Showing papers on "Real image published in 2011"

A Level Set Method for Image Segmentation in the Presence of Intensity Inhomogeneities With Application to MRI

Abstract: Intensity inhomogeneity often occurs in real-world images, which presents a considerable challenge in image segmentation. The most widely used image segmentation algorithms are region-based and typically rely on the homogeneity of the image intensities in the regions of interest, which often fail to provide accurate segmentation results due to the intensity inhomogeneity. This paper proposes a novel region-based method for image segmentation, which is able to deal with intensity inhomogeneities in the segmentation. First, based on the model of images with intensity inhomogeneities, we derive a local intensity clustering property of the image intensities, and define a local clustering criterion function for the image intensities in a neighborhood of each point. This local clustering criterion function is then integrated with respect to the neighborhood center to give a global criterion of image segmentation. In a level set formulation, this criterion defines an energy in terms of the level set functions that represent a partition of the image domain and a bias field that accounts for the intensity inhomogeneity of the image. Therefore, by minimizing this energy, our method is able to simultaneously segment the image and estimate the bias field, and the estimated bias field can be used for intensity inhomogeneity correction (or bias correction). Our method has been validated on synthetic images and real images of various modalities, with desirable performance in the presence of intensity inhomogeneities. Experiments show that our method is more robust to initialization, faster and more accurate than the well-known piecewise smooth model. As an application, our method has been used for segmentation and bias correction of magnetic resonance (MR) images with promising results.

Blind deconvolution using a normalized sparsity measure

Abstract: Blind image deconvolution is an ill-posed problem that requires regularization to solve. However, many common forms of image prior used in this setting have a major drawback in that the minimum of the resulting cost function does not correspond to the true sharp solution. Accordingly, a range of additional methods are needed to yield good results (Bayesian methods, adaptive cost functions, alpha-matte extraction and edge localization). In this paper we introduce a new type of image regularization which gives lowest cost for the true sharp image. This allows a very simple cost formulation to be used for the blind deconvolution model, obviating the need for additional methods. Due to its simplicity the algorithm is fast and very robust. We demonstrate our method on real images with both spatially invariant and spatially varying blur.

Image Denoising in Mixed Poisson–Gaussian Noise

Abstract: We propose a general methodology (PURE-LET) to design and optimize a wide class of transform-domain thresholding algorithms for denoising images corrupted by mixed Poisson-Gaussian noise. We express the denoising process as a linear expansion of thresholds (LET) that we optimize by relying on a purely data-adaptive unbiased estimate of the mean-squared error (MSE), derived in a non-Bayesian framework (PURE: Poisson-Gaussian unbiased risk estimate). We provide a practical approximation of this theoretical MSE estimate for the tractable optimization of arbitrary transform-domain thresholding. We then propose a pointwise estimator for undecimated filterbank transforms, which consists of subband-adaptive thresholding functions with signal-dependent thresholds that are globally optimized in the image domain. We finally demonstrate the potential of the proposed approach through extensive comparisons with state-of-the-art techniques that are specifically tailored to the estimation of Poisson intensities. We also present denoising results obtained on real images of low-count fluorescence microscopy.

Discriminative Models for Multi-Class Object Layout

Abstract: Many state-of-the-art approaches for object recognition reduce the problem to a 0-1 classification task. This allows one to leverage sophisticated machine learning techniques for training classifiers from labeled examples. However, these models are typically trained independently for each class using positive and negative examples cropped from images. At test-time, various post-processing heuristics such as non-maxima suppression (NMS) are required to reconcile multiple detections within and between different classes for each image. Though crucial to good performance on benchmarks, this post-processing is usually defined heuristically. We introduce a unified model for multi-class object recognition that casts the problem as a structured prediction task. Rather than predicting a binary label for each image window independently, our model simultaneously predicts a structured labeling of the entire image (Fig. 1). Our model learns statistics that capture the spatial arrangements of various object classes in real images, both in terms of which arrangements to suppress through NMS and which arrangements to favor through spatial co-occurrence statistics. We formulate parameter estimation in our model as a max-margin learning problem. Given training images with ground-truth object locations, we show how to formulate learning as a convex optimization problem. We employ the cutting plane algorithm of Joachims et al. (Mach. Learn. 2009) to efficiently learn a model from thousands of training images. We show state-of-the-art results on the PASCAL VOC benchmark that indicate the benefits of learning a global model encapsulating the spatial layout of multiple object classes (a preliminary version of this work appeared in ICCV 2009, Desai et al., IEEE international conference on computer vision, 2009).

