Showing papers on "Standard test image published in 2010"

Large Scale Online Learning of Image Similarity Through Ranking

Abstract: Learning a measure of similarity between pairs of objects is an important generic problem in machine learning. It is particularly useful in large scale applications like searching for an image that is similar to a given image or finding videos that are relevant to a given video. In these tasks, users look for objects that are not only visually similar but also semantically related to a given object. Unfortunately, the approaches that exist today for learning such semantic similarity do not scale to large data sets. This is both because typically their CPU and storage requirements grow quadratically with the sample size, and because many methods impose complex positivity constraints on the space of learned similarity functions. The current paper presents OASIS, an Online Algorithm for Scalable Image Similarity learning that learns a bilinear similarity measure over sparse representations. OASIS is an online dual approach using the passive-aggressive family of learning algorithms with a large margin criterion and an efficient hinge loss cost. Our experiments show that OASIS is both fast and accurate at a wide range of scales: for a data set with thousands of images, it achieves better results than existing state-of-the-art methods, while being an order of magnitude faster. For large, web scale, data sets, OASIS can be trained on more than two million images from 150K text queries within 3 days on a single CPU. On this large scale data set, human evaluations showed that 35% of the ten nearest neighbors of a given test image, as found by OASIS, were semantically relevant to that image. This suggests that query independent similarity could be accurately learned even for large scale data sets that could not be handled before.

A Generative Model for Image Segmentation Based on Label Fusion

Abstract: We propose a nonparametric, probabilistic model for the automatic segmentation of medical images, given a training set of images and corresponding label maps. The resulting inference algorithms rely on pairwise registrations between the test image and individual training images. The training labels are then transferred to the test image and fused to compute the final segmentation of the test subject. Such label fusion methods have been shown to yield accurate segmentation, since the use of multiple registrations captures greater inter-subject anatomical variability and improves robustness against occasional registration failures. To the best of our knowledge, this manuscript presents the first comprehensive probabilistic framework that rigorously motivates label fusion as a segmentation approach. The proposed framework allows us to compare different label fusion algorithms theoretically and practically. In particular, recent label fusion or multiatlas segmentation algorithms are interpreted as special cases of our framework. We conduct two sets of experiments to validate the proposed methods. In the first set of experiments, we use 39 brain MRI scans - with manually segmented white matter, cerebral cortex, ventricles and subcortical structures - to compare different label fusion algorithms and the widely-used FreeSurfer whole-brain segmentation tool. Our results indicate that the proposed framework yields more accurate segmentation than FreeSurfer and previous label fusion algorithms. In a second experiment, we use brain MRI scans of 282 subjects to demonstrate that the proposed segmentation tool is sufficiently sensitive to robustly detect hippocampal volume changes in a study of aging and Alzheimer's Disease.

A DCT Statistics-Based Blind Image Quality Index

Abstract: The development of general-purpose no-reference approaches to image quality assessment still lags recent advances in full-reference methods. Additionally, most no-reference or blind approaches are distortion-specific, meaning they assess only a specific type of distortion assumed present in the test image (such as blockiness, blur, or ringing). This limits their application domain. Other approaches rely on training a machine learning algorithm. These methods however, are only as effective as the features used to train their learning machines. Towards ameliorating this we introduce the BLIINDS index (BLind Image Integrity Notator using DCT Statistics) which is a no-reference approach to image quality assessment that does not assume a specific type of distortion of the image. It is based on predicting image quality based on observing the statistics of local discrete cosine transform coefficients, and it requires only minimal training. The method is shown to correlate highly with human perception of quality.

The Dresden Image Database for Benchmarking Digital Image Forensics

Abstract: This article introduces and documents a novel image database specifically built for the purpose of development and benchmarking of camera-based digital forensic techniques. More than 14,000 images of various indoor and outdoor scenes have been acquired under controlled and thus widely comparable conditions from altogether 73 digital cameras. The cameras were drawn from only 25 different models to ensure that device-specific and model-specific characteristics can be disentangled and studied separately, as validated with results in this article. In addition, auxiliary images for the estimation of device-specific sensor noise pattern were collected for each camera. Another subset of images to study model-specific JPEG compression algorithms has been compiled for each model. The Dresden Image Database is freely available for scientific purposes. The database is intended to become a useful resource for researchers and forensic investigators. Using a standard database as a benchmark makes results more ...

