Delineation of Rock Fragments by Classification of Image Patches using Compressed Random Features

2014 ◽  
Keyword(s):  
Rock Fragments ◽  
Image Patches

scholarly journals Deep Learning for the Classification of Non-Hodgkin Lymphoma on Histopathological Images

Cancers ◽  
2021 ◽  
Vol 13 (10) ◽  
pp. 2419
Author(s):  
Georg Steinbuss ◽  
Mark Kriegsmann ◽  
Christiane Zgorzelski ◽  
Alexander Brobeil ◽  
Benjamin Goeppert ◽  
...  
Keyword(s):  
Deep Learning ◽  
Hodgkin Lymphoma ◽  
Expert Knowledge ◽  
B Cell Lymphoma ◽  
High Accuracy ◽  
Lymphocytic Leukemia ◽  
Non Hodgkin Lymphoma ◽  
Image Patches ◽  
Histopathological Images

The diagnosis and the subtyping of non-Hodgkin lymphoma (NHL) are challenging and require expert knowledge, great experience, thorough morphological analysis, and often additional expensive immunohistological and molecular methods. As these requirements are not always available, supplemental methods supporting morphological-based decision making and potentially entity subtyping are required. Deep learning methods have been shown to classify histopathological images with high accuracy, but data on NHL subtyping are limited. After annotation of histopathological whole-slide images and image patch extraction, we trained and optimized an EfficientNet convolutional neuronal network algorithm on 84,139 image patches from 629 patients and evaluated its potential to classify tumor-free reference lymph nodes, nodal small lymphocytic lymphoma/chronic lymphocytic leukemia, and nodal diffuse large B-cell lymphoma. The optimized algorithm achieved an accuracy of 95.56% on an independent test set including 16,960 image patches from 125 patients after the application of quality controls. Automatic classification of NHL is possible with high accuracy using deep learning on histopathological images and routine diagnostic applications should be pursued.

scholarly journals Proposal for geological classification and nomenclature of soils: both genetic-descriptive and compositional-mineralogical

2020 ◽  
Vol 42 (1) ◽  
pp. 81-97
Author(s):  
Luis Enrique Cruz-Guevara ◽  
Luis Felipe Cruz-Ceballos ◽  
Gladys Marcela Avendaño-Sánchez ◽  
Mario García-González
Keyword(s):  
Chemical Weathering ◽  
Soil Classification ◽  
Original Structure ◽  
Rock Fragments ◽  
Sedimentary Deposits ◽  
Geological Processes ◽  
Detailed Classification ◽  
Clay Layers ◽  
Physical And Chemical

Numerous systems with detailed classification of soil are in existence. Most of them are based on a variety of complex criteria, such as material type and properties like the amount of organic material, presence of clay layers, and the presence of oxidation or reduction iron-rich horizons, as well as depositional characteristics, its landform morphology and depositional formation processes. Many of these have been developed for use in fields such as agronomy and geotechnics. This paper focuses on the classification of the soil by determining its materials, their origin and the geological processes that shape them, following these basic assumptions: (1) The soil initially comes from the weathering of a parent substrate that can be either sedimentary deposits (for example, alluvial or fluvial) or of any type of rock (igneous, metamorphic or sedimentary), (2) the parent substrate structure is composed by original sequential facies (e.g. foliation, igneous cumulates or stratigraphic intercalation of sedimentary layers), (3) the physical and chemical weathering and the biogenic activity and productivity processes that occur in the soil modify both the original structure and the constituents of the parental substrate, resulting in the formation of new materials, the conservation of others, and the overprint of the sequential facies of the soil (horizons A, B and C) developed on the original parental sequential facies, additionally (4) some materials will be lost from the system and others will be incorporated into it. Finally, a strictly compositional-mineralogical classification of soil is also proposed, which corresponds essentially to the main groups of minerals: silicates, carbonates, phosphates, oxides and hydroxides, sulfates, organic rich matter, nitrates, sulphides, borates, native elements and halides, named in sedimentology as monomaterials, plus the polymaterials or rock fragments (RF). This classification offers an advantage when examining materials that are not genetically linked to the parent substrates, making each soil profile unique, by highlighting the role played by the parental materials in this process. This classification is intended to complement, but not replace any existing soil classification

scholarly journals Automatic Classification of Chickpea Varieties Using Computer Vision Techniques

