By Topic

Digital Image Computing Techniques and Applications (DICTA), 2011 International Conference on

Date 6-8 Dec. 2011

Filter Results

Displaying Results 1 - 25 of 123
  • [Front cover]

    Page(s): C1
    Save to Project icon | Request Permissions | PDF file iconPDF (1703 KB)  
    Freely Available from IEEE
  • [Title page i]

    Page(s): i
    Save to Project icon | Request Permissions | PDF file iconPDF (19 KB)  
    Freely Available from IEEE
  • [Title page iii]

    Page(s): iii
    Save to Project icon | Request Permissions | PDF file iconPDF (49 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): iv
    Save to Project icon | Request Permissions | PDF file iconPDF (125 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): v - xiii
    Save to Project icon | Request Permissions | PDF file iconPDF (163 KB)  
    Freely Available from IEEE
  • Message from the General Chair

    Page(s): xiv
    Save to Project icon | Request Permissions | PDF file iconPDF (82 KB)  
    Freely Available from IEEE
  • Message from the Program Chair

    Page(s): xv
    Save to Project icon | Request Permissions | PDF file iconPDF (69 KB)  
    Freely Available from IEEE
  • Organizing Committee

    Page(s): xvi
    Save to Project icon | Request Permissions | PDF file iconPDF (86 KB)  
    Freely Available from IEEE
  • Reviewers

    Page(s): xvii - xviii
    Save to Project icon | Request Permissions | PDF file iconPDF (89 KB)  
    Freely Available from IEEE
  • An Automatic Image Based Single Dilution Method for End Point Titre Quantitation of Antinuclear Antibodies Tests Using HEp-2 Cells

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1304 KB) |  | HTML iconHTML  

    Indirect Immunofluorescence (IIF) on Human epithelial (HEp-2) cells test has been the golden standard for identifying the presence of Anti-Nuclear Antibodies (ANA) due to its high sensitivity and the large range of antigens that can be detected. Furthermore, IIF ANA test allows the positive sample strength (sample end point titre) to be reported. Despite its advantages, the IIF ANA test needs to be performed manually, and therefore it is perceived as an expensive and laborious process. This also applies to determining the strength of positive samples (end point titre) which traditionally is done by serially diluting the specimen. In this paper, we present an image-based method which is able to automatically determine the end point titre of positive samples based only on a single screening dilution. This can be done by simulating the manual titration process using a mathematical model of the exposure-density curve. Technically, a new Image Titration Endpoint (ITE) unit based on the model is introduced. Each specimen image is then measured in terms of this unit. Finally, the end point titre for the specimen is determined through a standard curve which specifies the end point titre given an ITE unit. This process is fully automated which would give an advantage over the current digital titration methods. The overall endpoint titre agreement between the proposed approach and the manual serial dilution method in the evaluation of 134 positive samples was 100%. This high agreement demonstrates that the proposed approach is suitable for routine ANA IIF testing in the clinical settings. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic Segmentation of the Prostate in 3D Magnetic Resonance Images Using Case Specific Deformable Models

    Page(s): 7 - 12
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1513 KB) |  | HTML iconHTML  

    This paper presents a novel approach to automatically segment the prostate (including seminal vesicles) using a surface that is actively deformed via shape and gray level models. The surface deformation process utilises the results of a multi-atlas registration approach, where training images are matched to the case image via non-rigid registration. Normalised mutual information is then used to measure the similarity between each image in the training set and the case image. The set of training images with a similarity greater than a threshold is then used to build the initialisation and the gray level model of the segmentation process. This case specific gray level model is used to deform the initial surface to more closely match the prostate boundary via normalised cross-correlation based template matching of gray level profiles. Mean and median Dice's Similarity Coefficients of 0.849 and 0.855, as well as a mean surface error of 2.11 mm, were achieved when segmenting 3T Magnetic Resonance clinical scans of fifty patients. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Surface-Base Approach Using a Multi-scale EM-ICP Registration for Statistical Population Analysis