Binarization of historical document images using the local maximum and minimum

Abstract: This paper presents a new document image binarization technique that segments the text from badly degraded historical document images. The proposed technique makes use of the image contrast that is defined by the local image maximum and minimum. Compared with the image gradient, the image contrast evaluated by the local maximum and minimum has a nice property that it is more tolerant to the uneven illumination and other types of document degradation such as smear. Given a historical document image, the proposed technique first constructs a contrast image and then detects the high contrast image pixels which usually lie around the text stroke boundary. The document text is then segmented by using local thresholds that are estimated from the detected high contrast pixels within a local neighborhood window. The proposed technique has been tested over the dataset that is used in the recent Document Image Binarization Contest (DIBCO) 2009. Experiments show its superior performance.

Detecting Double JPEG Compression With the Same Quantization Matrix

Abstract: Detection of double joint photographic experts group (JPEG) compression is of great significance in the field of digital forensics. Some successful approaches have been presented for detecting double JPEG compression when the primary compression and the secondary compression have different quantization matrixes. However, when the primary compression and the secondary compression have the same quantization matrix, no detection method has been reported yet. In this paper, we present a method which can detect double JPEG compression with the same quantization matrix. Our algorithm is based on the observation that in the process of recompressing a JPEG image with the same quantization matrix over and over again, the number of different JPEG coefficients, i.e., the quantized discrete cosine transform coefficients between the sequential two versions will monotonically decrease in general. For example, the number of different JPEG coefficients between the singly and doubly compressed images is generally larger than the number of different JPEG coefficients between the corresponding doubly and triply compressed images. Via a novel random perturbation strategy implemented on the JPEG coefficients of the recompressed test image, we can find a “proper” randomly perturbed ratio. For different images, this universal “proper” ratio will generate a dynamically changed threshold, which can be utilized to discriminate the singly compressed image and doubly compressed image. Furthermore, our method has the potential to detect triple JPEG compression, four times JPEG compression, etc.

Implementation and Comparative Study of Image Fusion Algorithms

Abstract: Image Fusion is a process of combining the relevant information from a set of images, into a single image, wherein the resultant fused image will be more informative and complete than any of the input images. This paper discusses the implementation of three categories of image fusion algorithms – the basic fusion algorithms, the pyramid based algorithms and the basic DWT algorithms, developed as an Image Fusion Toolkit - ImFus, using Visual C++ 6.0. The objective of the paper is to assess the wide range of algorithms together, which is not found in the literature. The fused images were assessed using Structural Similarity Image Metric (SSIM) [10], Laplacian Mean Squared Error along with seven other simple image quality metrics that helped us measure the various image features; which were also implemented as part of the toolkit. The readings produced by the image quality metrics, based on the image quality of the fused images, were used to assess the algorithms. We used Pareto Optimization method to figure out the algorithm that consistently had the image quality metrics produce the best readings. An assessment of the quality of the fused images was additionally performed with the help of ten respondents based on their visual perception, to verify the results produced by the metric based assessment. Coincidentally, both the assessment methods matched in their raking of the algorithms. The Pareto Optimization method picked DWT with Haar fusion method as the one with the best image quality metrics readings. The result here was substantiated by the visual perception based method where it was inferred that fused images produced by DWT with Haar fusion method was marked the best 63.33% of times which was far better than any other algorithm. Both the methods also matched in assessing Morphological Pyramid method as producing fused images of inferior quality.

