Proceedings Article•
Image Processing
01 Jan 1994-
TL;DR: The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images.
Abstract: MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.
Citations
More filters
01 Jan 2007
TL;DR: A computer-aided diagnosis (CAD) system to detect small-size pulmonary nodules from helical CT scans to help lower the number of omissions and to decrease the time needed to examine the scan by a radiologist.
Abstract: A computer-aided diagnosis (CAD) system to detect small-size (from 2mm to around 10mm) pulmonary nodules in helical CT scans is developed. This system uses two different schemes to locate juxtapleural nodules and non-pleural nodules. For juxtapleural nodules, morphological closing and thresholding is used to find nodule candidates. To locate nonpleural nodules, 3D blob detector uses multiscale filtration. System was tested on 5 cases with total sensitivity of 95%, with about 10 false positives/slice.
12 citations
Cites background or methods from "Image Processing"
...Binary thresholding [9] is the transformation of grayscale image f to binary(BW) image g as follows...
[...]
...Classifier [9] is a device with n inputs and one output....
[...]
...3D filtration of image f by a 3D filter h is a discrete convolution [9] api, j, kq h f ̧...
[...]
...In binary morphology [9] we have a point set X and a structure element A, represented by coordinates of white image pixels (in BW image we have only black or white pixels)....
[...]
TL;DR: A novel system is presented to dynamically measure the dynamic contact area of road and off-road vehicles performance using a metal box with a glass surface and a digital camera, which captures a video when the tire passes over it.
12 citations
TL;DR: The Paris System for Reporting Urinary Cytology was established using only liquid‐based preparation techniques, and to the authors' knowledge it is unknown whether TPS can be applied using other preparation methods.
Abstract: Background The Paris System for Reporting Urinary Cytology (TPS) defines clear morphologic criteria to classify urinary specimens into 7 diagnostic categories. According to TPS, a nuclear-to-cytoplasmic ratio (N:C ratio) >0.7 and hyperchromasia must be observed to render a diagnosis of high-grade urothelial carcinoma (HGUC). TPS was established using only liquid-based preparation techniques, and to the authors' knowledge it is unknown whether TPS can be applied using other preparation methods. Methods In the current prospective study, voided urine samples from patients with HGUC and negative for HGUC (NHGUC) were prepared using both ThinPrep and cytospin methods. ImageJ image processing software was used to measure the N:C ratio and hyperchromasia. For each patient, the N:C ratio and degree of hyperchromasia of urothelial cells present in both cytopreparations were compared. Results A total of 10 HGUC cases and 9 NHGUC cases, represented by a total of 688 cells (mean, 36.7 cells in HGUC cases; and mean, 35.8 cells in NHGUC cases), were evaluated in the current study. An overall comparison of HGUC cells with NHGUC cells demonstrated that HGUC cells had a higher average N:C ratio (0.5465 vs 0.2846) and greater hyperchromasia as measured by the average nuclear pixel gray value (100.8 vs 120.7). The N:C ratio was statistically different in 4 NHGUC cases, demonstrating higher N:C ratios in the ThinPrep preparations. Hyperchromasia was found to be statistically different in 6 cases, 5 of which demonstrated increased hyperchromasia in the ThinPrep specimens. Conclusions The morphologic features of HGUC cells appear to be similar in samples prepared using the ThinPrep and cytospin methods, and therefore TPS criteria may be applied successfully in laboratories that use these methods.
12 citations
TL;DR: Using genetically encoded FRET reporters targeted to distinct subcellular compartments of neonatal cardiac myocytes from the DMD mouse model mdx, whether lack of dystrophin disrupts local cyclic nucleotide signalling is investigated, thus potentially providing an early trigger for the development of cardiomyopathy.
Abstract: Duchenne muscular dystrophy (DMD) is the most frequent and severe form of muscular dystrophy. The disease presents with progressive body-wide muscle deterioration and, with recent advances in respiratory care, cardiac involvement is an important cause of morbidity and mortality. DMD is caused by mutations in the dystrophin gene resulting in the absence of dystrophin and, consequently, disturbance of other proteins that form the dystrophin-associated protein complex (DAPC), including neuronal nitric oxide synthase (nNOS). The molecular mechanisms that link the absence of dystrophin with the alteration of cardiac function remain poorly understood but disruption of NO-cGMP signalling, mishandling of calcium and mitochondrial disturbances have been hypothesized to play a role. cGMP and cAMP are second messengers that are key in the regulation of cardiac myocyte function and disruption of cyclic nucleotide signalling leads to cardiomyopathy. cGMP and cAMP signals are compartmentalised and local regulation relies on the activity of phosphodiesterases (PDEs). Here, using genetically encoded FRET reporters targeted to distinct subcellular compartments of neonatal cardiac myocytes from the DMD mouse model mdx, we investigate whether lack of dystrophin disrupts local cyclic nucleotide signalling, thus potentially providing an early trigger for the development of cardiomyopathy. Our data show a significant alteration of both basal and stimulated cyclic nucleotide levels in all compartments investigated, as well as a complex reorganization of local PDE activities.
12 citations
27 May 2008
TL;DR: Experimental results show that the proposed temporal synchronous compressed MPEG-4 video watermarking scheme has satisfactory ability in resisting the temporal synchronization attacks of frame deleting and frame inserting, therefore achieving well robustness.
