In this paper, we introduce a set of methods for processing and analyzing long time series of 3D images representing embryo evolution. The images are obtained by in vivo scanning using a confocal microscope where one of the channels represents the cell nuclei and the other one the cell membranes. Our image processing chain consists of three steps: image filtering, object counting (center detection) and segmentation. The corresponding methods are based on numerical solution of nonlinear PDEs, namely the geodesic mean curvature flow model, flux-based level set center detection and generalized subjective surface equation. All three models have a similar character and therefore can be solved using a common approach. We explain in details our semi-implicit time discretization and finite volume space discretization. This part is concluded by a short description of parallelization of the algorithms. In the part devoted to experiments, we provide the experimental order of convergence of the numerical scheme, the validation of the methods and numerous experiments with the data representing an early developmental stage of a zebrafish embryo.
Color quantization is an important process for image processing and various applications. Up to now, many color quantization methods have been proposed. The self-organizing maps (SOM) method is one of the most effective color quantization methods, which gives excellent color quantization results. However, it is slow, so it is not suitable for real-time applications. In this paper, we present a color importance{based SOM color quantization method. The proposed method dynamically adjusts the learning rate and the radius of the neighborhood using color importance. This makes the proposed method faster than the conventional SOM-based color quantization method. We compare the proposed method to 10 well-known color quantization methods to evaluate performance. The methods are compared by measuring mean absolute error (MAE), mean square error (MSE), and processing time. The experimental results show that the proposed method is effective and excellent for color quantization. Not only does the proposed method provide the best results compared to the other methods, but it uses only 67.18% of the processing time of the conventional SOM method.
In this study we have used scanning electron microscopy and atomic force microscopy (SEM and AFM) for evaluation and measurement of solar cell surfaces micro-geometry. SEM allowed to study large areas of the solar cells with considerable surface roughness (more than 10 μm) while AFM was carried out on relatively smooth areas, but it is truly 3D measurement. Currently, probe methods are more applicable for studying solid materials surfaces. AFM is a 3D surface morphology technique that provides quantitative information about surfaces, and characterizes roughness of the surface, and sizes of morphological features, such as grains. and Práce se zabývá měřením a vyhodnocením mikrogeometrického reliéfu povrchu monokrystalického a polykrystalického solárního článku. K měření povrchu byla využita skenovací elektronová mikroskopie SEM a mikroskopie atomárních sil AFM. Metoda SEM umožňuje snímat velké plochy solárních článků se značnou drsností povrchu a metoda AFM byla použita na poměrně hladké plochy, nicméně se jednalo o skutečné 3D měření. Metody využívající snímací sondy se používají pro studium povrchů pevných látek. AFM umožňuje 3D mapování povrchového reliéfu a poskytuje kvantitativní informace o povrchu, dokáže charakterizovat jeho drsnost a další morfologické charakteristiky, jako například zrnitost.
Chlorophyll fluorescence has developed into a well-established noninvasive technique to study photosynthesis and by extension, the physiology of plants and algae. The versatility of the fluorescence analysis has been improved significantly due to advancements in the technology of light sources, detectors, and data handling. This allowed the development of an instrumention that is effective, easy to handle, and affordable. Several of these techniques rely on point measurements. However, the response of plants to environmental stresses is heterogeneous, both spatially and temporally. Beside the nonimaging systems, low- and high-resolution imaging systems have been developed and are in use as real-time, multi-channel fluorometers to investigate heterogeneous patterns of photosynthetic performance of leaves and algae. This review will revise in several paragraphs the current status of chlorophyll fluorescence imaging, in exploring photosynthetic features to evaluate the physiological response of plant organisms in different domains. In the conclusion paragraph, an attempt will be made to answer the question posed in the title., R. Valcke., and Obsahuje bibliografické odkazy