    Page(s): 13 - 18
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (652 KB) |  | HTML iconHTML  

    The human cortex is a folded ribbon of neurons with a high inter-individual variability. It is a challenging structure to study especially when measuring small changes resulting from normal aging and neurodegenerative disorders such as Alzheimer's Disease (AD). Recent studies have proposed surface based approaches for statistical population comparison of cortical changes since such approaches better cope with the surfacic nature of the cortex. In this paper we present a new multi-scale EM-ICP registration that is embedded into a surface-based approach. We compare this new registration algorithm with the shape context in the context of statistical population analysis. When comparing the cortical thickness between healthy elderly subjects to Alzheimer's disease patients, the new pipeline reduces the intra class variability while increasing the statistical power of the T-tests between both groups. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automated 3D Segmentation of Vertebral Bodies and Intervertebral Discs from MRI

    Page(s): 19 - 24
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1548 KB) |  | HTML iconHTML  

    Recent developments in high resolution MRI scanning of the human spine are providing increasing opportunities for the development of accurate automated approaches for pathoanatomical assessment of intervertebral discs and vertebrae. We are developing a fully automated 3D segmentation approach for MRI scans of the human spine based on statistical shape analysis and template matching of grey level intensity profiles. The algorithm reported in the present study was validated on a dataset of high resolution volumetric scans of lower thoracic and lumbar spine obtained on a 3T scanner using the relatively new 3D SPACE (T2-weighted) pulse sequence, and on a dataset of axial T1-weighted scans of lumbar spine obtained on a 1.5T system. A 3D spine curve is initially extracted and used to position the statistical shape models for final segmentation. Initial validating experiments show promising results on both MRI datasets. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automated MR Hip Bone Segmentation

    Page(s): 25 - 30
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1045 KB) |  | HTML iconHTML  

    The accurate segmentation of the bone and articular cartilages from magnetic resonance (MR) images of the hip is important for clinical studies and drug trials into conditions like osteoarthritis. In current studies, segmentations are obtained using time-consuming manual or semi-automatic algorithms which have high inter- and intra-observer variabilities. This paper presents an important step towards obtaining automatic and accurate segmentations of the hip cartilages, namely an approach to automatically segment the bones. The segmentation is performed using three-dimensional active shape models, which are initialized using an affine registration to an atlas. The accuracy and robustness of the approach was experimentally validated using an MR database of we VIBE, we DESS and MEDIC MR images. The (left, right) femoral and ace tabular bone segmentation had a median Dice similarity coefficient of (0.921, 0.926) and (0.830, 0.813). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Non-Linear Diffeomorphic Framework for Prostate Multimodal Registration

    Page(s): 31 - 36
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2183 KB) |  | HTML iconHTML  

    This paper presents a novel method for non-rigid registration of prostate multimodal images based on a nonlinear framework. The parametric estimation of the non-linear diffeomorphism between the 2D fixed and moving images has its basis in solving a set of non-linear equations of thin-plate splines. The regularized bending energy of the thin-plate splines along with the localization error of established correspondences is jointly minimized with the fixed and transformed image difference, where, the transformed image is represented by the set of non-linear equations defined over the moving image. The traditional thin-plate splines with established correspondences may provide good registration of the anatomical targets inside the prostate but may fail to provide improved contour registration. On the contrary, the proposed framework maintains the accuracy of registration in terms of overlap due to the non-linear thin-plate spline functions while also producing smooth deformations of the anatomical structures inside the prostate as a result of established corrspondences. The registration accuracies of the proposed method are evaluated in 20 pairs of prostate mid-gland ultrasound and magnetic resonance images in terms of Dice similarity coefficient with an average of 0.982 ± 0.004, average 95% Hausdorff distance of 1.54 ± 0.46 mm and mean target registration and target localization errors of 1.90±1.27 mm and 0.15 ± 0.12 mm respectively. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Illumination-Invariant Loss for Monocular 3D Pose Estimation

    Page(s): 37 - 44
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1095 KB) |  | HTML iconHTML  

