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
TL;DR: Detailed investigation of Epichloë coenophiala strain AR601 in tall fescue revealed that at the early and mature developmental stages of the embryo sac, before host grass fertilization, there were large quantities of endophyte mycelium present, especially around the antipodal cells, indicating that this endophytes enters the embryosac before the fertilization stage.
Abstract: Asexual cool-season grass endophytes of the genus Epichloe (Ascomycota: Clavicipitaceae) are strictly vertically disseminated. The hosts of these mutualistic fungi express no symptoms during the fungal lifecycle that takes place entirely within the plant, while their hosts receive beneficial outcomes. These fungi are distributed in two major locations within the mature seeds of their hosts; namely, within the embryo (including the scutellum, coleoptile, plumule, radicle, and coleorhiza tissues) and between the aleurone and pericarp layers, with the latter hyphae playing no role in transmission of the fungus to the next plant generation. Conflicting evidence remains in the literature on the timing of embryo colonization. In a detailed investigation, utilizing confocal microscopy to observe the distribution of Epichloe coenophiala strain AR601 in tall fescue (Lolium arundinaceum), we tracked endophyte hyphal colonization in the ovary (pre-fertilization) through to the fully mature seed stage. Confocal microscopy images revealed that at the early and mature developmental stages of the embryo sac, before host grass fertilization, there were large quantities of endophyte mycelium present, especially around the antipodal cells, indicating that this endophyte enters the embryo sac before the fertilization stage. After host fertilization, fungal hyphae could be seen in the true embryo and early nonstarchy endosperm. Understanding the mechanisms of transmission to the seed is important for commercial seed producers and end users.
41 citations
Cites methods from "Image Processing"
...ImageJ (Abramoff et al. 2004), a public imaging program, was used to process images, including the addition of scale bars, whereas Adobe Photoshop CC 2015 (Adobe Systems Inc., San Jose, California) was used to crop images for publication....
[...]
TL;DR: A novel model based on neural networks denominated lateral interaction in accumulative computation (LIAC) is presented, based on a series of neuronal models in one layer, namely the local accum cumulative computation model, the double time scale model and the recurrent lateral interaction model.
41 citations
Cites methods from "Image Processing"
...For the purpose of categorisation, computer vision techniques can be divided into two main groups [46]....
[...]
TL;DR: From day 6 to day 12, the healing function followed the same time-course for the Pg and A treatments, but healing was achieved significantly earlier (4 days, p<0.03), suggesting that the effect of A on wound healing is achieved in the first six days, before the visual changes from epidermalization are analyzed.
Abstract: To define a healing function based on parameters measured on digitized images of wounds, and to use it to compare the rate of healing of two skin graft donor sites, one treated with petrolatum gauze (Pg) and the other with a topical preparation containing alginates (A). Digital photographs of donor sites (depth 0.6 mm) taken every two days between day 6 and day 12 were analyzed blind using the same algorithm, following changes in color and homogeneity. Analysis of variance was used to identify those parameters that changed during heating. The healing function was constructed using measurements made in six patients (group 1) randomly chosen from ten requiring skin grafts, and was applied and validated using data from the remaining four patients (group 2). The results given by this healing function were compared with those provided by principal component analysis. The most significant healing parameters were those measuring wound homogeneity, and our healing function reflects how these change with time. The time-dependent curves of the function calculated for groups 1 and 2 matched well enough to be considered as being derived from the same set of measurements. The results given by this healing function explained, by analogy, the meaning of the first principal component of principal component analysis. From day 6 to day 12, the healing function followed the same time-course for the Pg and A treatments, but healing was achieved significantly earlier (4 days, p<0.03) with A. This suggests that the effect of A on wound healing is achieved in the first six days, before the visual changes from epidermalization are analyzed.
41 citations
Cites background from "Image Processing"
...• Chromatic red, r = (100 R)=(R+G+B), is the percentage of red [16] in the overall color (the same principle applies to green and blue)....
[...]
TL;DR: It is concluded that basement membrane proteins and mesenchyme cells function as niche factors in salivary organoids to promote epithelial morphogenesis and expression of the early secretory proacinar markers Kit and AQP5.
Abstract: Epithelial progenitor cells are dependent upon a complex 3D niche to promote their proliferation and differentiation during development, which can be recapitulated in organoids. The specific requirements of the niche remain unclear for many cell types, including the proacinar cells that give rise to secretory acinar epithelial cells that produce saliva. Here, using ex vivo cultures of E16 primary mouse submandibular salivary gland epithelial cell clusters, we investigated the requirement for mesenchymal cells and other factors in producing salivary organoids in culture. Native E16 salivary mesenchyme, but not NIH3T3 cells or mesenchymal cell conditioned medium, supported robust protein expression of the progenitor marker Kit and the acinar/proacinar marker AQP5, with a requirement for FGF2 expression by the mesenchyme. Enriched salivary epithelial clusters that were grown in laminin-enriched basement membrane extract or laminin-111 together with exogenous FGF2, but not with EGF, underwent morphogenesis to form organoids that displayed robust expression of AQP5 in terminal buds. Knockdown of FGF2 in the mesenchyme or depletion of mesenchyme cells from the organoids significantly reduced AQP5 levels even in the presence of FGF2, suggesting a requirement for autocrine FGF2 signaling in the mesenchyme cells for AQP5 expression. We conclude that basement membrane proteins and mesenchyme cells function as niche factors in salivary organoids.
41 citations
Cites methods from "Image Processing"
...Positively stained areas (μm2) for EpCAM, AQP5 or vimentin markers were quantified by using calibrated and thresholded images using ImageJ software (Abràmofff et al., 2005), as we performed previously (Gervais et al., 2015)....
[...]
TL;DR: Experimental results demonstrate that the failure rate of the method proposed herein is improved by at least 86% compared to the model-fitting RANSAC algorithm with axis accuracy better than 1mm, at the expense of only a modest increase in computational effort.
41 citations
Cites methods from "Image Processing"
...In our method it is trained with decision stumps [37] and 10 weak classifiers....
[...]
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