A Study Of Image Segmentation Algorithms For A Study Of Image Segmentation Algorithms For A Study Of Image Segmentation Algorithms For A Study Of Image Segmentation Algorithms For Different Types Of Images Different Types Of Images Different Types Of Images Different Types Of Images

Abstract: In computer vision, segmentation refers to the process of partitioning a digital image into multiple segments (sets of pixels, also known as superpixels).Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain visual characteristics.The result of image segmentation is a set of segments that collectively cover the entire image, or a set of contours extracted from the image . Each of the pixels in a region are similar with respect to some characteristic or computed property, such as color, intensity, or texture.Due to the importance of image segmentation a number of algorithms have been proposed but based on the image that is inputted the algorithm should be chosen to get the best results. In this paper the author gives a study of the various algorithms that are available for color images,text and gray scale images.

Face Authentication Using Recognition-by-Parts, Boosting, and Transduction

Abstract: A robust recognition-by-parts authentication system for comparing and authenticating a test image with at least one training image is disclosed. This invention applies the concepts of recognition-by-parts, boosting, and transduction.

New Learning Based Super-Resolution: Use of DWT and IGMRF Prior

Abstract: In this paper, we propose a new learning-based approach for super-resolving an image captured at low spatial resolution. Given the low spatial resolution test image and a database consisting of low and high spatial resolution images, we obtain super-resolution for the test image. We first obtain an initial high-resolution (HR) estimate by learning the high-frequency details from the available database. A new discrete wavelet transform (DWT) based approach is proposed for learning that uses a set of low-resolution (LR) images and their corresponding HR versions. Since the super-resolution is an ill-posed problem, we obtain the final solution using a regularization framework. The LR image is modeled as the aliased and noisy version of the corresponding HR image, and the aliasing matrix entries are estimated using the test image and the initial HR estimate. The prior model for the super-resolved image is chosen as an Inhomogeneous Gaussian Markov random field (IGMRF) and the model parameters are estimated using the same initial HR estimate. A maximum a posteriori (MAP) estimation is used to arrive at the cost function which is minimized using a simple gradient descent approach. We demonstrate the effectiveness of the proposed approach by conducting the experiments on gray scale as well as on color images. The method is compared with the standard interpolation technique and also with existing learning-based approaches. The proposed approach can be used in applications such as wildlife sensor networks, remote surveillance where the memory, the transmission bandwidth, and the camera cost are the main constraints.

Learning full pairwise affinities for spectral segmentation

Abstract: This paper studies the problem of learning a full range of pairwise affinities gained by integrating local grouping cues for spectral segmentation. The overall quality of the spectral segmentation depends mainly on the pairwise pixel affinities. By employing a semi-supervised learning technique, optimal affinities are learnt from the test image without iteration. We first construct a multi-layer graph with pixels and regions, generated by the mean shift algorithm, as nodes. By applying the semi-supervised learning strategy to this graph, we can estimate the intra- and inter-layer affinities between all pairs of nodes together. These pair-wise affinities are then used to simultaneously cluster all pixel and region nodes into visually coherent groups across all layers in a single multi-layer framework of Normalized Cuts. Our algorithm provides high-quality segmentations with object details by directly incorporating the full range connections in the spectral framework. Since the full affinity matrix is defined by the inverse of a sparse matrix, its eigen-decomposition is efficiently computed. The experimental results on Berkeley and MSRC image databases demonstrate the relevance and accuracy of our algorithm as compared to existing popular methods.

Camera Response Functions for Image Forensics: An Automatic Algorithm for Splicing Detection

Abstract: We present a fully automatic method to detect doctored digital images. Our method is based on a rigorous consistency checking principle of physical characteristics among different arbitrarily shaped image regions. In this paper, we specifically study the camera response function (CRF), a fundamental property in cameras mapping input irradiance to output image intensity. A test image is first automatically segmented into distinct arbitrarily shaped regions. One CRF is estimated from each region using geometric invariants from locally planar irradiance points (LPIPs). To classify a boundary segment between two regions as authentic or spliced, CRF-based cross fitting and local image features are computed and fed to statistical classifiers. Such segment level scores are further fused to infer the image level authenticity. Tests on two data sets reach performance levels of 70% precision and 70% recall, showing promising potential for real-world applications. Moreover, we examine individual features and discover the key factor in splicing detection. Our experiments show that the anomaly introduced around splicing boundaries plays the major role in detecting splicing. Such finding is important for designing effective and efficient solutions to image splicing detection.

