By Topic

Image Processing, 2004. ICIP '04. 2004 International Conference on

Date 24-27 Oct. 2004

Go

Filter Results

Displaying Results 1 - 25 of 185
  • A fine-structure image/video quality measure using local statistics

    Publication Year: 2004 , Page(s): 3535 - 3538 Vol. 5
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (601 KB) |  | HTML iconHTML  

    An objective no-reference measure is presented to assess line-structure image/video quality. It was designed to measure image/video quality for video surveillance applications, especially for background modeling and foreground object detection. The proposed measure using local statistics reflects image degradation well in terms of noise and blur. The experimental results on a background subtraction algorithm validate the usefulness of the proposed measure, by showing its correlation with the algorithm's performance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • No-reference quality assessment for JPEG2000 compressed images

    Publication Year: 2004 , Page(s): 3539 - 3542 Vol. 5
    Cited by:  Papers (8)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (617 KB) |  | HTML iconHTML  

    No-reference quality assessment is a relatively new topic and has been attracting more and more attention in recent years. Due to the limited understanding of the human vision system, most of the existing methods focus on measuring to what extent the image has been distorted. In this paper, by viewing all edge points in JPEG2000 compressed images as 'distorted' or 'un-distorted', we propose using principal component analysis (PCA) to extract the local feature of a given edge point, which indicates both blurring and ringing. We also propose using the probabilities of the given edge point being 'distorted' and 'un-distorted' to model the local distortion metric, which is straightforward and can be easily applied to any type of local feature. Experimental results demonstrate the effectiveness of our scheme. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Expression morphing from distant viewpoints

    Publication Year: 2004 , Page(s): 3519 - 3522 Vol. 5
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (637 KB) |  | HTML iconHTML  

    In this paper, we propose an image-based approach to photo-realistic view synthesis by integrating field morphing and view morphing in a single framework. We thus provide a unified technique for synthesizing new images that include both viewpoint changes and object deformations. For view morphing, we relax the requirement of monotonicity along epipolar lines to piecewise monotonicity, by incorporating a segmentation stage prior to interpolation. This allows for dealing with occlusions and visibility issues, and hence alleviates the "ghosting effects" that typically occur when morphing is performed between distant viewpoints. We have particularly applied our approach to the synthesis of human facial expressions, while allowing for wide change of viewing positions and directions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On-line handwritten Chinese character recognition using a radical-based affine transformation

    Publication Year: 2004 , Page(s): 2881 - 2884 Vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (622 KB) |  | HTML iconHTML  

    On-line handwriting has been shown to be an effective tool for the input of Chinese characters. However, due to the high variabilities of handwriting, the recognition performance is somewhat limited. One approach to resolve this problem is to view the pattern mismatch as composed of two components: natural distortion component and residual discriminative component. By adopting a suitable deformation technique, the residual discriminative component can be extracted, which is then used for character recognition. The stroke-based affine transformation (SAT) is a prominent example of this approach. Although the SAT method proved to be successful, it did not fully exploit the structural nature of Chinese characters. This work extends Wakahara's SAT further by considering a higher-level character element, radical, which is commonly deemed as a true structural entity in Chinese characters. The proposed scheme contains two main parts: fuzzy stroke grouping and radical-based affine transformation (RAT). Simple yet effective fuzzy connectivity and transitivity concepts are adopted to extract pseudo-radicals. After the pseudo-radicals are found, an RAT is employed to deform each pseudo-radical so that the input test pattern can match the desired reference pattern more closely. A small-scale experiment was conducted to examine the feasibility of this approach. The results indicate some improvements of the presented approach over the SAT scheme and verify its applicability. Further performance improvement is expected if a writer has the tendency to write radicals more independently. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Light field compression based on prediction propagating and wavelet packet

    Publication Year: 2004 , Page(s): 3515 - 3518 Vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (594 KB) |  | HTML iconHTML  

    A novel data compression scheme of light field is presented. Different from the prior codecs, we perform image predicting and data coding in a set of subbands not directly in original images. In our approach, the original images are decomposed into subbands using wavelet packet transform, and the corresponding wavelet packet bases are divided into two parts: the predictable bases and the unpredictable bases by some criterions. In coding, a propagating algorithm and a rhombuses structure is used, and the subbands corresponding to the basis in predictable and unpredictable bases are added in sequence by relative energy until the reconstructing images meet the pre-established reconstruction quality. Experiments for two standard light fields verify the efficiency of our approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Halftone/contone conversion using neural networks

    Publication Year: 2004 , Page(s): 3547 - 3550 Vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (708 KB) |  | HTML iconHTML  