Agronomy ◽  
2019 ◽  
Vol 9 (11) ◽  
pp. 672 ◽  
Author(s):  
Pourdarbani ◽  
Sabzi ◽  
García-Amicis ◽  
García-Mateos ◽  
Molina-Martínez ◽  
...  
Keyword(s):  
Computer Vision ◽  
Morphological Characteristics ◽  
Texture Features ◽  
Correct Classification Rate ◽  
Classification Rate ◽  
Swarm Optimization ◽  
Visual Classification ◽  
Image Patches ◽  
Selection Of

There are about 90 different varieties of chickpeas around the world. In Iran, where this study takes place, there are five species that are the most popular (Adel, Arman, Azad, Bevanij and Hashem), with different properties and prices. However, distinguishing them manually is difficult because they have very similar morphological characteristics. In this research, two different computer vision methods for the classification of the variety of chickpeas are proposed and compared. The images were captured with an industrial camera in Kermanshah, Iran. The first method is based on color and texture features extraction, followed by a selection of the most effective features, and classification with a hybrid of artificial neural networks and particle swarm optimization (ANN-PSO). The second method is not based on an explicit extraction of features; instead, image patches (RGB pixel values) are directly used as input for a three-layered backpropagation ANN. The first method achieved a correct classification rate (CCR) of 97.0%, while the second approach achieved a CCR of 99.3%. These results prove that visual classification of fruit varieties in agriculture can be done in a very precise way using a suitable method. Although both techniques are feasible, the second method is generic and more easily applicable to other types of crops, since it is not based on a set of given features.

scholarly journals Sparse Contribution Feature Selection and Classifiers Optimized by Concave-Convex Variation for HCC Image Recognition

2017 ◽  
Vol 2017 ◽  
pp. 1-14 ◽  
Author(s):  
Wenbo Pang ◽  
Huiyan Jiang ◽  
Siqi Li
Keyword(s):  
Feature Selection ◽  
Random Forest ◽  
Image Recognition ◽  
Bilateral Filter ◽  
Variation Method ◽  
Support Vector ◽  
Image Patches ◽  
Learning Machine ◽  
Hematoxylin Eosin

Accurate classification of hepatocellular carcinoma (HCC) image is of great importance in pathology diagnosis and treatment. This paper proposes a concave-convex variation (CCV) method to optimize three classifiers (random forest, support vector machine, and extreme learning machine) for the more accurate HCC image classification results. First, in preprocessing stage, hematoxylin-eosin (H&E) pathological images are enhanced using bilateral filter and each HCC image patch is obtained under the guidance of pathologists. Then, after extracting the complete features of each patch, a new sparse contribution (SC) feature selection model is established to select the beneficial features for each classifier. Finally, a concave-convex variation method is developed to improve the performance of classifiers. Experiments using 1260 HCC image patches demonstrate that our proposed CCV classifiers have improved greatly compared to each original classifier and CCV-random forest (CCV-RF) performs the best for HCC image recognition.

Polished slickensides preserved in the Obir Caves (Austria) close to the Periadriatic Fault System

2020 ◽  
Author(s):  
Stefanie Koppensteiner ◽  
Harald Bauer ◽  
Lukas Plan ◽  
Bernhard Grasemann
Keyword(s):  
Spatial Orientation ◽  
Host Rock ◽  
Fault System ◽  
Rock Fragments ◽  
Seismic Slip ◽  
Slip Surfaces ◽  
Carbonate Host Rock ◽  
Thin Section Analysis ◽  
Section Analysis

