Set Of Standard Images Research Articles

Natural Feature Detection on Mobile Phones with 3D FAST

In this paper, we present a novel feature detection approach designed for mobile devices, showing optimized solutions for both detection and description. It is based on FAST (Features from Accelerated Segment Test) and named 3D FAST. Being robust, scale-invariant and easy to compute, it is a candidate for augmented reality (AR) applications running on low performance platforms. Using simple calculations and machine learning, FAST is a feature detection algorithm known to be efficient but not very robust in addition to its lack of scale information. Our approach relies on gradient images calculated for different scale levels on which a modified9 FAST algorithm operates to obtain the values of the corner response function. We combine the detection with an adapted version of SURF (Speed Up Robust Features) descriptors, providing a system with all means to implement feature matching and object detection. Experimental evaluation on a Symbian OS device using a standard image set and comparison with SURF using Hessian matrix-based detector is included in this paper, showing improvements in speed (compared to SURF) and robustness (compared to FAST)

Refined translation and scale Legendre moment invariants

Orthogonal Legendre moments are used in several pattern recognition and image processing applications. Translation and scale Legendre moment invariants were expressed as a combination of the approximate original Legendre moments. The shifted and scaled Legendre polynomials were expressed in terms of the original Legendre polynomials according to complicated and time-consuming algebraic relations. In this paper, refined translation-scale Legendre moment invariants are obtained through the exact computation of original Legendre moments which completely remove approximation. Fast straightforward computation of central Legendre moments significantly reduces the computational time. According to the tremendous reduction of the computational complexity, the refined set of Legendre invariants is suitable for large size images. The performance of descriptors is evaluated by using a set of standard images.

Medical Image on the Go!

The idea for softcopy viewing of medical image outside the radiology reading room spread among the scientists in various fields for several years. An image could be read on workstation of all types, from desktop across movable to handheld. Benefits are numerous and continue to grow as physicians use them discovering new usage cases. Proposed solutions vary with PACS architecture invasion level, communication and storage image formats, and utilization. We employ JPEG2000 standard because of its high (lossy/lossless) compression ratio with minimal spatial distortion, retrieval-oriented storage, and streaming. It is embedded in PACS as the DICOM Private Data Element containing JPIP parameter string, so-called DICOM2000. The DICOM2000 message is transparent for standard DICOM devices at the slightest level of invasion. Thanks to sophisticated JPEG2000 streaming, medical image becomes suitable for any resolution and quality display and (wireless) networks. The solution is validated on the ACR/NEMA standard test set of PACS images.

Qualitative assessment of ultrasound biomicroscopic images using standard photographs: the liwan eye study.

Objective. To classify anatomic features related to anterior chamber angles by a qualitative assessment system based on ultrasound biomicroscopy (UBM) images. Methods. Cases of primary angle-closure suspect (PACS), defined by pigmented trabecular meshwork that is not visible in two or more quadrants on static gonioscopy (cases) and systematically selected subjects (1 of every 10) who did not meet this criterion (controls) were enrolled during a population-based survey in Guangzhou, China. All subjects underwent UBM examination. A set of standard UBM images was used to qualitatively classify anatomic features related to the angle configuration, including iris thickness, iris convexity, iris angulation, ciliary body size, and ciliary process position. All analysis was conducted on right eye images. Results. Based on the qualitative grades, the difference in overall iris thickness between gonioscopically narrow eyes (n = 117) and control eyes (n = 57) was not statistically significant. The peripheral one third of the iris tended to be thicker in all quadrants of the PACS eyes, although the difference was statistically significant only in the superior quadrant (P = 0.008). No significant differences were found in the qualitative classifications of iris insertion, iris angulation, ciliary body size, and ciliary process position. The findings were similar when compared with the control group of eyes with wide angles in all quadrants. Conclusions. Basal iris thickness seems to be more relevant to narrow angle configuration than to overall iris thickness. Otherwise, the anterior rotation and size of the ciliary body, the iris insertion, and the overall iris thickness are comparable in narrow- and wide-angle eyes.