Image-to-class distance metric learning for image classification

Abstract: Image-To-Class (I2C) distance is first used in Naive-Bayes Nearest-Neighbor (NBNN) classifier for image classification and has successfully handled datasets with large intra-class variances. However, the performance of this distance relies heavily on the large number of local features in the training set and test image, which need heavy computation cost for nearest-neighbor (NN) search in the testing phase. If using small number of local features for accelerating the NN search, the performance will be poor. In this paper, we propose a large margin framework to improve the discrimination of I2C distance especially for small number of local features by learning Per-Class Mahalanobis metrics. Our I2C distance is adaptive to different class by combining with the learned metric for each class. These multiple Per-Class metrics are learned simultaneously by forming a convex optimization problem with the constraints that the I2C distance from each training image to its belonging class should be less than the distance to other classes by a large margin. A gradient descent method is applied to efficiently solve this optimization problem. For efficiency and performance improved, we also adopt the idea of spatial pyramid restriction and learning I2C distance function to improve this I2C distance. We show in experiments that the proposed method can significantly outperform the original NBNN in several prevalent image datasets, and our best results can achieve state-of-the-art performance on most datasets.

Image recognition in an augmented reality application

Abstract: A computer-implemented augmented reality method includes obtaining an image acquired by a computing device running an augmented reality application, identifying image characterizing data in the obtained image, the data identifying characteristic points in the image, comparing the image characterizing data with image characterizing data for a plurality of geo-coded images stored by a computer server system, identifying locations of items in the obtained image using the comparison, and providing, for display on the computing device at the identified locations, data for textual or graphical annotations that correspond to each of the items in the obtained image, and formatted to be displayed with the obtained image or a subsequently acquired image.

An improved histogram of edge local orientations for sketch-based image retrieval

Abstract: Content-based image retrieval requires a natural image (e.g, a photo) as query, but the absence of such a query image is usually the reason for a search. An easy way to express the user query is using a line-based hand-drawing, a sketch, leading to the sketch-based image retrieval. Few authors have addressed image retrieval based on a sketch as query, and the current approaches still keep low performance under scale, translation, and rotation transformations. In this paper, we describe a method based on computing efficiently a histogram of edge local orientations that we call HELO. Our method is based on a strategy applied in the context of fingerprint processing. This descriptor is invariant to scale and translation transformations. To tackle the rotation problem, we apply two normalization processes, one using principal component analysis and the other using polar coordinates. Finally, we linearly combine two distance measures. Our results show that HELO significantly increases the retrieval effectiveness in comparison with the state of the art.

Detecting Content Adaptive Scaling of Images for Forensic Applications

Abstract: Content-aware resizing methods have recently been developed, among which, seam-carving has achieved the most widespread use. Seam-carving's versatility enables deliberate object removal and benign image resizing, in which perceptually important content is preserved. Both types of modifications compromise the utility and validity of the modified images as evidence in legal and journalistic applications. It is therefore desirable that image forensic techniques detect the presence of seam-carving. In this paper we address detection of seam-carving for forensic purposes. As in other forensic applications, we pose the problem of seam-carving detection as the problem of classifying a test image in either of two classes: a) seam-carved or b) non-seam-carved. We adopt a pattern recognition approach in which a set of features is extracted from the test image and then a Support Vector Machine based classifier, trained over a set of images, is utilized to estimate which of the two classes the test image lies in. Based on our study of the seam-carving algorithm, we propose a set of intuitively motivated features for the detection of seam-carving. Our methodology for detection of seam-carving is then evaluated over a test database of images. We demonstrate that the proposed method provides the capability for detecting seam-carving with high accuracy. For images which have been reduced 30% by benign seam-carving, our method provides a classification accuracy of 91%.

