Showing papers on "Pixel published in 2011"

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

Abstract: Most state-of-the-art techniques for multi-class image segmentation and labeling use conditional random fields defined over pixels or image regions. While region-level models often feature dense pairwise connectivity, pixel-level models are considerably larger and have only permitted sparse graph structures. In this paper, we consider fully connected CRF models defined on the complete set of pixels in an image. The resulting graphs have billions of edges, making traditional inference algorithms impractical. Our main contribution is a highly efficient approximate inference algorithm for fully connected CRF models in which the pairwise edge potentials are defined by a linear combination of Gaussian kernels. Our experiments demonstrate that dense connectivity at the pixel level substantially improves segmentation and labeling accuracy.

ViBe: A Universal Background Subtraction Algorithm for Video Sequences

Abstract: This paper presents a technique for motion detection that incorporates several innovative mechanisms. For example, our proposed technique stores, for each pixel, a set of values taken in the past at the same location or in the neighborhood. It then compares this set to the current pixel value in order to determine whether that pixel belongs to the background, and adapts the model by choosing randomly which values to substitute from the background model. This approach differs from those based upon the classical belief that the oldest values should be replaced first. Finally, when the pixel is found to be part of the background, its value is propagated into the background model of a neighboring pixel. We describe our method in full details (including pseudo-code and the parameter values used) and compare it to other background subtraction techniques. Efficiency figures show that our method outperforms recent and proven state-of-the-art methods in terms of both computation speed and detection rate. We also analyze the performance of a downscaled version of our algorithm to the absolute minimum of one comparison and one byte of memory per pixel. It appears that even such a simplified version of our algorithm performs better than mainstream techniques.

SIFT Flow: Dense Correspondence across Scenes and Its Applications

Abstract: While image alignment has been studied in different areas of computer vision for decades, aligning images depicting different scenes remains a challenging problem. Analogous to optical flow, where an image is aligned to its temporally adjacent frame, we propose SIFT flow, a method to align an image to its nearest neighbors in a large image corpus containing a variety of scenes. The SIFT flow algorithm consists of matching densely sampled, pixelwise SIFT features between two images while preserving spatial discontinuities. The SIFT features allow robust matching across different scene/object appearances, whereas the discontinuity-preserving spatial model allows matching of objects located at different parts of the scene. Experiments show that the proposed approach robustly aligns complex scene pairs containing significant spatial differences. Based on SIFT flow, we propose an alignment-based large database framework for image analysis and synthesis, where image information is transferred from the nearest neighbors to a query image according to the dense scene correspondence. This framework is demonstrated through concrete applications such as motion field prediction from a single image, motion synthesis via object transfer, satellite image registration, and face recognition.

Hyperspectral Image Classification Using Dictionary-Based Sparse Representation

Abstract: A new sparsity-based algorithm for the classification of hyperspectral imagery is proposed in this paper. The proposed algorithm relies on the observation that a hyperspectral pixel can be sparsely represented by a linear combination of a few training samples from a structured dictionary. The sparse representation of an unknown pixel is expressed as a sparse vector whose nonzero entries correspond to the weights of the selected training samples. The sparse vector is recovered by solving a sparsity-constrained optimization problem, and it can directly determine the class label of the test sample. Two different approaches are proposed to incorporate the contextual information into the sparse recovery optimization problem in order to improve the classification performance. In the first approach, an explicit smoothing constraint is imposed on the problem formulation by forcing the vector Laplacian of the reconstructed image to become zero. In this approach, the reconstructed pixel of interest has similar spectral characteristics to its four nearest neighbors. The second approach is via a joint sparsity model where hyperspectral pixels in a small neighborhood around the test pixel are simultaneously represented by linear combinations of a few common training samples, which are weighted with a different set of coefficients for each pixel. The proposed sparsity-based algorithm is applied to several real hyperspectral images for classification. Experimental results show that our algorithm outperforms the classical supervised classifier support vector machines in most cases.