    The problem of identifying the 3D pose of a known object from a given 2D image has important applications in Computer Vision. Our proposed method of registering a 3D model of a known object on a given 2D photo of the object has numerous advantages over existing methods. It does not require prior training, knowledge of the camera parameters, explicit point correspondences or matching features between the image and model. Unlike techniques that estimate a partial 3D pose (as in an overhead view of traffic or machine parts on a conveyor belt), our method estimates the complete 3D pose of the object. It works on a single static image from a given view under varying and unknown lighting conditions. For this purpose we derive a novel illumination-invariant distance measure between the 2D photo and projected 3D model, which is then minimised to find the best pose parameters. Results for vehicle pose detection in real photographs are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust Image Registration via Cepstral Analysis

    Page(s): 45 - 50
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (501 KB) |  | HTML iconHTML  

    Cepstrum based image registration has been largely overlooked over the past two decades. Initial investigation of the method was limited to alignment of images exhibiting only translational differences. Later attempts to extend the method to handle rotations proved disappointing. This paper presents a cepstrum-based registration method that provides performance comparable to the state of the art over a wide range of scale factors and rotation angles, with reduced computational load. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D Model Assisted Image Segmentation

    Page(s): 51 - 58
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1256 KB) |  | HTML iconHTML  

    The problem of segmenting a given image into coherent regions is important in Computer Vision and many industrial applications require segmenting a known object into its components. Examples include identifying individual parts of a component for process control work in a manufacturing plant and identifying parts of a car from a photo for automatic damage detection. Unfortunately most of an object's parts of interest in such applications share the same pixel characteristics, having similar colour and texture. This makes segmenting the object into its components a non-trivial task for conventional image segmentation algorithms. In this paper, we propose a "Model Assisted Segmentation" method to tackle this problem. A 3D model of the object is registered over the given image by optimising a novel gradient based loss function. This registration obtains the full 3D pose from an image of the object. The image can have an arbitrary view of the object and is not limited to a particular set of views. The segmentation is subsequently performed using a level-set based method, using the projected contours of the registered 3D model as initialisation curves. The method is fully automatic and requires no user interaction. Also, the system does not require any prior training. We present our results on photographs of a real car. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Specularity Removal from Imaging Spectroscopy Data via Entropy Minimisation

    Page(s): 59 - 65
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (522 KB) |  | HTML iconHTML  

    In this paper, we present a method to remove specularities from imaging spectroscopy data. We do this by making use of the dichromatic model so as to cast the problem in a linear regression setting. We do this so as to employ the average radiance for each pixel as a means to map the spectra onto a two-dimensional space. This permits the use of an entropy minimisation approach so as to recover the slope of a line described by a linear regressor. We show how this slope can be used to recover the specular coefficient in the dichromatic model and provide experiments on real-world imaging spectroscopy data. We also provide comparison with an alternative and effect a quantitative analysis that shows our method is robust to changes the degree of specularity of the image or the location of the light source in the scene. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis on Tree Structure Selection for MRF Inference in Low-level Vision

    Page(s): 66 - 71
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (459 KB) |  | HTML iconHTML  

    MRF inference on the 4-connected grid is popularly utilized for early vision tasks. But due to the loopy structure of the 4-connected grid, inference becomes complicated and less efficient. This paper present a theoretical analysis on what is an optimal spanning tree structure (loop-free) to approximate the 4-connected grid, to facilitate an efficient inference. We formulate our problem in statistical view: inference on an optimal tree structure should obtain a similar distribution to that of a 4-connected grid. To measure the similarity between two distributions, KL-divergence is chosen as a powerful tool. Due to the asymmetric nature of KL-divergence, the optimization can be approached from two directions. We analyze both the two directions and find they are equivalent to tree partition function lower bound and upper bound optimization respectively. Finally, we develop a tree selection algorithm based on the two bounds optimization and evaluate them on both image denoising and stereo matching tasks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast Kernel Sparse Representation

    Page(s): 72 - 77
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (384 KB) |  | HTML iconHTML  