Method for assembling a collection of digital images

Abstract: A method for recommending a collection of digital images from a set of images includes specifying at least one image selection criterion. For each of a plurality of images in the set of images, an image quality value for the image is determined. Images are recommended for the collection by taking into consideration the image quality value for the images and the degree to which the collection satisfies the at least one image selection criterion.

Visual user interface validator

Abstract: Various embodiments described or referenced herein are directed to different devices, methods, systems, and computer program products for testing a user interface component. A client-side operation for rendering the user interface component may be performed. The rendered user interface component may be stored as a user interface component test image simulating a visual presentation of the user interface component at a client machine. A user interface component expected image may be retrieved from a storage medium accessible to the server. The user interface component expected image may represent an expected visual presentation of the rendered user interface component. A determination may be made as to whether the user interface component test image matches the user interface component expected image. When the user interface component test image does not match the user interface component expected image, an indication of an error condition may be provided.

Comparison of infrared images

Abstract: Methods for comparing infrared image data and/or for generating infrared image comparison data are provided. In one method two image data sets are selected including visual-light and infrared image data from one or more points of view of a scene. Visual-light image data from each data set can be compared to determine an alignment correlation between different points of view for the visual-light data. The alignment correlation can then be used to correlate infrared image data from each data set. The correlated infrared image data can be compared to generate infrared comparison image data. Thermal imaging cameras capable of performing such methods are also provided.

A globally optimal data-driven approach for image distortion estimation

Abstract: Image alignment in the presence of non-rigid distortions is a challenging task. Typically, this involves estimating the parameters of a dense deformation field that warps a distorted image back to its undistorted template. Generative approaches based on parameter optimization such as Lucas-Kanade can get trapped within local minima. On the other hand, discriminative approaches like Nearest-Neighbor require a large number of training samples that grows exponentially with the desired accuracy. In this work, we develop a novel data-driven iterative algorithm that combines the best of both generative and discriminative approaches. For this, we introduce the notion of a “pull-back” operation that enables us to predict the parameters of the test image using training samples that are not in its neighborhood (not ∊-close) in parameter space. We prove that our algorithm converges to the global optimum using a significantly lower number of training samples that grows only logarithmically with the desired accuracy. We analyze the behavior of our algorithm extensively using synthetic data and demonstrate successful results on experiments with complex deformations due to water and clothing.

Robust Human Authentication Using Holistic Anthropometric and Appearance-Based Features and Boosting

Abstract: A new robust human authentication system, device, and instructions, embeddable in a physical and tangible computer readable medium, for determining if at least one test image obtained using an imaging device matches at least one training image in an enrollment database, are disclosed. This invention applies the concepts of appearance (PCA or PCA+LDA) and holistic anthropometrics that include head, face, neck, and shoulder linear and non-linear geometric measurements. The appearance (“eigen”) coefficients and holistic anthropometric measurements selected may be used as feature vectors. A boosting algorithm ranks features as “weak learners” and combines their outputs for “strong” recognition.

A method and system for detection and enhancement of video images

Abstract: A method and a system for adaptive image enhancement are provided for measuring the image quality of a pixel region in a frame, performing an image classification based on the image quality measurement, and enhancing image quality by applying operations according to image classification of the region. Also provided is a method as above including the steps of dividing a frame into P pixel regions; and for each one of the pixel regions measuring the image quality; assigning an image quality class; and enhancing the image. Also provided is a system for adaptive image enhancement including a circuit to measure the image quality of a pixel region in a frame in a source video image; a circuit to perform an image classification of the region based on the image quality measurement; and a circuit to enhance the image quality of the region in the source video image a by applying operations based on the image classification of the frame.

Graphical data processing

Abstract: A method of controlling graphical data compression levels for a series of images of varying area in order to maintain a consistent image quality, irrespective of image area. An image of a first area is compressed using a first compression value. When the first image is decompressed for display, it is associated with a first image quality. When a new image with a different area is generated, it is compressed using a new compression value derived from the first compression value. The new compression value is suitable for delivering an image quality, when the new image is decompressed for display, substantially the same as the image quality of the first image.