A QVGA 143 dB Dynamic Range Frame-Free PWM Image Sensor With Lossless Pixel-Level Video Compression and Time-Domain CDS

Abstract: The biomimetic CMOS dynamic vision and image sensor described in this paper is based on a QVGA (304×240) array of fully autonomous pixels containing event-based change detection and pulse-width-modulation (PWM) imaging circuitry. Exposure measurements are initiated and carried out locally by the individual pixel that has detected a change of brightness in its field-of-view. Pixels do not rely on external timing signals and independently and asynchronously request access to an (asynchronous arbitrated) output channel when they have new grayscale values to communicate. Pixels that are not stimulated visually do not produce output. The visual information acquired from the scene, temporal contrast and grayscale data, are communicated in the form of asynchronous address-events (AER), with the grayscale values being encoded in inter-event intervals. The pixel-autonomous and massively parallel operation ideally results in lossless video compression through complete temporal redundancy suppression at the pixel level. Compression factors depend on scene activity and peak at ~1000 for static scenes. Due to the time-based encoding of the illumination information, very high dynamic range - intra-scene DR of 143 dB static and 125 dB at 30 fps equivalent temporal resolution - is achieved. A novel time-domain correlated double sampling (TCDS) method yields array FPN of 56 dB (9.3 bit) for >10 Lx illuminance.

Removal of High Density Salt and Pepper Noise Through Modified Decision Based Unsymmetric Trimmed Median Filter

Abstract: A modified decision based unsymmetrical trimmed median filter algorithm for the restoration of gray scale, and color images that are highly corrupted by salt and pepper noise is proposed in this paper. The proposed algorithm replaces the noisy pixel by trimmed median value when other pixel values, 0's and 255's are present in the selected window and when all the pixel values are 0's and 255's then the noise pixel is replaced by mean value of all the elements present in the selected window. This proposed algorithm shows better results than the Standard Median Filter (MF), Decision Based Algorithm (DBA), Modified Decision Based Algorithm (MDBA), and Progressive Switched Median Filter (PSMF). The proposed algorithm is tested against different grayscale and color images and it gives better Peak Signal-to-Noise Ratio (PSNR) and Image Enhancement Factor (IEF).

Efficient Reversible Watermarking Based on Adaptive Prediction-Error Expansion and Pixel Selection

Abstract: Prediction-error expansion (PEE) is an important technique of reversible watermarking which can embed large payloads into digital images with low distortion. In this paper, the PEE technique is further investigated and an efficient reversible watermarking scheme is proposed, by incorporating in PEE two new strategies, namely, adaptive embedding and pixel selection. Unlike conventional PEE which embeds data uniformly, we propose to adaptively embed 1 or 2 bits into expandable pixel according to the local complexity. This avoids expanding pixels with large prediction-errors, and thus, it reduces embedding impact by decreasing the maximum modification to pixel values. Meanwhile, adaptive PEE allows very large payload in a single embedding pass, and it improves the capacity limit of conventional PEE. We also propose to select pixels of smooth area for data embedding and leave rough pixels unchanged. In this way, compared with conventional PEE, a more sharply distributed prediction-error histogram is obtained and a better visual quality of watermarked image is observed. With these improvements, our method outperforms conventional PEE. Its superiority over other state-of-the-art methods is also demonstrated experimentally.

Fast and Accurate Detection and Classification of Plant Diseases

Abstract: We propose and experimentally evaluate a software solution for automatic detection and classification of plant leaf diseases. The proposed solution is an improvement to the solution proposed in [1] as it provides faster and more accurate solution. The developed processing scheme consists of four main phases as in [1]. The following two steps are added successively after the segmentation phase. In the first step we identify the mostlygreen colored pixels. Next, these pixels are masked based on specific threshold values that are computed using Otsu's method, then those mostly green pixels are masked. The other additional step is that the pixels with zeros red, green and blue values and the pixels on the boundaries of the infected cluster (object) were completely removed. The experimental results demonstrate that the proposed technique is a robust technique for the detection of plant leaves diseases. The developed algorithm‟s efficiency can successfully detect and classify the examined diseases with a precision between 83% and 94%, and can achieve 20% speedup over the approach proposed in [1].

