This work proposes a method for texture classification based on the successive application of a local transform presented here for the first time. Such transform comprises two steps: (1) We built a ...two-layer mapping relating each pixel with its neighborhood, with the weights in the first layer randomly assigned; (2) We use the parameters learned by such mapping to transform the original image. Finally, we extract local descriptors at different stages of the successive application of this transform to compose the texture descriptors. The performance of our method is verified in the classification of benchmark texture databases and compared with state-of-the-art approaches. We also present an application for plant species identification. The results confirm our expectation that a model that is not based on the classical learning-based approach can still be competitive in texture analysis.
•A local randomized projection is proposed for texture classification.•The projection is successively applied over the image and local descriptors are collected.•The performance of the proposed descriptors is verified on benchmark texture databases.•An application to the identification of Brazilian plant species is also presented.•Our approach outperforms state-of-the-art methods in terms of classification accuracy.
•Deep layers of Convolutional Neural Networks are used for feature extraction.•Handcrafted and learned features are used together to extract information.•Different architectures for combining ...handcrafted and learned features are proposed.•Combination of different features is used to solve image classification problems.
This work presents a generic computer vision system designed for exploiting trained deep Convolutional Neural Networks (CNN) as a generic feature extractor and mixing these features with more traditional hand-crafted features. Such a system is a single structure that can be used for synthesizing a large number of different image classification tasks. Three substructures are proposed for creating the generic computer vision system starting from handcrafted and non-handcrafter features: i)one that remaps the output layer of a trained CNN to classify a different problem using an SVM; ii) a second for exploiting the output of the penultimate layer of a trained CNN as a feature vector to feed an SVM; and iii) a third for merging the output of some deep layers, applying a dimensionality reduction method, and using these features as the input to an SVM. The application of feature transform techniques to reduce the dimensionality of feature sets coming from the deep layers represents one of the main contributions of this paper. Three approaches are used for the non-handcrafted features: deep transfer learning features based on convolutional neural networks (CNN), principal component analysis network (PCAN), and the compact binary descriptor (CBD). For the handcrafted features, a wide variety of state-of-the-art algorithms are considered: Local Ternary Patterns, Local Phase Quantization, Rotation Invariant Co-occurrence Local Binary Patterns, Completed Local Binary Patterns, Rotated local binary pattern image, Globally Rotation Invariant Multi-scale Co-occurrence Local Binary Pattern, and several others. The computer vision system based on the proposed approach was tested on many different datasets, demonstrating the generalizability of the proposed approach thanks to the strong performance recorded. The Wilcoxon signed rank test is used to compare the different methods; moreover, the independence of the different methods is studied using the Q-statistic. To facilitate replication of our experiments, the MATLAB source code will be available at (https://www.dropbox.com/s/bguw035yrqz0pwp/ElencoCode.docx?dl=0).
Local features are widely utilized in a large number of applications, e.g., object categorization, image retrieval, robust matching, and robot localization. In this review, we focus on detectors and ...local descriptors. Both earlier corner detectors, e.g., Harris corner detector, and later region detectors, e.g., Harris affine region detector, are described in brief. Most kinds of descriptors are described and summarized in a comprehensive way. Five types of descriptors are included, which are filter-based descriptors, distribution-based descriptors, textons, derivative-based descriptors and others. Finally, the matching methods and different applications with respect to the local features are also mentioned. The objective of this review is to provide a brief introduction for new researchers to the local feature research field, so that they can follow an appropriate methodology according to their specific requirements.
Electrocatalytic hydrogenation is increasingly studied as an alternative to integrate the use of recycled carbon feedstocks with renewable energy sources. However, the abundant empiric observations ...available have not been correlated with fundamental properties of substrates and catalysts. In this study, we investigated electrocatalytic hydrogenation of a homologues series of carboxylic acids, ketones, phenolics, and aldehydes on a variety of metals (Pd, Rh, Ru, Cu, Ni, Zn, and Co). We found that the rates of carbonyl reduction in aldehydes correlate with the corresponding binding energies between the aldehydes and the metals according to the Sabatier principle. That is, the highest rates are obtained at intermediate binding energies. The rates of H2 evolution that occur in parallel to hydrogenation also correlate with the H-metal binding energies, following the same volcano-type behavior. Within the boundaries of this model (e.g., compounds reactive at room temperature and without important steric effects over the carbonyl group), the reported correlations help to explain the complex trends derived from the experimental observations, allowing for the correlation of rates with binding energies and the differentiation of mechanistic routes.