Robust face recognition using locally adaptive sparse representation

Abstract: This paper presents a block-based face-recognition algorithm based on a sparse linear-regression subspace model via locally adaptive dictionary constructed from past observable data (training samples). The local features of the algorithm provide an immediate benefit — the increase in robustness level to various registration errors. Our proposed approach is inspired by the way human beings often compare faces when presented with a tough decision: we analyze a series of local discriminative features (do the eyes match? how about the nose? what about the chin?…) and then make the final classification decision based on the fusion of local recognition results. In other words, our algorithm attempts to represent a block in an incoming test image as a linear combination of only a few atoms in a dictionary consisting of neighboring blocks in the same region across all training samples. The results of a series of these sparse local representations are used directly for recognition via either maximum likelihood fusion or a simple democratic majority voting scheme. Simulation results on standard face databases demonstrate the effectiveness of the proposed algorithm in the presence of multiple mis-registration errors such as translation, rotation, and scaling.

Display device, image signal correction system, and image signal correction method

Abstract: A display device includes a display unit and a controller, the controller generating and transmitting a scan signal and an image data signal to a scan driver and a data driver, respectively. The controller includes a memory unit storing a look-up table of basic correction amounts for a test image data signal according a comparison result of comparing a measured value of an image of the display unit displaying the test image data signal with a target value of the test image data signal, and a data controller storing data for a modulation coefficient for applying the look-up table to the supplied image data signal, calculating a full correction amount corresponding to the supplied image data signal using the modulation coefficient and the basic correction amount of the look-up table, and outputting a corrected image data signal by correcting the supplied image data signal by the full correction amount.

Rake transform and edge statistics for image forgery detection

Abstract: In this paper, an effective framework for passive-blind color image forgery detection is proposed. It is a combination of image features extracted from image luminance by applying a rake-transform and from image chroma by using edge statistics. The efficacy of the image features has been tested over two color image datasets established for tampering detection. The proposed framework outweighs the state of the arts over the small-scale dataset, and performs well on the newly established large-scaled dataset (likely the first reported test result on this dataset). The initial tests on some real image forgery cases available in the website and those reported in the literature on image composition with advanced image and vision technologies indicate the promise possessed as well as the challenge faced by the community of image forgery detection.

Living iris detection method

Abstract: The invention relates to a living iris detection method, which comprises the following steps of: S1, pre-treating a living iris image and an artificial iris image in a training image library; performing multi-scale characteristic extraction of local binary mode in an obtained interested area, and selecting the preferable one from the obtained candidate characteristics by using an adaptive reinforcement learning algorithm, and establishing a classifier for living iris detection; and S2, pre-treating the randomly input test iris image, and calculating the preferable local binary-mode characteristic in the obtained interested area; inputting the calculated characteristic value into the classifier for living iris detection obtained in step S1, and judging whether the test image is from the living iris according to the output result of the classifier. The invention can perform effective anti-forgery detection and alarm for the iris image and reduce error rate in iris recognition. The invention is widely applicable to various application systems for identification and safety precaution by using iris recognition.

Unresolved Target Detection Blind Test Project Overview

Abstract: The development and testing of algorithms for unresolved target detection in hyperspectral imagery requires the availability of empirical imagery with adequate ground truth. However, target deployment and collection of imagery can be expensive, and the resulting data often have limited distribution due to concerns of a security or propriety nature. When data are made available, it is usually with full ground truth leading to the possibility of analysts "tuning" their algorithm and reporting optimistic results. There exists an ongoing need for widely available, well ground truthed, and independent data for the community. This paper provides an overview and introduction to such a standard blind test data set. Airborne hyperspectral imagery is provided together with spectral reflectance signatures of several fabric panels and vehicles in the scene. A self-test image is accompanied by pixel locations in the image for the targets of interest for algorithm development. A blind test image has additional targets in different locations and is provided without pixel truth for independent performance assessment. Since publicizing the data set in 2008, over 150 researchers from around the world have downloaded the data for testing. Further details on the data, the project, and the results of participants are presented.