG) [2] descriptor, we learn a codebook of video-words (i.e., clusters of LMSs) using k-means algorithm on a learning gesture video database. Then, the video-words are compacted to a code-book of codewords by the Maximization of Mutual Information (MMI) algorithm. At the final step, we compare the LMSs generated for a new gesture w.r.t. the learned code-book via the k-nearest neighbors (k-NN) algorithm and a novel voting strategy. Our main contribution is the handling of the N to N mapping between codewords and gesture labels within the proposed voting strategy. Experiments have been carried out on two public gesture databases: KTH [3] and IXMAS [4]. Results show that the proposed method outperforms recent state-of-the-art methods.
  IEEE Transactions on Pattern Analysis and Machine Intelligence 11/2012; 34(11):2247-58.
• Article: Proximity-Based Frameworks for Generating Embeddings from Multi-Output Data

  Tingting Mu, John Yannis Goulermas, Jun'ichi Tsujii, Sophia Ananiadou
  [show abstract] [hide abstract]
  ABSTRACT: This paper is about supervised and semi-supervised dimensionality reduction (DR) by generating spectral embeddings from multi-output data based on the pairwise proximity information. Two flexible and generic frameworks are proposed to achieve supervised DR (SDR) for multilabel classification. One is able to extend any existing single-label SDR to multilabel via sample duplication, referred to as MESD. The other is a multilabel design framework that tackles the SDR problem by computing weight (proximity) matrices based on simultaneous feature and label information, referred to as MOPE, as a generalization of many current techniques. A diverse set of different schemes for label-based proximity calculation, as well as a mechanism for combining label-based and feature-based weight information by considering information importance and prioritization, are proposed for MOPE. Additionally, we summarize many current spectral methods for unsupervised DR (UDR), single/multilabel SDR, and semi-supervised DR (SSDR) and express them under a common template representation as a general guide to researchers in the field. We also propose a general framework for achieving SSDR by combining existing SDR and UDR models, and also a procedure of reducing the computational cost via learning with a target set of relation features. The effectiveness of our proposed methodologies is demonstrated with experiments with document collections for multilabel text categorization from the natural language processing domain.
  IEEE Transactions on Pattern Analysis and Machine Intelligence 10/2012; 34:2216-2232.