Search

Determining the portion obscured by clouds in the night sky recorded in an image from a meteor monitoring station can be useful to help in the discussion and analysis of studies in this area. Thereby, this work presents a proposal to quantitatively measure the proportion of the night sky covered by clouds from images of meteor records. The images used are from EXOSS database, particularly from the UVP1 and UVP2 stations. Two approaches were elaborated: the first one computes the proportion of pixels in clouds over the total number of pixels, the second approach calculates another percentage value by using image processing techniques and applying an equalization method. An application was created to perform the calculations in an automated way. The program displays an enhanced image and the two calculated percentages and can be used for specialists as a tool to guide their choice of coverage values. The results showed that the second approach proves to be better for “many” and “few” clouds; furthermore, the first approach proves to be better in low cloud density images.

The aim of this article is to study the minimum variance analysis (MVA) degeneration problem based on the variance space geometry. We propose a mathematical metric to evaluate the separation of the eigenvalues. In the MVA method, a variance space is obtained geometrically using an ellipsoid where the axes are equal to the square root of the eigenvalues of the covariance matrix. The metric is defined as the product between the geometric flattening of the ellipsoid with respect to the three axes. In this article, we present a statistical analysis applied to the distribution of the eigenvalue ratios and the mathematical metric focussed on the study of several interplanetary coronal mass ejections with and without magnetic clouds (MCs). The results show the non-applicability of the ratio between the intermediate and minimum eigenvalues, as well as that around $90\%$ of MC events have values in the $[4.5,19.5]$ range for the defined metric. Our metric is compared with others and we show its robustness in indicating the usefulness of the MVA method to identify the axes of MCs.

The aim of this study was to evaluate the diagnostic imaging approach to identify the deficiency of boron in leaves of maize. The experiment was conducted in a greenhouse under a hydroponic...

International audience; The proposal of this study is to analyze the texture pattern recognition over the local jet space looking forward to improve the texture characterization. Local jets decompose the image based on partial derivatives allowing the texture feature extraction be exploited in different levels of geometrical structures. Each local jet component evidences a different local pattern, such as, flat regions, directional variations and concavity or convexity. Subsequently , a texture descriptor is used to extract features from 0th, 1st and 2nd-derivative components. Four well-known databases (Brodatz, Vistex, Usptex and Outex) and four texture descriptors (Fourier descriptors, Gabor filters, Local Binary Pattern and Local Binary Pattern Variance) were used to validate the idea, showing in most cases an increase of the success rates.

The identification of plant species is not a trivial task, since it is carried out by experts and depends on the presence of fruits, flowers and leaves. However, fruits and flowers are not available throughout the year, while leaves are accessible most of the year. In order to assist the specialized work of species identification, methods of texture image analysis are used to extract characteristics from samples of imaged leaves and thus predict the species. Texture image analysis is a versatile and powerful technique able to extract measurements from patterns in the images. Using this technique, recent research has found a close relationship between texture and plant species (da Silva et al., 2015 and 2016). Here, we describe the procedure to extract texture features from microscopic images of leaves using Fourier (Cosgriff, 1960; Azencott, 1997; Gonzalez and Woods, 2006). It is important to highlight that other methods for texture extraction can be used as well. This protocol is split into two parts: (A) leaf epidermal dissociation and (B) automatic method for leaf epidermal image analysis.

O milho é uma cultura anual importante para diferentes setores da economia mundial. Sua produção é principalmente utilizada para consumo humano e animal, além de indústrias química e de biocombustíveis. Com o aumento da demanda mundial, há a necessidade de aumento da produtividade com diminuição de custos, tanto econômicos como ambientais. Isso leva a investimentos para maior tecnificação do cultivo, seleção de diferentes cultivares e busca por maior eficiência nutricional. Nesse contexto insere-se este doutorado, o qual propõe metodologia para diagnóstico nutricional precoce em culturas de milho. Para tanto, objetiva-se melhorar um sistema de classificação nutricional por imagem de folhas, analisar a invariância deste diagnóstico a diferentes híbridos de milho e identificar características que permitam uma análise em estágio precoce do ciclo de crescimento. Além disso, os estudos são realizados sobre experimentos de cultivos em ambiente controlado e em ambiente comercial. A análise das imagens é realizada pela extração de características de textura e, consequentemente, resulta no desenvolvimento de metodologias inovadoras nesta área. Especificamente, são propostas duas metodologias na área de descritores fractais e usando transformação local jet. Os resultados da diagnose nutricional demonstram como é promissora a pesquisa, uma vez que obtém-se 98% de acerto na classificação de níveis nutricionais de nitrogênio ou potássio em etapa chave para correção nutricional em um mesmo ciclo da cultura. Outra abordagem proposta, ainda promove a identificação e visualização de sintomas em estágio em que esses sintomas são considerados ocultos, comprovando a eficácia do reconhecimento de padrões de textura. The maize is an important annual crop for different sectors of the world economy. Its production is mainly used for human and animal consumption as well as chemical and biofuels industry. Because of the increase in world demand, there is the need for increased productivity with lower costs, both economic and ecological. This leads to greater investments in technification of cultivation, selection of different cultivars and research to improve nutritional efficiency. In this context, this PhD research proposes a methodology for early nutritional diagnosis in maize crops. Therefore, it is aimed to improve a nutritional classification system for image of leaves, analysis the invariance of this diagnostic at different maize hybrids and identifying features to provide an analysis at an early stage of the growth cycle. Furthermore, studies are conducted on crops under controlled environment and in a commercial environment. The image analysis is performed by texture feature extracting and, consequently, results in innovative methodologies in this area. Specifically, two methods are proposed in the area of fractal descriptors and using local jet transformation. The results of nutritional diagnosis demonstrate how research is promising, due to the 98% success rate in the classification of nutritional levels of nitrogen or potassium, in a key stage for nutritional correction in the same crop cycle. Another proposed approach promotes the symptoms identification and visualization in a stage where these symptoms are considered hidden, proving the effectiveness of the pattern recognition based on texture features.