Statistically optimized inversion algorithm for enhanced retrieval of aerosol properties from spectral multi-angle polarimetric satellite observations

Abstract: . The proposed development is an attempt to enhance aerosol retrieval by emphasizing statistical optimization in inversion of advanced satellite observations. This optimization concept improves retrieval accuracy relying on the knowledge of measurement error distribution. Efficient application of such optimization requires pronounced data redundancy (excess of the measurements number over number of unknowns) that is not common in satellite observations. The POLDER imager on board the PARASOL micro-satellite registers spectral polarimetric characteristics of the reflected atmospheric radiation at up to 16 viewing directions over each observed pixel. The completeness of such observations is notably higher than for most currently operating passive satellite aerosol sensors. This provides an opportunity for profound utilization of statistical optimization principles in satellite data inversion. The proposed retrieval scheme is designed as statistically optimized multi-variable fitting of all available angular observations obtained by the POLDER sensor in the window spectral channels where absorption by gas is minimal. The total number of such observations by PARASOL always exceeds a hundred over each pixel and the statistical optimization concept promises to be efficient even if the algorithm retrieves several tens of aerosol parameters. Based on this idea, the proposed algorithm uses a large number of unknowns and is aimed at retrieval of extended set of parameters affecting measured radiation. The algorithm is designed to retrieve complete aerosol properties globally. Over land, the algorithm retrieves the parameters of underlying surface simultaneously with aerosol. In all situations, the approach is anticipated to achieve a robust retrieval of complete aerosol properties including information about aerosol particle sizes, shape, absorption and composition (refractive index). In order to achieve reliable retrieval from PARASOL observations even over very reflective desert surfaces, the algorithm was designed as simultaneous inversion of a large group of pixels within one or several images. Such multi-pixel retrieval regime takes advantage of known limitations on spatial and temporal variability in both aerosol and surface properties. Specifically the variations of the retrieved parameters horizontally from pixel-to-pixel and/or temporary from day-to-day are enforced to be smooth by additional a priori constraints. This concept is expected to provide satellite retrieval of higher consistency, because the retrieval over each single pixel will be benefiting from coincident aerosol information from neighboring pixels, as well, from the information about surface reflectance (over land) obtained in preceding and consequent observations over the same pixel. The paper provides in depth description of the proposed inversion concept, illustrates the algorithm performance by a series of numerical tests and presents the examples of preliminary retrieval results obtained from actual PARASOL observations. It should be noted that many aspects of the described algorithm design considerably benefited from experience accumulated in the preceding effort on developments of currently operating AERONET and PARASOL retrievals, as well as several core software components were inherited from those earlier algorithms.

A New Pan-Sharpening Method Using a Compressed Sensing Technique

Abstract: This paper addresses the remote sensing image pan-sharpening problem from the perspective of compressed sensing (CS) theory which ensures that with the sparsity regularization, a compressible signal can be correctly recovered from the global linear sampled data. First, the degradation model from a high- to low-resolution multispectral (MS) image and high-resolution panchromatic (PAN) image is constructed as a linear sampling process which is formulated as a matrix. Then, the model matrix is considered as the measurement matrix in CS, so pan-sharpening is converted into signal restoration problem with sparsity regularization. Finally, the basis pursuit (BP) algorithm is used to resolve the restoration problem, which can recover the high-resolution MS image effectively. The QuickBird and IKONOS satellite images are used to test the proposed method. The experimental results show that the proposed method can well preserve spectral and spatial details of the source images. The pan-sharpened high-resolution MS image by the proposed method is competitive or even superior to those images fused by other well-known methods.