    A novel neural network based method for halftoning and inverse halftoning of digital images is presented. We first start from inverse half-toning of images produced from error diffusion methods using an RBF network plus an MLP network. The restored contone images have had good quality already. Then, an SLP neural network is used to refine the halftoning processing and the training process of the inverse half-toning network is also involved. The combined training procedure produces half-tone images and the corresponding continuous tone images at the same time. It is found that these contone images have even better PSNR performance. Furthermore, the resulted half-tone images are visually sharper and clearer, too. The proposed inverse half-toning method is also compared to the well-known LUT method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Microcalcification detection based on localized texture comparison

    Publication Year: 2004 , Page(s): 2953 - 2956 Vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (621 KB) |  | HTML iconHTML  

    While microcalcifications (MCs) are important early signs of breast cancers, their reliable detection from mammograms has been largely elusive for both radiologists and computer-aided diagnosis (CAD) strategies. Two of the essential components in a CAD system are the detection of the suspicious MC pixels/regions using image processing and analysis techniques, and the training, classification, and recognition of these areas based on pattern recognition methods. In this paper, we present a novel scheme to identify and classify microcalcifications based on localized texture comparison. Relying on a texture removal and repairing (R&R) process of the preselected suspicious areas from their surrounding background tissues, pre- and post- R&R local characteristic features of these areas are extracted and compared. A modified AdaBoost algorithm is then adopted to train the classifier using expert-labelled microcalcifications, followed by a clustering process. Experiments with the mammographic images from the MIAS and DDSM databases have shown very promising results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A training-based no-reference image quality assessment algorithm

    Publication Year: 2004 , Page(s): 2973 - 2976 Vol. 5
    Cited by:  Papers (9)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (632 KB) |  | HTML iconHTML  

    We present a new image quality assessment algorithm that does not rely on reference images. Our general framework is to emulate human quality assessment by first detecting visual components, then assessing quality against an empirical model. We describe an instance of this framework where visual component detection is realized as a face detection method, and quality modeling is realized using radial basis function (RBF) networks. Experiments with this prototype system yielded promising results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Quantitative analysis of lymphocyte membrane protein redistribution from fluorescence microscopy

    Publication Year: 2004 , Page(s): 2933 - 2936 Vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (578 KB) |  | HTML iconHTML  

    The relocalization of plasma membrane proteins is critical for establishing cellular polarity and regulating cell signaling. Three-dimensional fluorescence video microscopy allows the dynamic visualization of proteins in living cells. We have developed a robust and automated method to employ fluorescence data acquired in this manner for quantitative analysis of membrane protein movements across the cell surface. Our method utilizes level-set-based surface reconstruction followed by a maximum likelihood surface registration algorithm for rigid-body alignment of noisy images. A surface-walking technique yields distance maps for the cell surface, which are then used to measure changes in protein surface distribution over time. Applying this method to signaling in T lymphocytes, we have used it to monitor receptor movements and have validated these results against previously reported single-particle tracking data. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An improved EZW algorithm based on set partitioning in hierarchical trees using wavelet regularity

    Publication Year: 2004 , Page(s): 3169 - 3172 Vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (674 KB) |  | HTML iconHTML  

    This paper presents an improved embedded zerotree wavelet (EZW) coding algorithm, which makes use of the wavelet regularity to derive a classification criterion of wavelet coefficients in spatial-orientation hierarchical trees. Variations of the EZW algorithm discussed in the open literature have proposed some modifications in the process of exploiting the similarity of coefficients through the scales, however, not defining a figure of merit to measure such a similarity. Simulation results achieved from the coding of well-known images in the literature, for several bit rates, show a better performance of the proposed algorithm in both PSNR and subjective terms, as compared with EZW and SPIHT algorithms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A parallel mediated reality platform

    Publication Year: 2004 , Page(s): 2865 - 2868 Vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (611 KB) |  | HTML iconHTML  

    Realtime image processing provides a general framework for robust mediated reality problems. This paper presents a realtime mediated reality system that is built upon realtime image processing algorithms. It has been shown that the graphics processing unit (GPU) is capable of efficiently performing image processing tasks. The system presented uses a parallel GPU architecture for image processing that enables realtime mediated reality. Our implementation has many benefits; the graphics hardware has high throughput and low latency; the GPU's are not prone to jitter. Additionally, the CPU is kept available for user applications. The system is easily constructed, consisting of readily available commodity hardware. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A calibrated pinhole camera model for single viewpoint omnidirectional imaging systems

    Publication Year: 2004 , Page(s): 2977 - 2980 Vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (682 KB) |  | HTML iconHTML  

    This paper presents a perspective imaging model that is able to eliminate image deformations caused by non-linear lens distortion and to detect the location of the optical center respectively. By using a calibration pattern it can detect the optical center by tracking the optical rays generated by 3D points that have the same representation on the image plane. Calibration pattern is also used in order to generate normalized virtual screens on which captured images are back projected, thus eliminating the deformations. Experimental results for single viewpoint omni-directional cameras demonstrate the effectiveness of our method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Face alignment using intrinsic information

