By Topic

36th Applied Imagery Pattern Recognition Workshop (aipr 2007)

10-12 Oct. 2007

Filter Results

Displaying Results 1 - 25 of 28
  • [Front cover]

    Publication Year: 2007, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (77 KB)
    Freely Available from IEEE
  • [Title page i]

    Publication Year: 2007, Page(s): i
    Request permission for commercial reuse | PDF file iconPDF (29 KB)
    Freely Available from IEEE
  • [Title page iii]

    Publication Year: 2007, Page(s): iii
    Request permission for commercial reuse | PDF file iconPDF (97 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2007, Page(s): iv
    Request permission for commercial reuse | PDF file iconPDF (58 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2007, Page(s):v - vi
    Request permission for commercial reuse | PDF file iconPDF (39 KB)
    Freely Available from IEEE
  • Workshop Summary

    Publication Year: 2007, Page(s): vii
    Request permission for commercial reuse | PDF file iconPDF (31 KB) | HTML iconHTML
    Freely Available from IEEE
  • 3D Organization of 2D Urban Imagery

    Publication Year: 2007, Page(s):3 - 8
    Cited by:  Papers (4)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2557 KB) | HTML iconHTML

    Working with New York data as a representative and instructive example, we fuse aerial ladar imagery with satellite pictures and Geographic Information System (GIS) layers to form a comprehensive 3D urban map. Digital photographs are then mathematically inserted into this detailed world space. Reconstruction of the photos' view frusta yields their cameras' locations and pointing directions which m... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Methodology for Automated Vector-to-Image Registration

    Publication Year: 2007, Page(s):9 - 14
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1134 KB) | HTML iconHTML

    Registration and alignment of feature (e.g., vector) and raster geospatial data is a difficult and time-consuming process when performed manually. This paper presents an approach for vector-to-raster registration. Candidate features are auto-extracted and vectorized from imagery, which are the basis to compare against existing vector layer(s) to be registered. Given that automated feature extracti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adapting to Change: The CFAR Problem in Advanced Hyperspectral Detection

    Publication Year: 2007, Page(s):15 - 21
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1332 KB) | HTML iconHTML

    Newer, realistic models of targets and backgrounds used in hyperspectral detection do not always lend themselves to a CFAR (constant false alarm rate) formulation. Several advanced techniques are considered here. It is found that incorporating a particular empirically validated method of target evolution permits an exact CFAR version of a large class of advanced detectors based on elliptically con... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image Differencing Approaches to Medical Image Classification

    Publication Year: 2007, Page(s):22 - 27
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (298 KB) | HTML iconHTML

    Image differencing is normally done by subtracting the low-level features like intensity in images that are already aligned. This paper extracts high-level features in order to learn an effective image differencing method for the diagnosis of breast cancer. However, this produces sets of features that are both spatial and unordered. Learning techniques are challenging when examples are sets of fea... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using Tactic-Based Learning (formerly Mentoring) to Accelerate Recovery of an Adaptive Learning System in a Changing Environment

    Publication Year: 2007, Page(s):31 - 36
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (663 KB) | HTML iconHTML

    Tactic-Based Learning (TBL), formerly referred to as mentoring, is a selection policy for statistical learning systems that has been initially tested with a Collective Learning Automaton that solves a simple, but representative, problem. To respond to an immature stimulus that does not yet have a high- confidence response associated with it, TBL hypothesizes that selecting a response that has been... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Imagery Pattern Recognition and Pub/Sub Information Management

    Publication Year: 2007, Page(s):37 - 41
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (345 KB) | HTML iconHTML

    Imagery pattern recognition (IPR) is becoming more challenging as image resolutions continue to improve and algorithms become more complex. Systems for analysis are being developed on increasingly diverse and heterogeneous platforms, from hardware support using field programmable gate arrays, graphics processing units, and Cell processors to high performance computers, featuring multi-core process... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • In Situ Adaptive Feature Extraction for Underwater Target Classification

    Publication Year: 2007, Page(s):42 - 47
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (599 KB) | HTML iconHTML

    This research compares the performance improvements of image-based sonar target classification algorithms when they are adapted to changing clutter environments. The distribution of seabed pixels in the sonar imagery is modeled as a correlated, K-distributed random variable allowing for a quantitative representation of seabed environments in the various testing scenarios. Parameterized environment... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automated Registration Evaluation System (ARES)

    Publication Year: 2007, Page(s):51 - 56
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (279 KB) | HTML iconHTML

    This paper describes the automated registration evaluation system (ARES). The goal of the ARES is to dramatically reduce the cost of evaluating different automated data (raster and/or vector) registration technologies. Under the first year of the ARES project, five different automated registration methods were selected for evaluation. These methods represented the state-of-the-art in automated ima... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using a High-Fidelity Simulation Framework for Performance Singularity

    Publication Year: 2007, Page(s):57 - 62
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1325 KB) | HTML iconHTML

