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 Nov 2017
TL;DR: In this article, morphometric analysis of more than 3,300 leaves from 40 different Passiflora species using two different methods: homologous landmarks and Elliptical Fourier Descriptors (EFDs).
Abstract: Not only does leaf shape vary between Passiflora species, but between sequential nodes of the vine. The profound changes in leaf shape within Passiflora vines reflect the temporal development of the shoot apical meristem from which leaves are derived and patterned, a phenomenon known as heteroblasty. We perform a morphometric analysis of more than 3,300 leaves from 40 different Passiflora species using two different methods: homologous landmarks and Elliptical Fourier Descriptors (EFDs). Changes in leaf shape across the vine are first quantified in allometric terms; that is, changes in the relative area of leaf subregions expressed in terms of overall leaf area. Shape is constrained to strict linear relationships as a function of size that vary between species. Statistical analysis of leaf shape, using landmarks and EFDs, reveals that species effects (regardless of node) are the strongest, followed by interaction effects between species and heteroblasty (i.e., species-specific patterns in leaf shape across nodes) and that heteroblasty effects across nodes (regardless of species) are negligible. The ability of different nodes to predictively discriminate species and the variability of landmark and EFD traits at each node is then analyzed. Heteroblastic trajectories, the changes in leaf shape between the first and last measured leaves in a vine, are then compared between species in a multivariate space. Leaf shape diversity among Passiflora species is expressed in a heteroblastic-dependent manner, unique to each species. Leaf shape is constrained by linear, allometric relationships related to leaf size that vary between species. There is a strong species × heteroblasty interaction effect for leaf shape, suggesting that different leaf shapes between species arise through changes in shape across nodes specific to each species. The first leaves in the series are not only more like each other, but are also less variable across species. From this similar, shared leaf shape, subsequent leaves in the heteroblastic series follow divergent morphological trajectories. The disparate leaf shapes characteristic of Passiflora species arise from a shared, juvenile morphology.
21 citations
Cites methods from "Image Processing"
...To isolate outlines for Elliptical Fourier Descriptor (EFD) analysis, the “Make Binary” function in ImageJ (Abr amoff et al., 2004) was found to be sufficient to segment leaves....
[...]
Proceedings Article•
25 Jul 2015TL;DR: A new optimization model to learn the robust kernel dictionary while isolating outliers in the training samples is proposed, essentially based on the decomposition of the reconstruction error into small dense noises and large sparse outliers.
Abstract: Kernel sparse coding is an effective strategy to capture the non-linear structure of data samples. However, how to learn a robust kernel dictionary remains an open problem. In this paper, we propose a new optimization model to learn the robust kernel dictionary while isolating outliers in the training samples. This model is essentially based on the decomposition of the reconstruction error into small dense noises and large sparse outliers. The outlier error term is formulated as the product of the sample matrix in the feature space and a diagonal coefficient matrix. This facilitates the kernelized dictionary learning. To solve the non-convex optimization problem, we develop a whole sequence convergent algorithm which guarantees the obtained solution sequence is a Cauchy sequence. The experimental results show that the proposed robust kernel dictionary learning method provides significant performance improvement.
21 citations
Cites background or methods or result from "Image Processing"
...The default parameter suggested in [Nguyen et al., 2013] are used for this implementation....
[...]
...Recently, some scholars proposed more principled kernel dictionary learning method[Anaraki and Hughes, 2013][Nguyen et al., 2013][Liu et al....
[...]
...This setting was suggested in [Nguyen et al., 2013] for K-KSVD method....
[...]
...Similar to the setting in [Nguyen et al., 2013], we learn the dictionary from 500 data sample set {yi}(500) i=1 that is generated from a 2-dimensional parabola {yi = [yi,1, yi,2] ∈ R(2)|yi,2 = y(2) i,1}....
[...]
...Similar to the setting in [Nguyen et al., 2013], we learn the dictionary from 500 data sample set {yi}500i=1 that is generated from a 2-dimensional parabola {yi = [yi,1, yi,2]T ∈ R2|yi,2 = y2i,1}....
[...]
TL;DR: The combined data from the Chl a fluorescence analysis, pigment quantification and biomass accumulation showed that transgenic M. truncatula plants are able to recover from water deprivation better than wild type plants.