    Publication Year: 2004 , Page(s): 3307 - 3310 Vol. 5
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (718 KB) |  | HTML iconHTML  

    Previous 2-D face alignment algorithms are generally quite sensitive to illumination variation and poor initialization. To account for these two obstacles, two forms of relatively lighting invariant descriptors - intrinsic gray-level information and intrinsic edge information - rare adopted in our algorithm to direct shape search. The former is recovered from local intensity normalization and useful at localizing face contours accurately despite its dependency on initialization. The latter is extracted from normalized local regions by Canny edge filtering and is robust at coarse alignment in spite of poor initialization. The different merits of these two forms of intrinsic information motivate us to employ them at different stages of our face alignment process. Extensive experimentations show that this proposed approach allows our system to handle not only illumination variation, but also poor initialization. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Variable metric for binary vector quantization

    Publication Year: 2004 , Page(s): 3499 - 3502 Vol. 5
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (584 KB) |  | HTML iconHTML  

    We present a new method for performing vector quantization of binary vectors. The proposed method varies the distance metric and updates the centroids in an optimal manner regarding the current metric. The corresponding centroids change from "soft", allowing variables of codevectors to have values between zero and one, to hard, pure binary codevectors. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Accelerating the computation of GLCM and Haralick texture features on reconfigurable hardware

    Publication Year: 2004 , Page(s): 2857 - 2860 Vol. 5
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (597 KB) |  | HTML iconHTML  

    Grey level co-occurrence matrix (GLCM), one of the best known tool for texture analysis, estimates image properties related to second-order statistics. These image properties commonly known as Haralick texture features can be used for image classification, image segmentation, and remote sensing applications. However, their computations are highly intensive especially for very large images such as medical ones. Therefore, methods to accelerate their computations are highly desired. This paper proposes the use of reconfigurable hardware to accelerate the calculation of GLCM and Haralick texture features. The performances of the proposed co-processor are then assessed and compared against a microprocessor based solution. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive photo collection page layout

    Publication Year: 2004 , Page(s): 2897 - 2900 Vol. 5
    Cited by:  Papers (5)  |  Patents (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (609 KB) |  | HTML iconHTML  

    This paper presents a new photo collection page layout that attempts to maximize page coverage without having photos overlap. Layout is based on a hierarchical page partition, which provides explicit control over the aspect ratios and relative areas of the photos. We present an efficient method for finding a partition that produces a photo arrangement suitable for the shape of the page. Rather than relying on a stochastic search we employ a deterministic procedure that mimics the natural process of adding photos to the layout one by one. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust reconstruction of 3D points from images

    Publication Year: 2004 , Page(s): 3017 - 3020 Vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (628 KB) |  | HTML iconHTML  

    This paper presents a robust approach for 3D point reconstruction based on a set of images taken from a static scene with known, but not necessarily exact or regular, camera parameters. The points to be reconstructed are chosen from the contours of images, and a world-based formulation of the reconstruction problem and associated epipolar geometry is used. The result is a powerful mean of transparently integrating contributions from multiple images, and increased robustness to situations such as occlusions or apparent contours. Two steps for adding robustness are proposed: cross-checking, which validates a reconstructed point taken from an image by projecting it on a special subset of the remaining images; and merging, which fuses pairs of reconstructed points that are close in 3D space and that were initially chosen from different images. Results obtained with a synthetic scene (for ground truth comparison and error assessment), and two real scenes show the improved robustness achieved with the steps proposed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Watermarking robust against analog VCR recording

    Publication Year: 2004 , Page(s): 3423 - 3426 Vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (597 KB) |  | HTML iconHTML  

    Watermarking techniques are now in the spotlight to protect their copyrights. Enough verifications of robustness against analog VCR recording, however, have not been performed explicitly in previous work while analog copied contents have raised their fidelity. We study on a watermarking technique that has durability against analog VCR copying. We found that the watermarks well survive after D/A and A/D conversions and VCR recording when they are embedded in the wavelet transform domain with three times horizontal and one time vertical 2-to-1 decimations. Our method increases the relative power of the watermark signals using the spread spectrum technique. Additionally, it varies embedding density as well as the magnitude of the watermark signal as an adaptive control. We embedded 64-bit information into a video sequence using the proposed method and confirmed that we can detect the watermarks correctly even from the analog copies recorded with the VHS standard mode. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The effect of global motion parameter accuracies on the efficiency of video coding

    Publication Year: 2004 , Page(s): 3359 - 3362 Vol. 5
    Cited by:  Papers (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (577 KB) |  | HTML iconHTML  