    Two efficient algorithms are proposed to seek the sparse representation on high-dimensional Hilbert space. By proving that all the calculations in Orthogonal Match Pursuit (OMP) are essentially inner-product combinations, we modify the OMP algorithm to apply the kernel-trick. The proposed Kernel OMP (KOMP) is much faster than the existing methods, and illustrates higher accuracy in some scenarios. Furthermore, inspired by the success of group-sparsity, we enforce a rigid group-sparsity constraint on KOMP which leads to a noniterative variation. The constrained cousin of KOMP, dubbed as Single-Step KOMP (S-KOMP), merely takes one step to achieve the sparse coefficients. A remarkable improvement (up to 2,750 times) in efficiency is reported for S-KOMP, with only a negligible loss of accuracy. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Phase Based Disparity Estimation Using Adaptive Structured Light and Dual-Tree Complex Wavelet

    Page(s): 78 - 83
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (584 KB) |  | HTML iconHTML  

    In this paper, we propose a phase-based approach to estimate disparity between stereo images using the Dual-Tree Complex Wavelet transform and adaptive structured light. Firstly, a random noise adaptive structured light pattern is projected onto objects and two cameras capture stereo images. The adaptive colors are acquired using principle component analysis in the RGB color space of the image of the scene under ambient light to maximize the energy of the structured light and meanwhile minimize the energy of other noise factors. A Dual tree Complex Wavelet transform is then applied on the original three RGB channels of the scene under adaptive structured light and a fourth channel which mainly contains projected random noise generated using inverse principle component analysis. Finally the disparity map between the stereo images is generated by locating the minimum phase differences between left and right complex wavelet coefficients. Our experimental results show the proposed approach can generate high quality disparity maps. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Superpixels, Occlusion and Stereo

    Page(s): 84 - 91
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5707 KB) |  | HTML iconHTML  

    Graph-based energy minimization is now the state of the art in stereo matching methods. In spite of its outstanding performance, few efforts have been made to enhance its capability of occlusion handling. We propose an occlusion constraint, an iterative optimization strategy and a mechanism that proceeds on both the digital pixel level and the super pixel level. Our method explicitly handles occlusion in the framework of graph-based energy minimization. It is fast and outperforms previous methods especially in the matching accuracy of boundary areas. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optical-Flow Perspective Invariant Registration

    Page(s): 92 - 98
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (402 KB) |  | HTML iconHTML  

    In this paper we examine the causes of one of the major shortcomings of current natural feature registration approaches, failure to register when the camera's view approaches parallel to the marker. The methods used by current registration algorithms in the attempt to overcome this problem are reviewed, and a novel tracking based approach called the Optical-flow Perspective Invariant Registration Augmentation (OPIRA) is presented which significantly improves the range of registration. A thorough evaluation of OPIRA is conducted using an external ground truth, showing the improvements possible when combined with leading natural feature registration algorithms such as SIFT, SURF and Ferns. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simultaneous Multi-class Pixel Labeling over Coherent Image Sets

    Page(s): 99 - 106
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2026 KB) |  | HTML iconHTML  

    Multi-class pixel labeling is an important problem in computer vision that has many diverse applications, including interactive image segmentation, semantic and geometric scene understanding, and stereo reconstruction. Current state-of-the-art approaches learn a model on a set of training images and then apply the learned model to each image in a test set independently. The quality of the results, therefore, depends strongly on the quality of the learned models and the information available within each training image. Importantly, this approach cannot leverage information available in other images at test time which may help to label the image at hand. Instead of labeling each image independently, we propose a semi-supervised approach that exploits the similarity between regions across many images in coherent image subsets. Specifically, our model finds similar regions in related images and constrains the joint labeling of the images to agree on the labels within these regions. By considering the joint labeling, our model gets to leverage contextual information that is not available when considering images in isolation. We test our approach on the popular 21-class MSRC multi-class image segmentation dataset and show improvement in accuracy over a strong baseline model. View full abstract»

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