A Variational Framework for Exemplar-Based Image Inpainting

Abstract: Non-local methods for image denoising and inpainting have gained considerable attention in recent years. This is in part due to their superior performance in textured images, a known weakness of purely local methods. Local methods on the other hand have demonstrated to be very appropriate for the recovering of geometric structures such as image edges. The synthesis of both types of methods is a trend in current research. Variational analysis in particular is an appropriate tool for a unified treatment of local and non-local methods. In this work we propose a general variational framework for non-local image inpainting, from which important and representative previous inpainting schemes can be derived, in addition to leading to novel ones. We explicitly study some of these, relating them to previous work and showing results on synthetic and real images.

Multiregion Image Segmentation by Parametric Kernel Graph Cuts

Abstract: The purpose of this study is to investigate multiregion graph cut image partitioning via kernel mapping of the image data. The image data is transformed implicitly by a kernel function so that the piecewise constant model of the graph cut formulation becomes applicable. The objective function contains an original data term to evaluate the deviation of the transformed data, within each segmentation region, from the piecewise constant model, and a smoothness, boundary preserving regularization term. The method affords an effective alternative to complex modeling of the original image data while taking advantage of the computational benefits of graph cuts. Using a common kernel function, energy minimization typically consists of iterating image partitioning by graph cut iterations and evaluations of region parameters via fixed point computation. A quantitative and comparative performance assessment is carried out over a large number of experiments using synthetic grey level data as well as natural images from the Berkeley database. The effectiveness of the method is also demonstrated through a set of experiments with real images of a variety of types such as medical, synthetic aperture radar, and motion maps.

No-Reference Blur Assessment of Digital Pictures Based on Multifeature Classifiers

Abstract: In this paper, we address the problem of no-reference quality assessment for digital pictures corrupted with blur. We start with the generation of a large real image database containing pictures taken by human users in a variety of situations, and the conduction of subjective tests to generate the ground truth associated to those images. Based upon this ground truth, we select a number of high quality pictures and artificially degrade them with different intensities of simulated blur (gaussian and linear motion), totalling 6000 simulated blur images. We extensively evaluate the performance of state-of-the-art strategies for no-reference blur quantification in different blurring scenarios, and propose a paradigm for blur evaluation in which an effective method is pursued by combining several metrics and low-level image features. We test this paradigm by designing a no-reference quality assessment algorithm for blurred images which combines different metrics in a classifier based upon a neural network structure. Experimental results show that this leads to an improved performance that better reflects the images' ground truth. Finally, based upon the real image database, we show that the proposed method also outperforms other algorithms and metrics in realistic blur scenarios.

Shape estimation in natural illumination

Abstract: The traditional shape-from-shading problem, with a single light source and Lambertian reflectance, is challenging since the constraints implied by the illumination are not sufficient to specify local orientation. Photometric stereo algorithms, a variant of shape-from-shading, simplify the problem by controlling the illumination to obtain additional constraints. In this paper, we demonstrate that many natural lighting environments already have sufficient variability to constrain local shape. We describe a novel optimization scheme that exploits this variability to estimate surface normals from a single image of a diffuse object in natural illumination. We demonstrate the effectiveness of our method on both simulated and real images.