Contextual and Variational Contrast Enhancement

Abstract: This paper proposes an algorithm that enhances the contrast of an input image using interpixel contextual information. The algorithm uses a 2-D histogram of the input image constructed using a mutual relationship between each pixel and its neighboring pixels. A smooth 2-D target histogram is obtained by minimizing the sum of Frobenius norms of the differences from the input histogram and the uniformly distributed histogram. The enhancement is achieved by mapping the diagonal elements of the input histogram to the diagonal elements of the target histogram. Experimental results show that the algorithm produces better or comparable enhanced images than four state-of-the-art algorithms.

System for capturing a document in an image signal

Abstract: Devices, methods, and software are disclosed for capturing a frame of image data having a representation of a feature. In an illustrative embodiment, a device includes an imaging subsystem, one or more memory components, and a processor. The imaging subsystem is capable of providing image data representative of light incident on said imaging subsystem. The one or more memory components include at least a first memory component operatively capable of storing an input frame of the image data. The processor is in communicative connection with executable instructions for enabling the processor for various steps. One step includes receiving the input frame from the first memory component. Another step includes generating a reduced resolution frame based on the input frame, the reduced resolution frame comprising fewer pixels than the input frame, in which a pixel in the reduced resolution frame combines information from two or more pixels in the input frame. Another step includes attempting to identify transition pairs comprising pairs of adjacent pixels in the reduced resolution frame having differences between the pixels that exceed a pixel transition threshold. Another step includes attempting to identify one or more linear features between two or more identified transition pairs in the reduced resolution frame. Another step includes providing an indication of one or more identified linear features in the reduced resolution frame.

Hyperspectral image classification via kernel sparse representation

Abstract: In this paper, a new technique for hyperspectral image classification is proposed. Our approach relies on the sparse representation of a test sample with respect to all training samples in a feature space induced by a kernel function. Projecting the samples into the feature space and kernelizing the sparse representation improves the separability of the data and thus yields higher classification accuracy compared to the more conventional linear sparsity-based classification algorithm. Moreover, the spatial coherence across neighboring pixels is also incorporated through a kernelized joint sparsity model, where all of the pixels within a small neighborhood are sparsely represented in the feature space by selecting a few common training samples. Two greedy algorithms are also provided in this paper to solve the kernel versions of the pixel-wise and jointly sparse recovery problems. Experimental results show that the proposed technique outperforms the linear sparsity-based classification technique and the classical Support Vector Machine classifiers.

Indicia reading terminal with color frame processing

Abstract: An indicia reading terminal can comprise an image sensor integrated circuit having a two-dimensional image sensor, a hand held housing encapsulating the two-dimensional image sensor, and an imaging lens configured to focus an image of a target decodable indicia onto the two-dimensional image sensor. The two-dimensional image sensor can include a plurality of pixels arranged in repetitive patterns. Each pattern can include at least one pixel sensitive in a first spectrum region, at least one pixel sensitive in a second spectrum region, and at least one pixel sensitive in a third spectrum region. The image sensor integrated circuit can be configured to capture a frame of image data by reading out a plurality of analog signals. Each read out analog signal can be representative of light incident on a group of two or more pixels of the plurality of pixels. The image sensor integrated circuit can be further configured to convert the plurality of analog signals to a plurality of digital signals and to store the plurality of digital signals in a memory. The indicia reading terminal can be operative to process the frame of image data for attempting to decode for decodable indicia.

Optical indicia reading terminal with color image sensor

Abstract: An optical indicia reading terminal can comprise a microprocessor, a memory, and an image sensor integrated circuit, all coupled to a system bus, and a hand held housing encapsulating the two-dimensional image sensor. The image sensor integrated circuit can comprise a two-dimensional image sensor including a plurality of pixels. The image sensor integrated circuit can be configured to read out a plurality of analog signals. Each analog signal of the plurality of analog signals can be representative of light incident on at least one pixel of the plurality of pixels. The image sensor integrated circuit can be further configured to derive a plurality of luminance signals from the plurality of analog signals, each luminance signal being representative of the luminance of light incident on at least one pixel of the plurality of pixels. The image sensor integrated circuit can be further configured to store a frame of image data in the terminal's memory by converting the plurality of luminance signals to a plurality of digital values, each digital value being representative of the luminance of light incident on at least one pixel of the plurality of pixels. The optical indicia reading terminal can be configured to process the frame of image data for decoding decodable indicia.