Abstract: As an effective technology for copyright protection, digital watermarking has been applied in videos. Temporal synchronization is an important aspect for video watermarking. If synchronization is lost, the detector may fail in extracting the correct watermark. This paper proposes a temporal synchronous compressed MPEG-4 video watermarking scheme. This scheme utilizes DCT direct current coefficients to divide video into several scenes. Watermarks are embedded according to features of scenes. Bit rate control is introduced to ensure that watermark embedding does not increase the size of video. Drift compensation is employed to counteract the visual distortion in P-frames and B-frames caused by watermark embedding. Visual masking is exploited to enhance the invisibility of watermark. Experimental results show that the scheme has satisfactory ability in resisting the temporal synchronization attacks of frame deleting and frame inserting, therefore achieving well robustness.
12 citations
References
More filters
01 Nov 1973
TL;DR: These results indicate that the easily computable textural features based on gray-tone spatial dependancies probably have a general applicability for a wide variety of image-classification applications.
Abstract: Texture is one of the important characteristics used in identifying objects or regions of interest in an image, whether the image be a photomicrograph, an aerial photograph, or a satellite image. This paper describes some easily computable textural features based on gray-tone spatial dependancies, and illustrates their application in category-identification tasks of three different kinds of image data: photomicrographs of five kinds of sandstones, 1:20 000 panchromatic aerial photographs of eight land-use categories, and Earth Resources Technology Satellite (ERTS) multispecial imagery containing seven land-use categories. We use two kinds of decision rules: one for which the decision regions are convex polyhedra (a piecewise linear decision rule), and one for which the decision regions are rectangular parallelpipeds (a min-max decision rule). In each experiment the data set was divided into two parts, a training set and a test set. Test set identification accuracy is 89 percent for the photomicrographs, 82 percent for the aerial photographic imagery, and 83 percent for the satellite imagery. These results indicate that the easily computable textural features probably have a general applicability for a wide variety of image-classification applications.
20,442 citations
Book•
03 Oct 1988TL;DR: This chapter discusses two Dimensional Systems and Mathematical Preliminaries and their applications in Image Analysis and Computer Vision, as well as image reconstruction from Projections and image enhancement.
Abstract: Introduction. 1. Two Dimensional Systems and Mathematical Preliminaries. 2. Image Perception. 3. Image Sampling and Quantization. 4. Image Transforms. 5. Image Representation by Stochastic Models. 6. Image Enhancement. 7. Image Filtering and Restoration. 8. Image Analysis and Computer Vision. 9. Image Reconstruction From Projections. 10. Image Data Compression.
8,504 citations
TL;DR: The image coding results, calculated from actual file sizes and images reconstructed by the decoding algorithm, are either comparable to or surpass previous results obtained through much more sophisticated and computationally complex methods.
Abstract: Embedded zerotree wavelet (EZW) coding, introduced by Shapiro (see IEEE Trans. Signal Processing, vol.41, no.12, p.3445, 1993), is a very effective and computationally simple technique for image compression. We offer an alternative explanation of the principles of its operation, so that the reasons for its excellent performance can be better understood. These principles are partial ordering by magnitude with a set partitioning sorting algorithm, ordered bit plane transmission, and exploitation of self-similarity across different scales of an image wavelet transform. Moreover, we present a new and different implementation based on set partitioning in hierarchical trees (SPIHT), which provides even better performance than our previously reported extension of EZW that surpassed the performance of the original EZW. The image coding results, calculated from actual file sizes and images reconstructed by the decoding algorithm, are either comparable to or surpass previous results obtained through much more sophisticated and computationally complex methods. In addition, the new coding and decoding procedures are extremely fast, and they can be made even faster, with only small loss in performance, by omitting entropy coding of the bit stream by the arithmetic code.
5,890 citations
TL;DR: Eight constructs decellularized hearts by coronary perfusion with detergents, preserved the underlying extracellular matrix, and produced an acellular, perfusable vascular architecture, competent a cellular valves and intact chamber geometry that could generate pump function in a modified working heart preparation.
Abstract: About 3,000 individuals in the United States are awaiting a donor heart; worldwide, 22 million individuals are living with heart failure. A bioartificial heart is a theoretical alternative to transplantation or mechanical left ventricular support. Generating a bioartificial heart requires engineering of cardiac architecture, appropriate cellular constituents and pump function. We decellularized hearts by coronary perfusion with detergents, preserved the underlying extracellular matrix, and produced an acellular, perfusable vascular architecture, competent acellular valves and intact chamber geometry. To mimic cardiac cell composition, we reseeded these constructs with cardiac or endothelial cells. To establish function, we maintained eight constructs for up to 28 d by coronary perfusion in a bioreactor that simulated cardiac physiology. By day 4, we observed macroscopic contractions. By day 8, under physiological load and electrical stimulation, constructs could generate pump function (equivalent to about 2% of adult or 25% of 16-week fetal heart function) in a modified working heart preparation.
2,454 citations
01 Sep 1997
TL;DR: This paper examines automated iris recognition as a biometrically based technology for personal identification and verification from the observation that the human iris provides a particularly interesting structure on which to base a technology for noninvasive biometric assessment.
Abstract: This paper examines automated iris recognition as a biometrically based technology for personal identification and verification. The motivation for this endeavor stems from the observation that the human iris provides a particularly interesting structure on which to base a technology for noninvasive biometric assessment. In particular the biomedical literature suggests that irises are as distinct as fingerprints or patterns of retinal blood vessels. Further, since the iris is an overt body, its appearance is amenable to remote examination with the aid of a machine vision system. The body of this paper details issues in the design and operation of such systems. For the sake of illustration, extant systems are described in some amount of detail.
2,046 citations