Systems and methods for generating a virtual camera viewpoint for an image

Abstract: A color image and a depth image of a live video are received. A user is extracted from the information of the color image and the depth image. Spurious depth vales may be corrected. Points or pixels of an image as seen from a viewpoint of a reference camera at a reference camera location are mapped to points of the image as would be seen from a viewpoint of a virtual camera at a virtual camera location. As such, a transformed color image is generated. Disoccluded pixels may be processed to address any gaps within the transformed color image.

Camera calibration with lens distortion from low-rank textures

Abstract: We present a simple, accurate, and flexible method to calibrate intrinsic parameters of a camera together with (possibly significant) lens distortion. This new method can work under a wide range of practical scenarios: using multiple images of a known pattern, multiple images of an unknown pattern, single or multiple image(s) of multiple patterns, etc. Moreover, this new method does not rely on extracting any low-level features such as corners or edges. It can tolerate considerably large lens distortion, noise, error, illumination and viewpoint change, and still obtain accurate estimation of the camera parameters. The new method leverages on the recent breakthroughs in powerful high-dimensional convex optimization tools, especially those for matrix rank minimization and sparse signal recovery. We will show how the camera calibration problem can be formulated as an important extension to principal component pursuit, and solved by similar techniques. We characterize to exactly what extent the parameters can be recovered in case of ambiguity. We verify the efficacy and accuracy of the proposed algorithm with extensive experiments on real images.

CG2Real: Improving the Realism of Computer Generated Images Using a Large Collection of Photographs

Abstract: Computer-generated (CG) images have achieved high levels of realism. This realism, however, comes at the cost of long and expensive manual modeling, and often humans can still distinguish between CG and real images. We introduce a new data-driven approach for rendering realistic imagery that uses a large collection of photographs gathered from online repositories. Given a CG image, we retrieve a small number of real images with similar global structure. We identify corresponding regions between the CG and real images using a mean-shift cosegmentation algorithm. The user can then automatically transfer color, tone, and texture from matching regions to the CG image. Our system only uses image processing operations and does not require a 3D model of the scene, making it fast and easy to integrate into digital content creation workflows. Results of a user study show that our hybrid images appear more realistic than the originals.

Correlative multi-label multi-instance image annotation

Abstract: In this paper, each image is viewed as a bag of local regions, as well as it is investigated globally. A novel method is developed for achieving multi-label multi-instance image annotation, where image-level (bag-level) labels and region-level (instance-level) labels are both obtained. The associations between semantic concepts and visual features are mined both at the image level and at the region level. Inter-label correlations are captured by a co-occurence matrix of concept pairs. The cross-level label coherence encodes the consistency between the labels at the image level and the labels at the region level. The associations between visual features and semantic concepts, the correlations among the multiple labels, and the cross-level label coherence are sufficiently leveraged to improve annotation performance. Structural max-margin technique is used to formulate the proposed model and multiple interrelated classifiers are learned jointly. To leverage the available image-level labeled samples for the model training, the region-level label identification on the training set is firstly accomplished by building the correspondences between the multiple bag-level labels and the image regions. JEC distance based kernels are employed to measure the similarities both between images and between regions. Experimental results on real image datasets MSRC and Corel demonstrate the effectiveness of our method.

3D light field cameras, images and files, and methods of using, operating, processing and viewing same

Abstract: A 3D stereo image of a scene is generated by generating first image data of the scene using light field data representing light rays from a first direction, and second image data of the scene using light field data representing light rays from a second direction. The 3D stereo image of the scene is then generated using the first image data and the second image data. A microlens array may be used to direct light rays onto a photosensor array, wherein each microlens of the microlens array includes a physical aperture which correlates to a plurality of associated photosensors, a first virtual aperture which correlates to a first subset of the associated photosensors, and a second virtual aperture which correlates to a second subset of the associated photosensors. Each virtual aperture thus provides light rays from a different direction for use in generating the 3D stereo image.