New Methods for Objective Evaluation of Fabric Pilling by Frequency Domain Image Processing

Fabric pilling is a serious problem for the apparel industry. Resistance to pilling is normally tested by simulated accelerated wear and manual assessment of degree of pilling based on a visual comparison of the sample to a set of test images. A number of automated systems based on image analysis have been developed. The authors propose new methods of image analysis based on the two-dimensional wavelet transform to objectively measure the pilling intensity in sample images. Initial work employed the detail coefficients of the two-dimensional discrete wavelet transform (2DDWT) as a measure of the pilling intensity of woven/knitted fabrics. This method is shown to be robust to image translation and brightness variation. Using the approximation coefficients of the 2DDWT, the method is extended to non-woven pilling image sets. Wavelet texture analysis (WTA) combined with principal components analysis are shown to produce a richer texture description of pilling for analysis and classification. Finally, employing the two-dimensional dual-tree complex wavelet transform as the basis for the WTA feature vector is shown to produce good automated classification on a range of standard pilling image sets.

Response to Comment on "100% Accuracy in Automatic Face Recognition"

Contrary to the suggestion of Deng et al ., image registration reduced face-recognition accuracy when divorced from the averaging procedure. Average-to-photo mapping generalizes beyond specific photographs, and averaging either gallery images or probe images can improve the match. The alternative protocol suggested by the authors is unsuitable because it evaluates face-matching algorithms, not face representations, and relies on standard image sets.

Phase correlation processing for DPIV measurements

A novel digital particle image velocimetry (DPIV) correlation method is presented, the Gaussian transformed phase correlation (GTPC) estimator, using nonlinear filtering techniques coupled with the phase-transform (PHAT) generalized cross-correlation filter. The use of spatial windowing is shown to be ideally suited for the use of phase correlation estimators, due to their invariance to the loss of correlation effects. Error analysis demonstrates the increased valid vector detection and measurement accuracy of the windowed GTPC over the traditional Fourier based estimator in a series of uniform displacement Monte Carlo simulations. Analysis of the GTPC performance in the PIV standard image sets shows error reductions on the order of 15–45% over the range of simulations. Experimental DPIV images from a turbulent rib roughened channel flow are used to validate the use of the GTPC, which shows a strong reduction in peak locking effects, background noise errors, and erroneous vectors. Together, these results demonstrate the coupled benefits provided by the use of advanced filtering techniques applied to the phase correlation estimator. With the correct implementation of these filters, the GTPC is able to provide substantial improvements to the robustness of DPIV estimation.

Objective Pilling Evaluation of Wool Fabrics

An objective pilling evaluation method based on the multi-scale two-dimensional dual-tree complex wavelet transform and linear discriminant function of Bayes' Rule was developed. The surface fuzz and pills are identified from the high-frequency noise, fabric textures, fabric surface unevenness, and illuminative variation of a pilled fabric image by the two-dimensional dual-tree complex wavelet decomposition and reconstruction. The energies of the reconstructed subimages in six spatial orientations (±15º, ±45º, ±75º) are calculated as the elements of the pilling feature vector, whose dimension is reduced by principal component analysis. A linear discriminant function of Bayes' Rule was used as a classifier to establish classification rules among the five pilling grades. A new pilled sample with the same physical construction can then be automatically assigned to one of the five pilling grades by the classification rules. A general evaluation of the proposed method was conducted using the SM50 woven, non-woven, and SM54 knitted standard pilling test image sets. The results suggest that the new method can successfully establish classification rules among the five pilling grade groups for each of the three standard pilling test image sets and should be applicable to practical objective pilling evaluation.

A comparative analysis of pre-processing techniques in colour retinal images

Diabetic retinopathy (DR) is a chronic disease of the ocular retina, which most of the times is only discovered when the disease is on an advanced stage and most of the damage is irreversible. For that reason, early diagnosis is paramount for avoiding the most severe consequences of the DR, of which complete blindness is not uncommon. Unsupervised or supervised image processing of retinal images emerges as a feasible tool for this diagnosis. The preprocessing stages are the key for any further assessment, since these images exhibit several defects, including non uniform illumination, sampling noise, uneven contrast due to pigmentation loss during sampling, and many others. Any feasible diagnosis system should work with images where these defects were compensated. In this work we analyze and test several correction techniques. Non uniform illumination is compensated using morphology and homomorphic filtering; uneven contrast is compensated using morphology and local enhancement. We tested our processing stages using Fuzzy C-Means, and local Hurst (self correlation) coefficient for unsupervised segmentation of the abnormal blood vessels. The results over a standard set of DR images are more than promising.

