scholarly journals Recognition of boards using wood fingerprints based on a fusion of feature detection methods

2015 ◽  
Vol 111 ◽  
pp. 164-173 ◽  
Author(s):  
Tobias Pahlberg ◽  
Olle Hagman ◽  
Matthew Thurley
Keyword(s):  
Feature Detection ◽  
Detection Methods

scholarly journals Augmented Reality and Machine Learning Incorporation Using YOLOv3 and ARKit

2021 ◽  
Vol 11 (13) ◽  
pp. 6006
Author(s):  
Huy Le ◽  
Minh Nguyen ◽  
Wei Qi Yan ◽  
Hoa Nguyen
Keyword(s):  
Machine Learning ◽  
Augmented Reality ◽  
Object Detection ◽  
Feature Detection ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Data Annotation ◽  
Machine Learning Model ◽  
Potential Benefits ◽  
Feature Detection And Tracking

Augmented reality is one of the fastest growing fields, receiving increased funding for the last few years as people realise the potential benefits of rendering virtual information in the real world. Most of today’s augmented reality marker-based applications use local feature detection and tracking techniques. The disadvantage of applying these techniques is that the markers must be modified to match the unique classified algorithms or they suffer from low detection accuracy. Machine learning is an ideal solution to overcome the current drawbacks of image processing in augmented reality applications. However, traditional data annotation requires extensive time and labour, as it is usually done manually. This study incorporates machine learning to detect and track augmented reality marker targets in an application using deep neural networks. We firstly implement the auto-generated dataset tool, which is used for the machine learning dataset preparation. The final iOS prototype application incorporates object detection, object tracking and augmented reality. The machine learning model is trained to recognise the differences between targets using one of YOLO’s most well-known object detection methods. The final product makes use of a valuable toolkit for developing augmented reality applications called ARKit.

Objective 3D atmospheric front detection in high-resolution numerical weather prediction data

2021 ◽  
Author(s):  
Andreas Beckert ◽  
Lea Eisenstein ◽  
Tim Hewson ◽  
George C. Craig ◽  
Marc Rautenhaus
Keyword(s):  
High Resolution ◽  
Numerical Weather Prediction ◽  
Feature Detection ◽  
3D Visualization ◽  
Weather Prediction ◽  
Three Dimensional ◽  
Detection Methods ◽  
Numerical Weather ◽  
Atmospheric Fronts ◽  
Front Detection

<p><span>Atmospheric fronts, a widely used conceptual model in meteorology, describe sharp boundaries between two air masses of different thermal properties. In the mid-latitudes, these sharp boundaries are commonly associated with extratropical cyclones. The passage of a frontal system is accompanied by significant weather changes, and therefore fronts are of particular interest in weather forecasting. Over the past decades, several two-dimensional, horizontal feature detection methods to objectively identify atmospheric fronts in numerical weather prediction (NWP) data were proposed in the literature (e.g. Hewson, Met.Apps. 1998). In addition, recent research (Kern et al., IEEE Trans. Visual. Comput. Graphics, 2019) has shown the feasibility of detecting atmospheric fronts as three-dimensional surfaces representing the full 3D frontal structure. In our work, we build on the studies by Hewson (1998) and Kern et al. (2019) to make front detection usable for forecasting purposes in an interactive 3D visualization environment. We consider the following aspects: (a) As NWP models evolved in recent years to resolve atmospheric processes on scales far smaller than the scale of midlatitude-cyclone- fronts, we evaluate whether previously developed detection methods are still capable to detect fronts in current high-resolution NWP data. (b) We present integration of our implementation into the open-source “Met.3D” software (http://met3d.wavestoweather.de) and analyze two- and three-dimensional frontal structures in selected cases of European winter storms, comparing different models and model resolution. (c) The considered front detection methods rely on threshold parameters, which mostly refer to the magnitude of the thermal gradient within the adjacent frontal zone - the frontal strength. If the frontal strength exceeds the threshold, a so-called feature candidate is classified as a front, while others are discarded. If a single, fixed, threshold is used, unwanted “holes” can be observed in the detected fronts. Hence, we use transparency mapping with fuzzy thresholds to generate continuous frontal features. We pay particular attention to the adjustment of filter thresholds and evaluate the dependence of thresholds and resolution of the underlying data.</span></p>

Systematic development and evaluation of composite methods for recognition of three-dimensional subtractive features

2005 ◽  
Vol 219 (12) ◽  
pp. 871-890 ◽  
Author(s):  
O Owodunni ◽  
S Hinduja
Keyword(s):  
Feature Detection ◽  
Three Dimensional ◽  
Detection Methods ◽  
Test Bed ◽  
The Public ◽  
Detection Systems ◽  
Composite Methods ◽  
Composite Feature ◽  
Tree Pruning ◽  
Pruning Technique