Identifying Image Composites Through Shadow Matte Consistency

Abstract: In this paper, we propose a framework for detecting tampered digital images based on photometric consistency of illumination in shadows. In particular, we formulate color characteristics of shadows measured by the shadow matte value. The shadow boundaries and the penumbra shadow region in an image are first extracted. Then a simple and efficient method is used to estimate shadow matte values of shadows. Our approach efficiently extracts these constraints from a single view of a target scene and makes use of them for the digital forgery detection. Experimental results on both simulated photos and visually plausible real images demonstrate the effectiveness of the proposed method.

Pixel opacity for augmented reality

Abstract: In embodiments of pixel opacity for augmented reality, a display lens system includes a first display panel that displays a virtual image generated to appear as part of an environment viewed through optical lenses. A second display panel displays an environment image of the environment as viewed through the optical lenses, and the environment image includes opaque pixels that form a black silhouette of the virtual image. The display lens system also includes a beam-splitter panel to transmit light of the environment image and reflect light of the virtual image to form a composite image that appears as the virtual image displayed over the opaque pixels of the environment image.

Skeleton Search: Category-Specific Object Recognition and Segmentation Using a Skeletal Shape Model

Abstract: We describe a top-down object detection and segmentation approach that uses a skeleton-based shape model and that works directly on real images. The approach is based on three components. First, we propose a fragment-based generative model for shape that is based on the shock graph and has minimal dependency among its shape fragments. The model is capable of generating a wide variation of shapes as instances of a given object category. Second, we develop a progressive selection mechanism to search among the generated shapes for the category instances that are present in the image. The search begins with a large pool of candidates identified by a dynamic programming (DP) algorithm and progressively reduces it in size by applying series of criteria, namely, local minimum criterion, extent of shape overlap, and thresholding of the objective function to select the final object candidates. Third, we propose the Partitioned Chamfer Matching (PCM) measure to capture the support of image edges for a hypothesized shape. This measure overcomes the shortcomings of the Oriented Chamfer Matching and is robust against spurious edges, missing edges, and accidental alignment between the image edges and the shape boundary contour. We have evaluated our approach on the ETHZ dataset and found it to perform well in both object detection and object segmentation tasks.

Light guide plate and virtual image display apparatus having the same

Abstract: Since a distance from an image extraction part to a light exiting surface is shorter downstream in an optical path than upstream in the optical path in relation to Z direction that is an arraying direction of reflection units, image light that propagates to pass between the image extraction part and the light exiting surface without becoming incident on the reflection units and therefore cannot be extracted to outside can be reduced. That is, since image light having a large total reflection angle in a light guide plate can be securely made incident on the image extraction part and efficiently extracted from the light exiting surface, light use efficiency in image formation can be enhanced. Thus, a virtual image display apparatus with brightness and high performance can be provided.

Calibration of Central Catadioptric Cameras Using a DLT-Like Approach

Abstract: In this study, we present a calibration technique that is valid for all single-viewpoint catadioptric cameras. We are able to represent the projection of 3D points on a catadioptric image linearly with a 6×10 projection matrix, which uses lifted coordinates for image and 3D points. This projection matrix can be computed from 3D---2D correspondences (minimum 20 points distributed in three different planes). We show how to decompose it to obtain intrinsic and extrinsic parameters. Moreover, we use this parameter estimation followed by a non-linear optimization to calibrate various types of cameras. Our results are based on the sphere camera model which considers that every central catadioptric system can be modeled using two projections, one from 3D points to a unitary sphere and then a perspective projection from the sphere to the image plane. We test our method both with simulations and real images, and we analyze the results performing a 3D reconstruction from two omnidirectional images.