    A common way to evaluate the performance of a system is to compare the algorithmic outputs with ground truth to identify divergences in the system's performance and discover the errors it is prone to. In the absence of such ground truth or as a follow-on to performance evaluation, performance analysis at the algorithmic level can provide developers insight into performance singularities. Such perf... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combining Rule-based and Machine Learning Approaches for Shape Recognition

    Publication Year: 2007, Page(s):65 - 70
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (367 KB) | HTML iconHTML

    Shape recognition applications are multi-step processes that include capture, preprocessing, feature extraction, recognition, and a decision process. Each step can use approaches in the continuum from rule-based to machine learning. This paper presents example approaches, the pros and cons of these rule-based and adaptive approaches, and performance differences in biometric applications. Rule-base... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • lambda-Connectedness Determination for Image Segmentation

    Publication Year: 2007, Page(s):71 - 79
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (429 KB) | HTML iconHTML

    Image segmentation is to separate an image into distinct homogeneous regions belonging to different objects. It is an essential step in image analysis and computer vision. This paper compares some segmentation technologies and attempts to find an automated way to better determine the parameters for image segmentation, especially the connectivity value of lambda in lambda-connected segmentation. Ba... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Mathematical Architecture for Molecular Computing

    Publication Year: 2007, Page(s):80 - 86
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (184 KB) | HTML iconHTML

    Traditional computing uses transistors and binary logic in order to perform computing operations. This approach has proved successful as long as the number of transistors per integrated circuit can be scaled to accommodate increasing speed and heat requirements. Unfortunately, this approach does not allow speeds above the limit where the size of the transistors approaches the limit of the integrat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Regional Variance Dependant Sub-frame Reduction for Face Detection in High Definition Video Frames

    Publication Year: 2007, Page(s):89 - 94
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (414 KB) | HTML iconHTML

    Statistical learning based face detection systems search multiple scale sub-frames of an image or frame of a video stream with a trained classifier to detect face objects. If the frame is large there will be a large number of these sub-frames. Sections of the frame with a regional variance below a predefined threshold do not need to be searched as it is not possible for a face to exist in these sp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Super-Resolution of Video Sequences Using Local Motion Estimates

    Publication Year: 2007, Page(s):95 - 100
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2569 KB) | HTML iconHTML

    We present a method for boosting the resolution of 'target' frames of video using available supra-Nyquist information in surrounding frames during slow scene motion. Pixels in the frames surrounding a target frame were aligned to the target frame at subpixel resolution, by estimating translations of small upsampled image patches surrounding each pixel. This analysis was performed locally in order ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Moving Vehicle Registration and Super-Resolution

    Publication Year: 2007, Page(s):101 - 107
    Cited by:  Papers (2)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (506 KB) | HTML iconHTML

    We describe a method for registering and super-resolving moving vehicles from aerial surveillance video. The challenge of vehicle super-resolution lies in the fact that vehicles may be very small and thus frame-to-frame registration does not offer enough constraints to yield registration with sub-pixel accuracy. To overcome this, we first register the large-scale image backgrounds and then, relati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • General Shape Generation by Contouring Fractals and Applying Linear Boundary Regression

    Publication Year: 2007, Page(s):111 - 116
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (724 KB) | HTML iconHTML

    The ALISA Component Module (ACM) has been developed as a general-purpose shape classifier for objects in Digital Transmissive Images (DTIs). The Component Module classifies contoured DTIs intended to reveal the internal structures of objects and to facilitate feature extraction. The ACM is trained with exemplars of regions-of-interest (ROIs) representing object components. While the ACM has demons... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Biologically Inspired Object Categorization in Cluttered Scenes

    Publication Year: 2007, Page(s):117 - 122
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (789 KB) | HTML iconHTML

    Humans have the ability to recognize objects in a cluttered scene in 100 s of milliseconds. Computer algorithms operate at a much lower performance level compared to humans. Furthermore, it has proven to be particularly difficult to develop algorithms to recognize all objects in a category, such as, all cat faces vs dog faces, because of the large in-class variability. The distinguishing features ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Robust Method for Multiple Face Tracking Using Kalman Filter

    Publication Year: 2007, Page(s):125 - 130
    Cited by:  Papers (11)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (340 KB) | HTML iconHTML

    A robust method for tracking faces of multiple people moving in a scene using Kalman filter is proposed in this paper. To distinguish faces of people during partial occlusion the proposed method uses the non-parametric cloth distribution. To overcome the problem of total occlusion, faces are tracked using the values generated by Kalman prediction algorithm. The size, top-left coordinate and veloci... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D Scene Reconstruction through a Fusion of Passive Video and Lidar Imagery

    Publication Year: 2007, Page(s):133 - 138
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (365 KB) | HTML iconHTML

    Geometric structure of a scene can be reconstructed using many methods. In recent years, two prominent approaches have been digital photogrammetric analysis using passive stereo imagery and feature extraction from lidar point clouds. In the first method, the traditional technique relies on finding common points in two or more 2D images that were acquired from different view perspectives. More rece... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.