This paper describes a systematic procedure for developing composite feature detection systems from six methods for detecting three-dimensional depression features. The six methods, proposed by the authors in earlier papers, correspond to all the possible ways of grouping faces together from the simplest to the most complex grouping. All the possible ways of combining the six feature detection methods are considered and arranged in a tree structure. The possible composites are reduced to 20, using a tree pruning technique based on the criteria that the features detected should be the same (i.e. consistent), irrespective of the ordering of the faces in the B-rep model and that all faces of the component should be detected (i.e. complete coverage). A test bed for these 20 composites has been developed, implemented, and tested using carefully selected components from the public domain. The performance of these 20 composites is evaluated on the basis of suitability of the features as input to a machining application with minimal or no additional geometric reasoning, thus enabling the most promising composites to be identified.

scholarly journals Kronos: a workflow assembler for genome analytics and informatics

2016 ◽  
Author(s):  
M Jafar Taghiyar ◽  
Jamie Rosner ◽  
Diljot Grewal ◽  
Bruno Grande ◽  
Radhouane Aniba ◽  
...  
Keyword(s):  
Feature Detection ◽  
Automated Analysis ◽  
Configuration File ◽  
Detection Methods ◽  
Reproducible Research ◽  
Robust Implementation ◽  
Free Open Source ◽  
Standard Framework ◽  
Python Package ◽  
Generation Sequencing

The field of next generation sequencing informatics has matured to a point where algorithmic advances in sequence alignment and individual feature detection methods have stabilized. Practical and robust implementation of complex analytical workflows (where such tools are structured into "best practices" for automated analysis of NGS datasets) still requires significant programming investment and expertise. We present Kronos, a software platform for automating the development and execution of reproducible, auditable and distributable bioinformatics workflows. Kronos obviates the need for explicit coding of workflows by compiling a text configuration file into executable Python applications. The framework of each workflow includes a run manager to execute the encoded workflows locally (or on a cluster or cloud), parallelize tasks, and log all runtime events. Resulting workflows are highly modular and configurable by construction, facilitating flexible and extensible meta-applications which can be modified easily through configuration file editing. The workflows are fully encoded for ease of distribution and can be instantiated on external systems, promoting and facilitating reproducible research and comparative analyses. We introduce a framework for building Kronos components which function as shareable, modular nodes in Kronos workflows. The Kronos platform provides a standard framework for developers to implement custom tools, reuse existing tools, and contribute to the community at large. Kronos is shipped with both Docker and Amazon AWS machine images. It is free, open source and available through PyPI (Python Package Index) and https://github.com/jtaghiyar/kronos. Keywords: genomics; workflow; pipeline; reproducibility

scholarly journals Weighted Polynomial Approximation for Automated Detection of Inspiratory Flow Limitation

2017 ◽  
Vol 2017 ◽  
pp. 1-10
Author(s):  
Sheng-Cheng Huang ◽  
Hao-Yu Jan ◽  
Tieh-Cheng Fu ◽  
Wen-Chen Lin ◽  
Geng-Hong Lin ◽  
...  
Keyword(s):  
Polynomial Approximation ◽  
Feature Detection ◽  
Absolute Error ◽  
Time Algorithm ◽  
Inspiratory Flow ◽  
Detection Methods ◽  
Flow Limitation ◽  
Third Order ◽  
Time Curve ◽  
Order Polynomial

Inspiratory flow limitation (IFL) is a critical symptom of sleep breathing disorders. A characteristic flattened flow-time curve indicates the presence of highest resistance flow limitation. This study involved investigating a real-time algorithm for detecting IFL during sleep. Three categories of inspiratory flow shape were collected from previous studies for use as a development set. Of these, 16 cases were labeled as non-IFL and 78 as IFL which were further categorized into minor level (20 cases) and severe level (58 cases) of obstruction. In this study, algorithms using polynomial functions were proposed for extracting the features of IFL. Methods using first- to third-order polynomial approximations were applied to calculate the fitting curve to obtain the mean absolute error. The proposed algorithm is described by the weighted third-order (w.3rd-order) polynomial function. For validation, a total of 1,093 inspiratory breaths were acquired as a test set. The accuracy levels of the classifications produced by the presented feature detection methods were analyzed, and the performance levels were compared using a misclassification cobweb. According to the results, the algorithm using the w.3rd-order polynomial approximation achieved an accuracy of 94.14% for IFL classification. We concluded that this algorithm achieved effective automatic IFL detection during sleep.