A global sampling method for alpha matting

Abstract: Alpha matting refers to the problem of softly extracting the foreground from an image. Given a trimap (specifying known foreground/background and unknown pixels), a straightforward way to compute the alpha value is to sample some known foreground and background colors for each unknown pixel. Existing sampling-based matting methods often collect samples near the unknown pixels only. They fail if good samples cannot be found nearby. In this paper, we propose a global sampling method that uses all samples available in the image. Our global sample set avoids missing good samples. A simple but effective cost function is defined to tackle the ambiguity in the sample selection process. To handle the computational complexity introduced by the large number of samples, we pose the sampling task as a correspondence problem. The correspondence search is efficiently achieved by generalizing a randomized algorithm previously designed for patch matching[3]. A variety of experiments show that our global sampling method produces both visually and quantitatively high-quality matting results.

Local Intensity Order Pattern for feature description

Abstract: This paper presents a novel method for feature description based on intensity order. Specifically, a Local Intensity Order Pattern(LIOP) is proposed to encode the local ordinal information of each pixel and the overall ordinal information is used to divide the local patch into subregions which are used for accumulating the LIOPs respectively. Therefore, both local and overall intensity ordinal information of the local patch are captured by the proposed LIOP descriptor so as to make it a highly discriminative descriptor. It is shown that the proposed descriptor is not only invariant to monotonic intensity changes and image rotation but also robust to many other geometric and photometric transformations such as viewpoint change, image blur and JEPG compression. The proposed descriptor has been evaluated on the standard Oxford dataset and four additional image pairs with complex illumination changes. The experimental results show that the proposed descriptor obtains a significant improvement over the existing state-of-the-art descriptors.

Semiconductor display device

Abstract: To provide a semiconductor display device capable of displaying an image having clarity and a desired color, even when the speed of deterioration of an EL layer is influenced by its environment. Display pixels and sensor pixels of an EL display each have an EL element, and the sensor pixels each have a diode. The luminance of the EL elements of each in the display pixels is controlled in accordance with the amount of electric current flowing in each of the diodes.

Method and system operative to process monochrome image data

Abstract: A method and system operative to process monochrome image data are disclosed. In one embodiment, the method can comprise the steps of receiving monochrome image data, segmenting the input pixel values into pixel value ranges, assigning pixel positions in the lowest pixel value range an output pixel value of a first binary value, assigning pixel positions in the highest pixel value range an output pixel value of a second binary value, wherein the first and second binary values are different, and assigning pixel positions in intermediate pixel value ranges output pixel values that correspond to a spatial binary pattern. The resulting binary image data can be written to a file for subsequent storage, transmission, processing, or retrieval and rendering. In further embodiments, a system can be made operative to accomplish the same.

The FE-I4 pixel readout integrated circuit

Abstract: A new pixel readout integrated circuit denominated FE-I4 is being designed to meet the requirements of ATLAS experiment upgrades. It will be the largest readout IC produced to date for particle physics applications, filling the maximum allowed reticle area. This will significantly reduce the cost of future hybrid pixel detectors. In addition, FE-I4 will have smaller pixels and higher rate capability than the present generation of LHC pixel detectors. Design features are described along with simulation and test results, including low power and high rate readout architecture, mixed signal design strategy, and yield hardening.