Cellular automata (CA) are grouped into four classes, according to Wolfram's classification.An innovative approach to classify CAs in an automated way is proposed.Texture descriptors capture the nature of the evolved space-time diagrams.Experiments with elementary and totalistic CAs are presented. The spatio-temporal dynamics of cellular automata (CAs) has attracted the attention of researchers from different fields, mainly mathematics, computer science and engineering, as a consequence of both the intriguing spatio-temporal patterns that these dynamical systems evolve and the fact that they enable the modelling of complex natural phenomena. Yet, to this day, there are only a few studies that focus on the automated classification of cellular automata on the basis of the space-time diagrams they evolve. Here, we present an innovative approach to classify CAs according to Wolfram's classification scheme in an automated way by relying on texture descriptors that capture the nature of the evolved space-time diagrams. More specifically, we propose the use of one of two well-known texture descriptors, namely Local Binary Pattern Variance and Fourier descriptors, to generate features grasping the diagrams' nature, followed by nearest neighbor classification. The performance of this approach is assessed through a cross-validation and by analysing the percentage of pre-classified rules that is required to arrive at an acceptable success rate. The experiments involve the family of elementary CAs and four families of totalistic CAs with neighborhood radii ranging from one to three, and a state space consisting of up to three states. The results show the potential of our proposal with success rates varying between 65% and 98% depending on the size of the training set, which ranges from 10% to 90% of the rules in the CA family at stake. For totalistic CAs, this training set should be classified manually to start the process of automated classification.

Made available in DSpace on 2018-12-11T17:28:20Z (GMT). No. of bitstreams: 0 Previous issue date: 2016-05-24 This paper proposes a methodology for plant analysis and identification based on extracting texture features from microscopic images of leaf epidermis. All the experiments were carried out using 32 plant species with 309 epidermal samples captured by an optical microscope coupled to a digital camera. The results of the computational methods using texture features were compared to the conventional approach, where quantitative measurements of stomatal traits (density, length and width) were manually obtained. Epidermis image classification using texture has achieved a success rate of over 96%, while success rate was around 60% for quantitative measurements taken manually. Furthermore, we verified the robustness of our method accounting for natural phenotypic plasticity of stomata, analysing samples from the same species grown in different environments. Texture methods were robust even when considering phenotypic plasticity of stomatal traits with a decrease of 20% in the success rate, as quantitative measurements proved to be fully sensitive with a decrease of 77%. Results from the comparison between the computational approach and the conventional quantitative measurements lead us to discover how computational systems are advantageous and promising in terms of solving problems related to Botany, such as species identification. Institute of Mathematics and Computer Science University of São Paulo USP, Avenida Trabalhador são-carlense, 400 Scientific Computing Group São Carlos Institute of Physics University of São Paulo, PO Box 369 Department of Biological Sciences Faculty of Sciences and Languages Univ Estadual Paulista UNESP, Av. Dom Antônio, 2100 Department of Applied Biology Faculty of Agriculture and Veterinary Sciences Univ Estadual Paulista UNESP, Via de Acesso Prof. Paulo Donatto Castellane S/N Department of Biological Sciences Faculty of Sciences and Languages Univ Estadual Paulista UNESP, Av. Dom Antônio, 2100 Department of Applied Biology Faculty of Agriculture and Veterinary Sciences Univ Estadual Paulista UNESP, Via de Acesso Prof. Paulo Donatto Castellane S/N

This work proposes to obtain novel fractal descriptors from gray-level texture images by combining information from interior and boundary measures of the Minkowski dilation applied to the texture surface. At first, the image is converted into a surface where the height of each point is the gray intensity of the respective pixel in that position in the image. Thus, this surface is morphologically dilated by spheres. The radius of such spheres is ranged within an interval and the volume and the external area of the dilated structure are computed for each radius. The final descriptors are given by such measures concatenated and subject to a canonical transform to reduce the dimensionality. The proposal is an enhancement to the classical Bouligand-Minkowski fractal descriptors, where only the volume (interior) information is considered. As different structures may have the same volume, but not the same area, the proposal yields to more rich descriptors as confirmed by results on the classification of benchmark databases., Comment: 6 pages 3 figures