Objective Grading of Fabric Pilling with Wavelet Texture Analysis

A new objective fabric pilling grading method based on wavelet texture analysis was developed. The new method created a complex texture feature vector based on the wavelet detail coefficients from all decomposition levels and horizontal, vertical and diagonal orientations, permitting a much richer and more complete representation of pilling texture in the image to be used as a basis for classification. Standard multi-factor classification techniques of principal components analysis and discriminant analysis were then used to classify the pilling samples into five pilling degrees. The preliminary investigation of the method was performed using standard pilling image sets of knitted, woven and non-woven fabrics. The results showed that this method could successfully evaluate the pilling intensity of knitted, woven and non-woven fabrics by selecting the suitable wavelet and associated analysis scale.

Bayesian stereo matching

A Bayesian framework is proposed for stereo vision where solutions to both the model parameters and the disparity map are posed in terms of predictions of latent variables, given the observed stereo images. A mixed sampling and deterministic strategy is adopted to balance between effectiveness and efficiency: the parameters are estimated via Markov Chain Monte Carlo sampling techniques and the Maximum A Posteriori (MAP) disparity map is inferred by a deterministic approximation algorithm. Additionally, a new method is provided to evaluate the partition function of the associated Markov random field model. Encouraging results are obtained on a standard set of stereo images as well as on synthetic forest images.

Stereo matching via selective multiple windows

Window-based correlation algorithms are widely used for stereo matching due to their computational efficiency as compared to global algorithms. In this paper, a multiple window correlation algorithm for stereo matching is presented which addresses the problems associated with a fixed window size. The developed algorithm differs from the previous multiple window algorithms by introducing a reliability test to select the most reliable window among multiple windows of increasing sizes. This ensures that at least one window is large enough to cover a region of adequate intensity variations while at the same time small enough to cover a constant depth region. A recursive computation procedure is also used to allow a computationally efficient implementation of the algorithm. The outcome obtained from a standard set of images with known disparity maps shows that the generated disparity maps are more accurate as compared to two popular stereo matching local algorithms.

Free fermion antibunching in a degenerate atomic Fermi gas released from an optical lattice

Noise in a quantum system is fundamentally governed by the statistics and the many-body state of the underlying particles. The correlated noise observed for bosonic particles (for example, photons or bosonic neutral atoms) can be explained within a classical field description with fluctuating phases; however, the anticorrelations ('antibunching') observed in the detection of fermionic particles have no classical analogue. Observations of such fermionic antibunching are scarce and have been confined to electrons and neutrons. Here we report the direct observation of antibunching of neutral fermionic atoms. By analysing the atomic shot noise in a set of standard absorption images of a gas of fermionic (40)K atoms released from an optical lattice, we find reduced correlations for distances related to the original spacing of the trapped atoms. The detection of such quantum statistical correlations has allowed us to characterize the ordering and temperature of the Fermi gas in the lattice. Moreover, our findings are an important step towards revealing fundamental fermionic many-body quantum phases in periodic potentials, which are at the focus of current research.

Evaluation of Real-Time Single-Shot Fast Spin-Echo MRI for Visualization of the Fetal Midline Corpus Callosum and Secondary Palate