Depth camera based on structured light and stereo vision

Abstract: A depth camera system uses a structured light illuminator and multiple sensors such as infrared light detectors, such as in a system which tracks the motion of a user in a field of view. One sensor can be optimized for shorter range detection while another sensor is optimized for longer range detection. The sensors can have a different baseline distance from the illuminator, as well as a different spatial resolution, exposure time and sensitivity. In one approach, depth values are obtained from each sensor by matching to the structured light pattern, and the depth values are merged to obtain a final depth map which is provided as an input to an application. The merging can involve unweighted averaging, weighted averaging, accuracy measures and/or confidence measures. In another approach, additional depth values which are included in the merging are obtained using stereoscopic matching among pixel data of the sensors.

Single-image shadow detection and removal using paired regions

Abstract: In this paper, we address the problem of shadow detection and removal from single images of natural scenes. Different from traditional methods that explore pixel or edge information, we employ a region based approach. In addition to considering individual regions separately, we predict relative illumination conditions between segmented regions from their appearances and perform pairwise classification based on such information. Classification results are used to build a graph of segments, and graph-cut is used to solve the labeling of shadow and non-shadow regions. Detection results are later refined by image matting, and the shadow free image is recovered by relighting each pixel based on our lighting model. We evaluate our method on the shadow detection dataset in [19]. In addition, we created a new dataset with shadow-free ground truth images, which provides a quantitative basis for evaluating shadow removal.

Gradient Profile Prior and Its Applications in Image Super-Resolution and Enhancement

Abstract: In this paper, we propose a novel generic image prior-gradient profile prior, which implies the prior knowledge of natural image gradients. In this prior, the image gradients are represented by gradient profiles, which are 1-D profiles of gradient magnitudes perpendicular to image structures. We model the gradient profiles by a parametric gradient profile model. Using this model, the prior knowledge of the gradient profiles are learned from a large collection of natural images, which are called gradient profile prior. Based on this prior, we propose a gradient field transformation to constrain the gradient fields of the high resolution image and the enhanced image when performing single image super-resolution and sharpness enhancement. With this simple but very effective approach, we are able to produce state-of-the-art results. The reconstructed high resolution images or the enhanced images are sharp while have rare ringing or jaggy artifacts.

Single image super-resolution using Gaussian process regression

Abstract: In this paper we address the problem of producing a high-resolution image from a single low-resolution image without any external training set. We propose a framework for both magnification and deblurring using only the original low-resolution image and its blurred version. In our method, each pixel is predicted by its neighbors through the Gaussian process regression. We show that when using a proper covariance function, the Gaussian process regression can perform soft clustering of pixels based on their local structures. We further demonstrate that our algorithm can extract adequate information contained in a single low-resolution image to generate a high-resolution image with sharp edges, which is comparable to or even superior in quality to the performance of other edge-directed and example-based super-resolution algorithms. Experimental results also show that our approach maintains high-quality performance at large magnifications.

NL-InSAR: Nonlocal Interferogram Estimation

Abstract: Interferometric synthetic aperture radar (SAR) data provide reflectivity, interferometric phase, and coherence images, which are paramount to scene interpretation or low-level processing tasks such as segmentation and 3-D reconstruction. These images are estimated in practice from a Hermitian product on local windows. These windows lead to biases and resolution losses due to the local heterogeneity caused by edges and textures. This paper proposes a nonlocal approach for the joint estimation of the reflectivity, the interferometric phase, and the coherence images from an interferometric pair of coregistered single-look complex (SLC) SAR images. Nonlocal techniques are known to efficiently reduce noise while preserving structures by performing the weighted averaging of similar pixels. Two pixels are considered similar if the surrounding image patches are “resembling.” Patch similarity is usually defined as the Euclidean distance between the vectors of graylevels. In this paper, a statistically grounded patch-similarity criterion suitable to SLC images is derived. A weighted maximum likelihood estimation of the SAR interferogram is then computed with weights derived in a data-driven way. Weights are defined from the intensity and interferometric phase and are iteratively refined based both on the similarity between noisy patches and on the similarity of patches from the previous estimate. The efficiency of this new interferogram construction technique is illustrated both qualitatively and quantitatively on synthetic and true data.