Display omitted
•QSPR model with improved predictability is developed to estimate the degradation rate constants of VOCs.•Atomic data derived from quantum mechanical calculations are firstly ...introduced to norm descriptors.•External prediction is made to assess the −logkOH of nine hydrofluoroethers.
The kinetic rate constant of volatile organic compounds (VOCs) degradation represents an important parameter, which is valuable for evaluating the removal efficiency and ecological risk of pollutants. In this study, the multiple-linear-regression method using quantum chemical and norm descriptors is utilized to develop a room-temperature quantitative structure–property relationships (QSPR) model for kinetic rate constant estimation. The correlation coefficient (R2) and root-mean-square error (RMSE) are 0.8918 and 0.4086 for the training set, as well as 0.9096 and 0.3901 for the test set, respectively, which suggests the as-developed model has good stability and predictability. Applicability domain analysis demonstrates that the model is reliable and generalizable for assessing the −logkOH of VOCs covering a wide variety of molecular structures. In addition, an external prediction is made to assess the degradation rate constants of nine hydrofluoroethers, which implies the predictability of the model. It is worth noting that the quantum mechanical parameters, i.e., natural population analysis and orbital energy for atoms are introduced to norm descriptors, which expands the number/type of norm descriptors and greatly improves the accuracy of the model. Such combinational quantum chemical and norm descriptors are expected to be used for building accurate and robust models for other chemical properties prediction.
The delimitation of fish stocks and how species use habitats are essential keys to develop and to implement fishery resources management and rational sustainable programs. Otolith shape and ...microchemistry analyses can provide helpful information for defining population units and solving ecological connectivity issues. The black drum, Pogonias courbina, is an important fishery resource in the southeastern Brazil lagoon systems, and is considered a vulnerable fish according to the IUCN Red List of Threatened Species. Thus, the present study aimed to understand the population structure and habitat connectivity of P. courbina in two lagoon systems in the south-east coast of Rio de Janeiro, Brazil. A total of 60 individuals were collected from the lagoons of Saquarema (SQ) and Araruama (AR), between November 2019 and April 2020. Thirty individuals from each location, all estimated to be two years old based on the counting of the annual growth increments, were used. The composition (multi-elemental signatures – MES) and shape (elliptic Fourier descriptors – EFD) of the sagittal otoliths were integrated to evaluate the population structure and the habitat connectivity of the fish inside these lagoon systems. EFD showed differences between lagoon systems, with an overall reclassification rate of 97%. The MES exhibited distinct patterns between lagoon systems, mainly driven by differences in Ba/Ca, Co/Ca, Li/Ca, Mg/Ca, Ni/Ca, Sr/Ca, and Zn/Ca ratios. The overall reclassification rate for MES was also 97% (93% and 100% for SQ and ARA, respectively). The overall reclassification rate obtained using both EFD and MES was 98%. The results suggest a clear spatial discrimination and low connectivity between these groups of two years old P. coubina individuals living in the studied lagoon systems. These findings imply that small-scale artisanal fisheries in the lagoon systems require more attention, aiming to maximize local management strategies for commercially exploited species.
•Population structure and habitat connectivity of Pogonias courbina in two Brazilian coastal lagoon systems were studied•Otolith shape and chemical signatures indicated a clear spatial discrimination and low connectivity between individuals.•These findings suggest that the small-scale artisanal fisheries in the lagoon systems should be managed locally.
Analysis of the statistical properties of natural images has played a vital role in the design of no-reference (NR) image quality assessment (IQA) techniques. In this paper, we propose parametric ...models describing the general characteristics of chromatic data in natural images. They provide informative cues for quantifying visual discomfort caused by the presence of chromatic image distortions. The established models capture the correlation of chromatic data between spatially adjacent pixels by means of color invariance descriptors. The use of color invariance descriptors is inspired by their relevance to visual perception, since they provide less sensitive descriptions of image scenes against viewing geometry and illumination variations than luminances. In order to approximate the visual quality perception of chromatic distortions, we devise four parametric models derived from invariance descriptors representing independent aspects of color perception: 1) hue; 2) saturation; 3) opponent angle; and 4) spherical angle. The practical utility of the proposed models is examined by deploying them in our new general-purpose NR IQA metric. The metric initially estimates the parameters of the proposed chromatic models from an input image to constitute a collection of quality-aware features (QAF). Thereafter, a machine learning technique is applied to predict visual quality given a set of extracted QAFs. Experimentation performed on large-scale image databases demonstrates that the proposed metric correlates well with the provided subjective ratings of image quality over commonly encountered achromatic and chromatic distortions, indicating that it can be deployed on a wide variety of color image processing problems as a generalized IQA solution.