The objective of our study was to assess the visibility of the fetal corpus callosum and soft palate on standard single-shot fast spin-echo (SSFSE) imaging versus real-time (RT) SSFSE imaging. Part 1 of the study was a prospective analysis using a questionnaire rating the ease of use and utility of RT imaging. Part 2 of the study was a retrospective analysis of 69 fetal MRI studies with RT sagittal midline imaging of the head, face, or both. Standard and RT SSFSE image sets were de-identified, randomized, and shown to three pediatric neuroradiologists who rated on a 5-point scale whether the images were midline and how well they could see and characterize as normal the corpus callosum and secondary palate. The imaging results were correlated with postnatal diagnosis. Statistical methods included the Wilcoxon's signed rank test, McNemar chi-square test, and analysis of variance. Prospectively, the RT SSFSE technique was ranked as excellent in all the categories assessed. Retrospective analysis showed that the midline view obtained with RT SSFSE imaging was helpful in diagnosing the normal and abnormal secondary palate, allowing improved diagnosis of 19 (30.6%) of 62 cases of normal palate and four (57.1%) of seven cases of abnormal palate, when compared with the standard SSFSE technique. RT SSFSE imaging improved the ability to diagnose a normal corpus callosum on the midline view in 13 (27.6%) of 47 fetuses of 20 or more weeks gestational age. The RT SSFSE technique can aid in obtaining images in planes that are critical to the evaluation of a moving fetus, particularly when a midline sagittal view of the corpus callosum or palate is required. The use of this technique may lead to improved diagnosis of CNS or orofacial abnormalities in fetuses.

A Gradient Based Predictive Coding for Lossless Image Compression

Natural, continuous tone images have a very important property of high correlation of adjacent pixels. Images which we wish to compress are usually non-stationary and can be reasonably modeled as smooth and textured areas separated by edges. This property has been successfully exploited in LOCO-I and CALIC by applying gradient based predictive coding as a major de-correlation tool. However, they only examine the horizontal and vertical gradients, and assume the local edge can only occur in these two directions. Their over-simplified assumptions hurt the robustness of the prediction in higher complex areas. In this paper, we propose an accurate gradient selective prediction (AGSP) algorithm which is designed to perform robustly around any type of image texture. Our method measures local texture information by comparison and selection of normalized scalar representation of the gradients in four directions. An adaptive predictor is formed based on the local gradient information and immediate causal pixels. Local texture properties are also exploited in the context modeling of the prediction error. The results we obtained on a test set of several standard images are encouraging. On the average, our method achieves a compression ratio significantly better than CALIC without noticeably increasing of computational complexity.

Use of an amorphous silicon electronic portal imaging device for multileaf collimator quality control and calibration

Multileaf collimator (MLC) calibration and quality control is a time-consuming procedure typically involving the processing, scanning and analysis of films to measure leaf and collimator positions. Faster and more reliable calibration procedures are required for these tasks, especially with the introduction of intensity modulated radiotherapy which requires more frequent checking and finer positional leaf tolerances than previously. A routine quality control (QC) technique to measure MLC leaf bank gain and offset, as well as minor offsets (individual leaf position relative to a reference leaf), using an amorphous silicon electronic portal imaging device (EPID) has been developed. The technique also tests the calibration of the primary and back-up collimators. A detailed comparison between film and EPID measurements has been performed for six linear accelerators (linacs) equipped with MLC and amorphous silicon EPIDs. Measurements of field size from 4 to 24 cm with the EPID were systematically smaller than film measurements over all field sizes by 0.4 mm for leaves/back-up collimators and by 0.2 mm for conventional collimators. This effect is due to the gain calibration correction applied by the EPID, resulting in a ‘flattening’ of primary beam profiles. Linac dependent systematic differences of up to 0.5 mm in individual leaf/collimator positions were also found between EPID and film measurements due to the difference between the mechanical and radiation axes of rotation. When corrections for these systematic differences were applied, the residual random differences between EPID and film were 0.23 mm and 0.26 mm (1 standard deviation) for field size and individual leaf/back-up collimator position, respectively. Measured gains (over a distance of 220 mm) always agreed within 0.4 mm with a standard deviation of 0.17 mm. Minor offset measurements gave a mean agreement between EPID and film of 0.01 ± 0.10 mm (1 standard deviation) after correction for the tilt of the EPID and small rotational misalignments between leaf banks and the back-up collimators used as a reference straight edge. Reproducibility of EPID measurements was found to be very high, with a standard deviation of <0.05 mm for field size and <0.1 mm for individual leaf/collimator positions for a 10 × 10 cm2 field. A standard set of QC images (three field sizes defined both by leaves only and collimators only) can be acquired in less than 20 min and analysed in 5 min.