<p>We studied polished slickensides, which are perfectly preserved in the Obir Caves (Northern Karavanke Mountains, Austria) situated in the Middle Triassic Wetterstein limestone of the Hochobir massif. The investigated area is located close to the seismogenic ESE-trending Periadriatic Fault System, which is the border between the Eastern and Southern Alps. The polished slickensides observed on a block between two major left-lateral NE-SW trending slickensides record a range of polishing from none to highly-reflective fault surfaces. A classification of the different polishing grades of the fault surfaces inside the cave compared with their spatial orientation shows that there is no relationship between the degree of polishing and fault orientation. Associated cataclastically deformed brittle fault zones and partly polished slickensides at the cave entrance and on the Eastern slope of the Hochobir massif where the fault zone localizes in shattered dolomitic rocks, show similar kinematics and spatial orientation to the faults inside the Obir Caves.</p><p>Thin section analysis identified the smooth fault mirror surfaces as principal slip surfaces. Cataclastic grains are truncated along the principal slip surfaces and along secondary Riedel faults. Five different stages of cataclastic deformation can be distinguished: I) Undeformed carbonate host rock. II) Isolated fractures in the host rock with injected ultracataclastic material. III) Dilation cataclasites containing jigsaw breccia. IV) Ultracataclasite with angular-to-rounded host rock fragments and jigsaw breccia. V) Ultracataclasite with isolated clasts and truncated grains close to the mirror surfaces.</p><p>The microstructures including polished slickensides, injected cataclasites and truncated grains along principal slip surfaces as well as the geological position close to the seismogenic Periadriatic Fault System suggest that the investigated fault surfaces in the Obir Caves formed during seismic slip.</p>

scholarly journals A High-Accuracy Model Average Ensemble of Convolutional Neural Networks for Classification of Cloud Image Patches on Small Datasets

2019 ◽  
Vol 9 (21) ◽  
pp. 4500 ◽  
Author(s):  
Phung ◽  
Rhee
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Classification Accuracy ◽  
Complete Solution ◽  
Large Data ◽  
High Accuracy ◽  
Learning Approaches ◽  
Model Average ◽  
Image Patches

Research on clouds has an enormous influence on sky sciences and related applications, and cloud classification plays an essential role in it. Much research has been conducted which includes both traditional machine learning approaches and deep learning approaches. Compared with traditional machine learning approaches, deep learning approaches achieved better results. However, most deep learning models need large data to train due to the large number of parameters. Therefore, they cannot get high accuracy in case of small datasets. In this paper, we propose a complete solution for high accuracy of classification of cloud image patches on small datasets. Firstly, we designed a suitable convolutional neural network (CNN) model for small datasets. Secondly, we applied regularization techniques to increase generalization and avoid overfitting of the model. Finally, we introduce a model average ensemble to reduce the variance of prediction and increase the classification accuracy. We experiment the proposed solution on the Singapore whole-sky imaging categories (SWIMCAT) dataset, which demonstrates perfect classification accuracy for most classes and confirms the robustness of the proposed model.

scholarly journals MR Brain Segmentation using Decision Trees

2013 ◽  
Author(s):  
Amod Jog ◽  
Snehashis Roy ◽  
Jerry L. Prince ◽  
Aaron Carass
Keyword(s):  
Decision Trees ◽  
Magnetic Resonance Images ◽  
Image Feature ◽  
Data Channel ◽  
Model Free ◽  
Image Patches ◽  
Validation Experiment ◽  
Fluid Attenuated Inversion Recovery ◽  
Leave One Out

Segmentation of the human cerebrum from magnetic resonance images (MRI) into its component tissues has been a defining problem in medical imaging. Until recently, this has been solved as the tissue classification of the T1-weighted (T1-w) MRI, with numerous solutions for this problem having appeared in the literature. The clinical demands of understanding lesions, which are indistinguishable from gray matter in T1-w images, has necessitated the incorporation of T2-weighted Fluid Attenuated Inversion Recovery (FLAIR) images to improve segmentation of the cerebrum. Many of the existing methods fail to handle the second data channel gracefully, because of assumptions about their model. In our new approach, we explore a model free algorithm which uses a classification technique based on ensembles of decision trees to learn the mapping from an image feature to the corresponding tissue label. We use corresponding image patches from a registered set of T1-w and FLAIR images with a manual segmentation to construct our decision tree ensembles. Our method is efficient, taking less than two minutes on a 240x240x48 volume. We conduct experiments on five training sets in a leave-one-out fashion, as well as validation on an additional twelve subjects, and a landmark validation experiment on another cohort of five subjects.

scholarly journals Contextual Classification of Image Patches with Latent Aspect Models

2009 ◽  
Vol 2009 ◽  
pp. 1-20 ◽  
Author(s):  
Florent Monay ◽  
Pedro Quelhas ◽  
Jean-Marc Odobez ◽  
Daniel Gatica-Perez
Keyword(s):  
Image Patches
Sign in / Sign up

Export Citation Format

Share Document