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
11 Jul 2017
TL;DR: This paper investigates enhancement of monochromatic medical modality into colorized images by improving the contrast of anatomical structures facilitates precise segmentation and proposes a framework for pre-processing to remove noise and improve edge information.
Abstract: Medical images contain precious anatomical information for clinical procedures. Improved understanding of medical modality may contribute significantly in arena of medical image analysis. This paper investigates enhancement of monochromatic medical modality into colorized images. Improving the contrast of anatomical structures facilitates precise segmentation. The proposed framework starts with pre-processing to remove noise and improve edge information. Then colour information is embedded to each pixel of a subject image. A resulting image has a potential to portray better anatomical information than a conventional monochromatic image. To evaluate the performance of colorized medical modality, the structural similarity index and the peak signal to noise ratio are computed. Supremacy of proposed colorization is validated by segmentation experiments and compared with greyscale monochromatic images.
20 citations
Cites background from "Image Processing"
...Digital image and signal processing encompasses a vast arena of technologies for analysis of internal biological structure, function and treatment [8]....
[...]
TL;DR: Under short-time high fat diet challenge, lipid tends to initially accumulate extra-cellularly, which might reflect compensative responses of skeletal muscle to dietary lipid overload in order to regulate metabolic homeostasis.
Abstract: Objective To investigate whether differences in muscle fiber types affect early-stage fat accumulation, under high fat diet challenge in mice. Methods Twelve healthy male C57BL/6 mice experienced with short-term (6 weeks) diet treatment for the evaluation of early pattern changes in muscular fat. The mice were randomly divided into two groups: high fat diet (n = 8) and normal control diet (n = 4). Extra- and intra-myocellular lipid (EMCL and IMCL) in lumbar muscles (type I fiber predominant) and tibialis anterior (TA) muscle (type II fiber predominant) were determined using magnetic resonance spectroscopy (MRS). Correlation of EMCL, IMCL and their ratio between TA and lumbar muscles was evaluated. Results EMCL increased greatly in both muscle types after high fat diet. IMCL in TA and lumbar muscles increased to a much lower extent, with a slightly greater increase in TA muscles. EMCLs in the 2 muscles were positively correlated (r = 0.84, p = 0.01), but IMCLs showed a negative relationship (r = -0.84, p = 0.01). In lumbar muscles, high fat diet significantly decreased type I fiber while it increased type II fiber (all p≤0.001). In TA muscle, there was no significant fiber type shifting (p>0.05). Conclusions Under short-time high fat diet challenge, lipid tends to initially accumulate extra-cellularly. In addition, compared to type II dominant muscle, Type I dominant muscle was less susceptible to IMCL accumulation but more to fiber type shifting. These phenomena might reflect compensative responses of skeletal muscle to dietary lipid overload in order to regulate metabolic homeostasis.
20 citations
TL;DR: The aim of this study was to analyze NK cell responses to vascularized xenografts using an ex vivo perfusion system of pig limbs with human blood to protect against xenogeneic NK cytotoxicity.
Abstract: Background: In pig-to-human xenotransplantation, interactions between human natural killer (NK) cells and porcine endothelial cells (pEC) are characterized by recruitment and cytotoxicity. Protection from xenogeneic NK cytotoxicity can be achieved in vitro by the expression of the non-classical human leukocyte antigen-E (HLA-E) on pEC. Thus, the aim of this study was to analyze NK cell responses to vascularized xenografts using an ex vivo perfusion system of pig limbs with human blood. Methods: Six pig forelimbs per group, respectively, stemming from either wild-type (wt) or HLA-E/hCD46 double-transgenic (tg) animals, were perfused ex vivo with heparinized human blood for 12hours. Blood samples were collected at defined time intervals, cell numbers counted, and peripheral blood mononuclear cells analyzed for phenotype by flow cytometry. Muscle biopsies were analyzed for NK cell infiltration. In vitro NK cytotoxicity assays were performed using pEC derived from wt and tg animals as target cells. Results: Ex vivo, a strong reduction in circulating human CD45 leukocytes was observed after 60minutes of xenoperfusion in both wt and tg limb groups. NK cell numbers dropped significantly. Within the first 10minutes, the decrease in NK cells was more significant in the wt limb perfusions as compared to tg limbs. Immunohistology of biopsies taken after 12hours showed less NK cell tissue infiltration in the tg limbs. In vitro, NK cytotoxicity against hCD46 single tg pEC and wt pEC was similar, while lysis of double tg HLA-E/hCD46 pEC was significantly reduced. Finally, circulating cells of pig origin were observed during the ex vivo xenoperfusions. These cells expressed phenotypes mainly of monocytes, B and T lymphocytes, NK cells, as well as some activated endothelial cells. Conclusion: sEx vivo perfusion of pig forelimbs using whole human blood represents a powerful tool to study humoral and early cell-mediated rejection mechanisms of vascularized pig-to-human xenotransplantation, although there are several limitations of the model. Here, we show that (i) transgenic expression of HLA-E/hCD46 in pig limbs provides partial protection from human NK cell-mediated xeno responses and (ii) the emergence of a pig cell population during xenoperfusions with implications for the immunogenicity of xenografts.
20 citations
TL;DR: A collective sensing approach that integrates imperfect Volunteered Geographic Information obtained through Citizen Science tree mapping projects with very high resolution (VHR) optical remotely sensed data for low-cost, fine-scale, and accurate mapping of trees in urban orchards is presented.
Abstract: This paper presents a collective sensing approach that integrates imperfect Volunteered Geographic Information (VGI) obtained through Citizen Science (CS) tree mapping projects with very high resolution (VHR) optical remotely sensed data for low-cost, fine-scale, and accurate mapping of trees in urban orchards. To this end, an individual tree crown (ITC) detection technique utilizing template matching (TM) was developed for extracting urban orchard trees from VHR optical imagery. To provide the training samples for the TM algorithm, remotely sensed VGI about trees including the crowdsourced data about ITC locations and their crown diameters was adopted in this study. A data quality assessment of the proposed approach in the study area demonstrated that the detected trees had a very high degree of completeness (92.7%), a high thematic accuracy (false discovery rate (FDR) = 0.090, false negative rate (FNR) = 0.073, and F1 score (F1) = 0.918), and a fair positional accuracy (root mean square error(RMSE) = 1.02 m). Overall, the proposed approach based on the crowdsourced training samples generally demonstrated a promising ITC detection performance in our pilot project.
20 citations
TL;DR: In this article, the authors collected raindrops on dyed filter paper and calculated KEvol and erosivity values for each rainfall event, and established a relationship between rainfall intensity I and volume-specific kinetic energy KEvol for the Central Rift Valley area of the Ethiopian highlands.
Abstract: Knowledge of rainfall characteristics is important for estimating soil erosion in arid areas. We determined basic rainfall characteristics (raindrop size distribution, intensity and kinetic energy), evaluated the erosivity of rainfall events, and established a relationship between rainfall intensity I and volume-specific kinetic energy KEvol for the Central Rift Valley area of the Ethiopian highlands. We collected raindrops on dyed filter paper and calculated KEvol and erosivity values for each rainfall event. For most rainfall intensities the median volume drop diameter (D50) was higher than expected, or reported in most studies. Rainfall intensity in the region was not high, with 8% of rain events exceeding 30 mm h-1. We calculated soil erosion from storm energy and maximum 30-min intensity for soils of different erodibility under conditions of fallow (unprotected soil), steep slope (about 9%) and no cover and management practice on the surface, and determined that 3 MJ mm ha-1 h-1 is the thresh...
20 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