Quantitative analysis of retinopathy in type 2 diabetes: identification of prognostic parameters for developing visual loss secondary to diabetic maculopathy

To describe whether quantitative assessment of early changes in the morphology of retinopathy lesions can predict development of vision-threatening diabetic maculopathy. We used a nested case-control study, and we studied 11 type 2 diabetes patients who had developed visual loss secondary to diabetic maculopathy. For each diabetes patient, we also studied three matched control patients who had been followed for a comparable period of time without developing visual loss. Fundus photographs describing the early development of retinopathy were digitized and subjected to a full manual quantitative grading on a computer monitor. Differences in the early development of retinal morphology were compared between the two groups. The outcome parameters were changes in the number and area of haemorrhages and exudates in different regions of the fundus, and the weighted distance of these lesions from the fovea and the optic disc. In patients who developed visual loss secondary to diabetic maculopathy there was significant early progression in the total area and number of haemorrhages and exudates. The haemorrhages had progressed in all retinal areas except the area around the optic disc and the temporal vascular arcades. The exudates had progressed temporally from the fovea and in the retinal periphery. The results suggest that a quantitative description of the regional development of early diabetic retinopathy may help in identifying patients who will later develop vision-threatening maculopathy.

Inter-rater agreement on chromosome 5 breakage in FISH-based mutagen sensitivity assays (MSAs)

In chromosome breakage assays, validated, universal criteria for selection of cells and classification of chromosome aberrations may enhance their utility for cancer susceptibility screening. To standardize a fluorescence in situ hybridization (FISH) modification of the mutagen sensitivity assay (MSA), scoring criteria were evaluated by web-based validation. Two hundred digital FISH images were assigned random identification numbers. With this set of images, criteria for inclusion of cells and measurement of the frequency of abnormal cells were evaluated by eight observers, all of whom had five or more years of experience. Observers included doctoral and MS/BS level cytogeneticists, and were drawn from a randomized pool of 54 volunteers. Questions addressed were: (1) how uniformly were criteria applied to analysis of a standard digital FISH image set and (2) did concordance vary with educational level? These data suggest inter-rater agreement within a factor of 2 for average breakage frequency, but revealed greater variability in cell selection. These results aid in estimating the components of assay variance due to definitions, technical parameters and biological variables.

A fast area-based stereo matching algorithm

This paper proposes an area-based stereo algorithm suitable to real time applications. The core of the algorithm relies on the uniqueness constraint and on a matching process that rejects previous matches as soon as more reliable ones are found. The proposed approach is also compared with bidirectional matching (BM), since the latter is the basic method for detecting unreliable matches in most area-based stereo algorithms. We describe the algorithm's matching core, the additional constraints introduced to improve the reliability and the computational optimizations carried out to achieve a very fast implementation. We provide a large set of experimental results, obtained on a standard set of images with ground-truth as well as on stereo sequences, and computation time measurements. These data are used to evaluate the proposed algorithm and compare it with a well-known algorithm based on BM.

Automatic particle selection: results of a comparative study

Manual selection of single particles in images acquired using cryo-electron microscopy (cryoEM) will become a significant bottleneck when datasets of a hundred thousand or even a million particles are required for structure determination at near atomic resolution. Algorithm development of fully automated particle selection is thus an important research objective in the cryoEM field. A number of research groups are making promising new advances in this area. Evaluation of algorithms using a standard set of cryoEM images is an essential aspect of this algorithm development. With this goal in mind, a particle selection “bakeoff” was included in the program of the Multidisciplinary Workshop on Automatic Particle Selection for cryoEM. Twelve groups participated by submitting the results of testing their own algorithms on a common dataset. The dataset consisted of 82 defocus pairs of high-magnification micrographs, containing keyhole limpet hemocyanin particles, acquired using cryoEM. The results of the bakeoff are presented in this paper along with a summary of the discussion from the workshop. It was agreed that establishing benchmark particles and using bakeoffs to evaluate algorithms are useful in promoting algorithm development for fully automated particle selection, and that the infrastructure set up to support the bakeoff should be maintained and extended to include larger and more varied datasets, and more criteria for future evaluations.