SAR Image Simulation with Application to Target Recognition

Abstract: This paper presents a novel synthetic aperture radar (SAR) image simulation approach to target recognition, which consists of two frameworks, referred to as the satellite SAR images simulation and the target recognition and identiflcation. The images simulation makes use of the sensor and target geo-location relative to the Earth, movement of SAR sensor, SAR system parameters, radiometric and geometric characteristics of the target, and target radar cross section (RCS), orbital parameters estimation, SAR echo signal generation and image focusing to build SAR image database. A hybrid algorithm that combines the physical optics, physical difiraction theory, and shooting and bouncing rays was used to compute the RCS of complex radar targets. Such database is vital for aided target recognition and identiflcation system Followed by reformulating the projection kernel in an optimization equation form, the target's re∞ectivity fleld can be accurately estimated. Accordingly, the target's features can be efiectively enhanced and extracted, and the dominant scattering centers are well separated. Experimental results demonstrate that the simulated database developed in this paper is well suited for target recognition. Performance is extensively tested and evaluated from real images by Radarsat-2 and TerraSAR-X. Efiectiveness and e-ciency of the proposed method are further conflrmed.

Enhanced object reconstruction

Abstract: Processing images includes projecting an infra-red pattern onto a three-dimensional object and producing a first image, a second image, and a third image of the three-dimensional object while the pattern is projected on the three-dimensional object. The first image and the second image include the three-dimensional object and the pattern. The first image and the second image are produced by capturing at a first camera and a second camera, respectively, light filtered through an infra-red filter. The third image includes the three-dimensional object but not the pattern. Processing the images also includes establishing a first-pair correspondence between a portion of pixels in the first image and a portion of pixels in the second image. Processing the images further includes constructing, based on the first-pair correspondence and the third image, a two-dimensional image that depicts a three-dimensional construction of the three-dimensional object.

Fuzzy c-means clustering with non local spatial information for noisy image segmentation

Abstract: As an effective image segmentation method, the standard fuzzy c-means (FCM) clustering algorithm is very sensitive to noise in images. Several modified FCM algorithms, using local spatial information, can overcome this problem to some degree. However, when the noise level in the image is high, these algorithms still cannot obtain satisfactory segmentation performance. In this paper, we introduce a non local spatial constraint term into the objective function of FCM and propose a fuzzy cmeans clustering algorithm with non local spatial information (FCM_NLS). FCM_NLS can deal more effectively with the image noise and preserve geometrical edges in the image. Performance evaluation experiments on synthetic and real images, especially magnetic resonance (MR) images, show that FCM_NLS is more robust than both the standard FCM and the modified FCM algorithms using local spatial information for noisy image segmentation.

A Spatial Correlation-Based Image Compression Framework for Wireless Multimedia Sensor Networks

Abstract: Data redundancy caused by correlation has motivated the application of collaborative multimedia in-network processing for data filtering and compression in wireless multimedia sensor networks (WMSNs). This paper proposes an information theoretic image compression framework with an objective to maximize the overall compression of the visual information gathered in a WMSN. The novelty of this framework relies on its independence of specific image types and coding algorithms, thereby providing a generic mechanism for image compression under different coding solutions. The proposed framework consists of two components. First, an entropy-based divergence measure (EDM) scheme is proposed to predict the compression efficiency of performing joint coding on the images collected by spatially correlated cameras. The EDM only takes camera settings as inputs without requiring statistics of real images. Utilizing the predicted results from EDM, a distributed multi-cluster coding protocol (DMCP) is then proposed to construct a compression-oriented coding hierarchy. The DMCP aims to partition the entire network into a set of coding clusters such that the global coding gain is maximized. Moreover, in order to enhance decoding reliability at data sink, the DMCP also guarantees that each sensor camera is covered by at least two different coding clusters. Experiments on H.264 standards show that the proposed EDM can effectively predict the joint coding efficiency from multiple sources. Further simulations demonstrate that the proposed compression framework can reduce 10%-23% total coding rate compared with the individual coding scheme, i.e., each camera sensor compresses its own image independently.

Image capturing device including lens array and processing

Abstract: Disclosed herein is an image pickup apparatus, including: an image pickup lens; a lens array disposed on an image formation plane of the image pickup lens; an image pickup device adapted to receive a light ray passing through the image pickup lens and the lens array to acquire picked up image data; and an image processing section adapted to carry out an image process for the picked up image data; the image processing section including a viewpoint image production section adapted to produce a plurality of viewpoint images based on the picked up image data, and an image synthesis processing section adapted to synthesize two or more viewpoint images from among the viewpoint images.