The process of manual species identification is a daunting task, so much so that the number of taxonomists is seen to be declining. In order to assist taxonomists, many methods and algorithms have been proposed to develop semi-automated and fully automated systems for species identification. While semi-automated tools would require manual intervention by a domain expert, fully automated tools are assumed to be not as reliable as manual or semi-automated identification tools. Hence, in this study we investigate the accuracy of fully automated and semi-automated models for species identification. We have built fully automated and semi-automated species classification models using the monogenean species image dataset. With respect to monogeneans’ morphology, they are differentiated based on the morphological characteristics of haptoral bars, an-chors, marginal hooks and reproductive organs (male and female copulatory organs). Landmarks (in the semi-automated model) and shape morphometric features (in the fully automated model) were extracted from four monogenean species images, which were then classified using k-nearest neighbour and artificial neural network. In semi-automated models, a classification accuracy of 96.67 % was obtained using the k-nearest neighbour and 97.5 % using the artificial neural network, whereas in fully automated models, a classification accuracy of 90 % was obtained using the k-nearest neighbour and 98.8 % using the artificial neural network. As for the cross-validation, semi-automated models performed at 91.2 %, whereas fully automated models performed slightly higher at 93.75 %. and Corresponding author: Sarinder Kaur A/p Kashmir Singh
We develop a method for counting number of cells and extraction of approximate cell centers in 2D and 3D images of early stages of the zebra-fish embryogenesis. The approximate cell centers give us the starting points for the subjective surface based cell segmentation. We move in the inner normal direction all level sets of nuclei and membranes images by a constant speed with slight regularization of this flow by the (mean) curvature. Such multi-scale evolutionary process is represented by a geometrical advection-diffusion equation which gives us at a certain scale the desired information on the number of cells. For solving the problems computationally we use flux-based finite volume level set method developed by Frolkovič and Mikula in \cite{FM1} and semi-implicit co-volume subjective surface method given in \cite{CMSSg, MSSg_CVS, MSSg_chapter}. Computational experiments on testing and real 2D and 3D embryogenesis images are presented and the results are discussed.
Danish Fungi 2020 (DF20) is a fine-grained dataset and benchmark. The dataset, constructed from observations submitted to the Danish Fungal Atlas, is unique in its taxonomy-accurate class labels, small number of errors, highly unbalanced long-tailed class distribution, rich observation metadata, and well-defined class hierarchy. DF20 has zero overlap with ImageNet, allowing unbiased comparison of models fine-tuned from publicly available ImageNet checkpoints.
The dataset has 1,604 different classes, with 248,466 training images and 27,608 test images.
The aim of the course is to introduce digital humanities and to describe various aspects of digital content processing.
The course consists of 10 lessons with video material and a PowerPoint presentation with the same content.
Every lesson contains a practical session – either a Jupyter Notebook to work in Python or a text file with a short description of the task. Most of the practical tasks consist of running the programme and analyse the results.
Although the course does not focus on programming, the code can be reused easily in individual projects.
Some experience in running Python code is desirable but not required.
Alzheimer's Disease (AD) is the most frequent form of degenerative dementia and its early diagnosis is essential for effective treatment. Functional imaging modalities including Single Photon Emission Computed Tomography (SPECT) are often used with such an aim. However, conventional evaluation of SPECT images relies on manual reorientation and visual evaluation of tomographic slices which is time consuming, subjective and therefore prone to error. Our aim is to show an automatic Computer-Aided Diagnosis (CAD) system for improving the early detection of the AD. For this purpose, affine invariant descriptors of 3D SPECT image can be useful. The method consists of four steps: evaluation of invariant descriptors obtained using spherical harmonic analysis, statistical testing of their significance, application of regularized binary index models, and model verification via leave-one-out cross-validation scheme. The second approach is based on Support Vector Machine (SVM) classifier and visualization with use of self-organizing maps. Our approaches were tested on SPECT data from 11 adult patients with definite Alzheimer's disease and 10 adult patients with Amyotrophic Lateral Sclerosis (ALS) who were used as controls. A significant difference between SPECT spherical cuts of AD group and ALS group was both visually and numerically evaluated.
In this paper we deal with a problem of segmentation (including missing boundary completion) and subjective contour creation. For the corresponding models we apply the semi-implicit finite volume numerical schemes leading to methods which are robust, efficient and stable without any restriction to a time step. The finite volume discretization enables to use the spatial adaptivity and thus improve significantly the computational time. The computational results related to image segmentation with partly missing boundaries and subjective contour extraction are presented.