    In this paper, we present theoretical analysis on how the global motion parameter accuracies affect the efficiency of motion compensated video coding. The inaccurate global motion compensation is modelled by introducing probabilistic rotation, scale and translation parameter errors. Approximate expressions that relate the power spectrum of the prediction error to motion parameter errors is derived. By doubling the accuracy of the motion parameters, up to 6 dB theoretical gains can be obtained in prediction error variance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CT image compression with level of interest

    Publication Year: 2004 , Page(s): 3185 - 3188 Vol. 5
    Cited by:  Patents (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (611 KB) |  | HTML iconHTML  

    This paper proposes a novel CT image coding concept named LOI which stands for level of interest and coding methods based on that concept. The well-known ROI (region of interest) coding gives priority to pixels in particular regions of an image when encoding or decoding the image. Similarly, LOI coding gives priority to the pixels having a particular pixel level. LOI is ideal for coding of CT images and offers remarkably high coding efficiency. This paper proposes two types of LOI coding methods. One type is the floating point method and the other is the integer method. This paper verifies that the both types improve coding efficiency of pixels in the LOI window. This paper also shows that adequate image quality is obtained even if the viewing window is different from the LOI window. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolutionary Gibbs sampler for image segmentation

    Publication Year: 2004 , Page(s): 3479 - 3482 Vol. 5
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (613 KB) |  | HTML iconHTML  

    We propose a novel evolutionary algorithm for the function optimization problem in Bayesian image segmentation with Markov random field prior. Function variables are partitioned into several codings. A pivot coding is selected and variables in it are evolved respectively according to their probability distributions which encode both the evolutionary pressure and contextual constraints from neighboring pixels. Variables in other codings are evolved according to their conditional probabilities. In summary, the algorithm is about building probabilistic models to guide search. It achieves the efficiency and flexibility by incorporating Gibbs sampler in an evolutionary approach. Remarkable performance is observed in some experiments. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Contextual disambiguation for multi-class object detection

    Publication Year: 2004 , Page(s): 2873 - 2876 Vol. 5
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (628 KB) |  | HTML iconHTML  

    We consider the problem of detecting and localizing instances from multiple object classes. Suppose an overcomplete index - an initial list with extra detections but none missed - is provided. We and others have previously shown how this can be done efficiently with coarse-to-fine search. How would one prune such a list to a final interpretation? We propose a method based on contextual disambiguation: first, a Viterbi algorithm is utilized to extract N candidate interpretations by using the global context to provide constraints among object classes or poses. Then, the extracted candidates are compared in a pairwise fashion to resolve remaining ambiguities, and the final interpretation is constructed. The whole procedure is illustrated by experiments in reading license plates. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Arbitrary viewpoints image representation based on 3-D geometric model and specular reflection tracing

    Publication Year: 2004 , Page(s): 2989 - 2992 Vol. 5
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (639 KB) |  | HTML iconHTML  

    In order to develop a system to synthesize arbitrary viewpoint images efficiently, two representative schemes that use the 3-D geometric model to synthesize images have been the focus of attention: model-based rendering and image-based rendering. Image-based rendering is reported to give a better coding performance than the model-based rendering. Although the image-based rendering synthesizes the relatively accurate diffuse reflection component from the camera images at the different viewpoints, it can not synthesize the specular reflection component with sufficient accuracy because the movement of the specular reflection component on the object surface by the viewpoint change is not taken into consideration. Therefore, we propose a method of synthesizing arbitrary viewpoint images by estimating the motion vectors of the specular reflection components for the 3-D model-based synthesized image used as the reference image. Experiments with a carved wooden object show the effectiveness of the proposed method through the coding performance and the subjective evaluation of the synthesized image. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Compact rotation-invariant texture classification

    Publication Year: 2004 , Page(s): 3033 - 3036 Vol. 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (660 KB) |  | HTML iconHTML  

    This paper constructs a texture feature extractor based on a morphological scale-space. It produces features that are invariant to rotation of the texture. The features are used with a very simple k-nearest neighbour classifier and tested using the Outex methodology. The classifier has comparable performance to a number of benchmark classifiers but uses fewer features. The algorithm is quick to compute and provides insight into the underlying structure of texture. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • High-capacity data hiding in halftone images using minimal error bit searching

    Publication Year: 2004 , Page(s): 3463 - 3466 Vol. 5
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (826 KB) |  | HTML iconHTML  

    In this paper, a high capacity data hiding is proposed for embedding a large amount of information into halftone images. The embedded watermark can be distributed into several error-diffused images by the proposed minimal error bit searching technique (MEBS). The method can be generalized to self-decoding mode with dot diffusion or color halftone images. From the experiments, the embedded capacity from 33% up to 50% and good quality result are achieved. Furthermore, the proposed MEBS method is also extended for robust watermarking to against the degradation from printing-and-scanning and several kinds of distortions. View full abstract»

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