Edge Detection with sub-pixel accuracy based on approximation of Edge with Erf function

Abstract: Edge detection is an often used procedure in digital image processing. For some practical applications it is desirable to detect edges with sub-pixel accuracy. In this paper we present edge detection method for 1-D images based on approximation of real image function with Erf function. This method is verified by simulations and experiments for various numbers of samples of simulated and real images. Results of simulations and experiments are also used to compare proposed edge detection scheme with two often used moment-based edge detectors with sub-pixel precision.

Retinal image restoration by means of blind deconvolution.

Abstract: Retinal imaging plays a key role in the diagnosis and management of ophthalmologic disorders, such as diabetic retinopathy, glaucoma, and age-related macular degeneration. Because of the acquisition process, retinal images often suffer from blurring and uneven illumination. This problem may seriously affect disease diagnosis and progression assessment. Here we present a method for color retinal image restoration by means of multichannel blind deconvolution. The method is applied to a pair of retinal images acquired within a lapse of time, ranging from several minutes to months. It consists of a series of preprocessing steps to adjust the images so they comply with the considered degradation model, followed by the estimation of the point-spread function and, ultimately, image deconvolution. The preprocessing is mainly composed of image registration, uneven illumination compensation, and segmentation of areas with structural changes. In addition, we have developed a procedure for the detection and visualization of structural changes. This enables the identification of subtle developments in the retina not caused by variation in illumination or blur. The method was tested on synthetic and real images. Encouraging experimental results show that the method is capable of significant restoration of degraded retinal images.

RGB-D camera-based parallel tracking and meshing

Abstract: Compared to standard color cameras, RGB-D cameras are designed to additionally provide the depth of imaged pixels which in turn results in a dense colored 3D point cloud representing the environment from a certain viewpoint. We present a real-time tracking method that performs motion estimation of a consumer RGB-D camera with respect to an unknown environment while at the same time reconstructing this environment as a dense textured mesh. Unlike parallel tracking and mapping performed with a standard color or grey scale camera, tracking with an RGB-D camera allows a correctly scaled camera motion estimation. Therefore, there is no need for measuring the environment by any additional tool or equipping the environment by placing objects in it with known sizes. The tracking can be directly started and does not require any preliminary known and/or constrained camera motion. The colored point clouds obtained from every RGB-D image are used to create textured meshes representing the environment from a certain camera view and the real-time estimated camera motion is used to correctly align these meshes over time in order to combine them into a dense reconstruction of the environment. We quantitatively evaluated the proposed method using real image sequences of a challenging scenario and their corresponding ground truth motion obtained with a mechanical measurement arm. We also compared it to a commonly used state-of-the-art method where only the color information is used. We show the superiority of the proposed tracking in terms of accuracy, robustness and usability. We also demonstrate its usage in several Augmented Reality scenarios where the tracking allows a reliable camera motion estimation and the meshing increases the realism of the augmentations by correctly handling their occlusions.

A new image-based method for concrete bridge bottom crack detection

Abstract: Crack detection is crucial for safety and cost-effective maintenance of concrete structures. Researchers have proposed several methods based on machine vision techniques to inspect the cracks on the bottom surface of concrete bridges, such as Fujita's method. However, it is difficult to obtain high-quality images and image processing results because of complex environmental and light conditions under bridges. In this study, we propose a new method of crack image processing for concrete bridge bottom crack inspections to solve this problem. We build a machine vision system based on this method, which could detect cracks in real time. We examine the efficiency of the proposed system by evaluating it with real images of cracks and compare them with other image processing methods. In terms of efficiency and accuracy of detecting cracks, experimental results show that proposed method is superior to conventional methods in complex environments under bridges.