Abstract: In this article, we present the response of Medicago truncatula Gaert. cv. Jemalong plants expressing constitutively the Dsp22 gene from Craterostigma plantagineum to water stress and rehydration. The Dsp22 gene encodes an ELIP-like protein thought to protect the chloroplast against photooxidative damage during the dehydration and rehydration. The Dsp22 transgenic homozygous M. truncatula plants showed higher amount of chlorophyll (Chl), lower Chl a/Chl b ratio and higher actual efficiency of energy conversion in photosystem 2 (ΦPSII) after rehydration, when compared to the wild type. The combined data from the Chl a fluorescence analysis, pigment quantification and biomass accumulation showed that transgenic M. truncatula plants are able to recover from water deprivation better than wild type plants.
21 citations
TL;DR: The results indicate that ontogenetic shifts in group foraging strategies can have large ecosystem-wide consequences when the species is an important ecosystem modifier.
Abstract: The relative benefits of group foraging change as animals grow Metabolic requirements, competitive abilities and predation risk are often allometric and influenced by group size How individuals optimise costs and benefits as they grow can strongly influence consumption patterns The shoaling fish Sarpa salpa is the principal herbivore of temperate Posidonia oceanica seagrass meadows We used in-situ observations to describe how ontogeny influenced S salpa individual feeding behaviour, shoaling behaviour and group foraging strategies, and its potential consequences to seagrass meadows Shoaling was strongly influenced by body length: shoals were highly length-assorted and there was a clear positive relationship between body length and shoal size Foraging strategies changed dramatically with shoal size Small shoals foraged simultaneously and scattered over large areas In contrast, larger shoals (made of larger individuals) employed a potentially cooperative strategy where individuals fed rotationally and focused in smaller areas for longer times (spot feeding) Thus, as individuals grew, they increased their potential impact as well, not merely because they consumed more, but because they formed larger shoals capable of considerably concentrating their grazing within the landscape Our results indicate that ontogenetic shifts in group foraging strategies can have large ecosystem-wide consequences when the species is an important ecosystem modifier
21 citations
TL;DR: In this paper, a meta-analysis was performed to assess the effect of micro-and nanoplastics particles (MNP) exposure on algal growth and found that exposure to MNP was not significantly associated with growth inhibition in any of the models tested.
Abstract: Background: Ecological impacts of micro- and nanoplastics particles (MNP) are among the most discussed environmental concerns. In algae, MNP are commonly hypothesized to reduce growth, which is a standard ecotoxicological endpoint. However, the reported test outcomes vary, with both growth inhibition and stimulation being observed. Due to this conflict of information, a data synthesis for MNP potential to cause growth inhibition in toxicity testing is needed. Methods: We performed a meta-analysis study to assess the effect of MNP exposure on algal growth. Twenty studies published between 2010 and 2020 and representing 16 algal species and five polymer materials administered as particles in size range 0.04 to 3000 µm were included in this meta-analysis. A random-effect model was used to estimate the effect size in three datasets: (1) Low concentration range (< 100 mg/L), (2) High concentration range (≥ 100 mg/L), and (3) Full range model (0.004 to 1100 mg/L), which encompassed all studies using the combination of experimental settings (test species, MNP concentration, polymer material, and particle size) yielding the highest effect size within a study. Results: The exposure to MNP was not significantly associated with growth inhibition in any of the models tested. However, a high heterogeneity between the studies was found in all three models. Neither MNP concentration nor polymer material contributed significantly to the heterogeneity, whereas polymer density had a significant moderating effect, with a higher risk of growth inhibition at lower densities. We also identified a publication bias, with small studies that reported significant inhibition being overrepresented in our dataset. Conclusions: The meta-analysis found limited evidence for MNP effect on microalgal growth in the standard algal growth inhibition test. The heterogeneity and varying methodological quality of studies limited the interpretation and the confidence in the findings. For hazard assessment, standardization and controlled exposure are needed as well as more sensitive endpoints that can inform us about the effect mechanisms. Finally, using particle-free controls in such tests cannot account for the presence of inert particulates in the test system, and, hence, does not allow to attribute observed effects to the test polymers.
21 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