The Research on the Detection Methods of EMU Break Valves Features

2014 ◽  
Vol 687-691 ◽  
pp. 1034-1037
Author(s):  
Chun Ling Guan
Keyword(s):  
Neural Network ◽  
Feature Detection ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Characteristic Parameters ◽  
Spatial Function ◽  
Network Algorithm ◽  
Detection Technology ◽  
Neural Network Algorithm ◽  
Multiple Units

This paper focuses on the detection technology for Electric Multiple Units (EMU) break valves features. Aiming at the issues of EMU break valves features detection, this paper propose a kind of EMU break valves feature detection technology based on neural network algorithm which does not overly dependent on break valve characteristic parameters. The spatial function neural network algorithm is used to predict the EMU break valves features. The experiments illustrate the proposed algorithm can increase the detection accuracy with satisfactory effects in EMU break valves features detection.

scholarly journals Analysis of Electron Transparent Beam-Sensitive Samples Using Scanning Electron Microscopy Coupled With Energy-Dispersive X-ray Spectroscopy

2020 ◽  
Vol 26 (3) ◽  
pp. 373-386 ◽  
Author(s):  
Anders Brostrøm ◽  
Kirsten Inga Kling ◽  
Karin Sørig Hougaard ◽  
Kristian Mølhave
Keyword(s):  
Electron Microscopy ◽  
Scanning Electron Microscopy ◽  
Feature Detection ◽  
Energy Dispersive ◽  
Detection Methods ◽  
Acquisition Time ◽  
Particle Analysis ◽  
X Ray ◽  
Advantages And Disadvantages ◽  
Scanning Electron

AbstractScanning electron microscopy, coupled with energy-dispersive X-ray spectroscopy (EDS), is a powerful tool used in many scientific fields. It can provide nanoscale images, allowing size and morphology measurements, as well as provide information on the spatial distribution of elements in a sample. This study compares the capabilities of a traditional EDS detector with a recently developed annular EDS detector when analyzing electron transparent and beam-sensitive NaCl particles on a TEM grid. The optimal settings for single particle analysis are identified in order to minimize beam damage and optimize sample throughput via the choice of acceleration voltage, EDS acquisition time, and quantification model. Here, a linear combination of two models is used to bridge results for particle sizes, which are neither bulk nor sufficiently thin to assume electron transparent. Additionally, we show that the increased count rate obtainable with the annular detector enables mapping as a viable analysis strategy compared with feature detection methods, which only scan segmented regions. Finally, we discuss advantages and disadvantages of the two analysis strategies.

scholarly journals High precision automated detection of labeled nuclei in Gigapixel resolution image data of Mouse Brain

2018 ◽  
Author(s):  
Sukhendu Das ◽  
Jaikishan Jayakumar ◽  
Samik Banerjee ◽  
Janani Ramaswamy ◽  
Venu Vangala ◽  
...  
Keyword(s):  
Mouse Brain ◽  
High Performance ◽  
Feature Detection ◽  
Human Performance ◽  
Fluorescent Protein ◽  
Ground Truth ◽  
Classification Problem ◽  
Complex Problem ◽  
Detection Methods ◽  
Imaging Data

AbstractThere is a need in modern neuroscience for accurate and automated image processing techniques for analyzing the large volume of neuroanatomical imaging data. Even at light microscopic levels, imaging mouse brains produces individual data volumes in the TerraByte range. A fundamental task involves the detection and quantification of objects of a given type, e.g. neuronal nuclei or somata, in brain scan dataset. Traditionally this quantification has been performed by human visual inspection with high accuracy, that is not scalable. When modern automated CNN and SVM-based methods are used to solve this classification problem, they achieve accuracy levels that range between 85 – 92%. However, higher rates of precision and recall that are close to that of human performance are necessary. In this paper, we describe an unsupervised, iterative algorithm, which provides a high performance for a specific problem of detecting Green Fluorescent Protein labeled nuclei in 2D scans of mouse brains. The algorithm judiciously combines classical computer vision techniques and is focused on the complex problem of decomposing strong overlapped objects of interest. Our proposed technique uses feature detection methods on ridge lines over distance transformation of the image and an arc based iterative spatial-filling method to solve the problem. We demonstrate our results on mouse brain dataset of Gigabyte resolution and compare it with manual annotation of the brains. Our results show that an aptly designed CV algorithm with classical feature extractors when tailored to this problem of interest achieves near-ideal human-like performance. Quantitative comparative analysis, using manually annotated ground truth, reveals that our approach performs better on mouse brain scans than general purpose machine learning (including deep CNN) methods.

Sign in / Sign up

Export Citation Format

Share Document