scholarly journals The Use of Robust Local Hausdorff Distances in Accuracy Assessment for Image Alignment of Brain MRI

2008 ◽  
Author(s):  
Eric Billet ◽  
Andriy Fedorov ◽  
Nikos Chrisochoides
Keyword(s):  
Error Estimation ◽  
Accuracy Assessment ◽  
Brain Mri ◽  
Source Code ◽  
Visual Assessment ◽  
Image Alignment ◽  
Error Assessment ◽  
Registration Error ◽  
Robust Version ◽  
Local Distance

We present and implement an error estimation protocol in the Insight Toolkit (ITK) for assessing the accuracy of image alignment. We base this error estimation on a robust version of the HausdorffDistance (HD) metric applied to the recovered edges of the images. The robust modifications we introduce to the HD metric significantly reduce the amount of outliers in the local distance error estimation. We evaluate the accuracy of our protocol on synthetically deformed images. We provide the source code and datasets to reproduce this evaluation. The proposed method is shown to improve error assessment when it is compared with conventional HD methods. This approach has many applications including local estimation and visual assessment of registration error and registration parameter selection.

scholarly journals A Registration Error Estimation Framework for Correlative Imaging

2021 ◽  
Author(s):  
Guillaume Potier ◽  
Frederic Lavancier ◽  
Stephan Kunne ◽  
Perrine Paul-Gilloteaux
Keyword(s):  
Error Estimation ◽  
Registration Error ◽  
Correlative Imaging

scholarly journals ACCURACY ASSESSMENT OF A UAV-BASED LANDSLIDE MONITORING SYSTEM

2016 ◽  
Vol XLI-B5 ◽  
pp. 895-902 ◽  
Author(s):  
M. V. Peppa ◽  
J. P. Mills ◽  
P. Moore ◽  
P. E. Miller ◽  
J. E. Chambers
Keyword(s):  
Image Matching ◽  
Accuracy Assessment ◽  
Bundle Adjustment ◽  
Landslide Monitoring ◽  
Control Points ◽  
Error Assessment ◽  
Ground Sample ◽  
Ground Control Points ◽  
Pixel Image ◽  
Spatio Temporal

Landslides are hazardous events with often disastrous consequences. Monitoring landslides with observations of high spatio-temporal resolution can help mitigate such hazards. Mini unmanned aerial vehicles (UAVs) complemented by structure-from-motion (SfM) photogrammetry and modern per-pixel image matching algorithms can deliver a time-series of landslide elevation models in an automated and inexpensive way. This research investigates the potential of a mini UAV, equipped with a Panasonic Lumix DMC-LX5 compact camera, to provide surface deformations at acceptable levels of accuracy for landslide assessment. The study adopts a self-calibrating bundle adjustment-SfM pipeline using ground control points (GCPs). It evaluates misalignment biases and unresolved systematic errors that are transferred through the SfM process into the derived elevation models. To cross-validate the research outputs, results are compared to benchmark observations obtained by standard surveying techniques. The data is collected with 6 cm ground sample distance (GSD) and is shown to achieve planimetric and vertical accuracy of a few centimetres at independent check points (ICPs). The co-registration error of the generated elevation models is also examined in areas of stable terrain. Through this error assessment, the study estimates that the vertical sensitivity to real terrain change of the tested landslide is equal to 9 cm.

scholarly journals Source Code Assessment and Classification Based on Estimated Error Probability Using Attentive LSTM Language Model and Its Application in Programming Education

2020 ◽  
Vol 10 (8) ◽  
pp. 2973 ◽  
Author(s):  
Md. Mostafizer Rahman ◽  
Yutaka Watanobe ◽  
Keita Nakamura
Keyword(s):  
Error Detection ◽  
Error Probability ◽  
Short Term Memory ◽  
Language Model ◽  
Source Code ◽  
Attention Mechanism ◽  
Error Assessment ◽  
Programming Education ◽  
Proposed Model ◽  
Estimated Error

The rate of software development has increased dramatically. Conventional compilers cannot assess and detect all source code errors. Software may thus contain errors, negatively affecting end-users. It is also difficult to assess and detect source code logic errors using traditional compilers, resulting in software that contains errors. A method that utilizes artificial intelligence for assessing and detecting errors and classifying source code as correct (error-free) or incorrect is thus required. Here, we propose a sequential language model that uses an attention-mechanism-based long short-term memory (LSTM) neural network to assess and classify source code based on the estimated error probability. The attentive mechanism enhances the accuracy of the proposed language model for error assessment and classification. We trained the proposed model using correct source code and then evaluated its performance. The experimental results show that the proposed model has logic and syntax error detection accuracies of 92.2% and 94.8%, respectively, outperforming state-of-the-art models. We also applied the proposed model to the classification of source code with logic and syntax errors. The average precision, recall, and F-measure values for such classification are much better than those of benchmark models. To strengthen the proposed model, we combined the attention mechanism with LSTM to enhance the results of error assessment and detection as well as source code classification. Finally, our proposed model can be effective in programming education and software engineering by improving code writing, debugging, error-correction, and reasoning.

scholarly journals D-GENIES : Dot plot large GENomes in an interactive, efficient and simple way

2018 ◽  
Author(s):  
Floréal Cabanettes ◽  
Christophe Klopp
Keyword(s):  
Open Source ◽  
Open Source Software ◽  
Software Package ◽  
Web Application ◽  
Source Code ◽  
Input Sequence ◽  
Image Alignment ◽  
Large Genome ◽  
Open Source Software Package ◽  
Large Genomes

Dot plots are widely used to quickly compare sequence sets. They provide a synthetic similarity overview, highlighting repetitions, breaks and inversions. Different tools have been developed to easily generated genomic alignment dot plots, but they are often limited in the input sequence size. D-GENIES is a standalone and WEB application performing large genome alignments using minimap2 software package and generating interactive dot plots. It enables users to sort query sequences along the reference, zoom in the plot and download several image, alignment or sequence files. D-GENIES is an easy to install open source software package (GPL) developed in Python and JavaScript. The source code is available at https://github.com/genotoul-bioinfo/dgenies and it can be tested at http://dgenies.toulouse.inra.fr/.

scholarly journals D-GENIES : Dot plot large GENomes in an interactive, efficient and simple way

2018 ◽  
Author(s):  
Christophe Klopp ◽  
Floréal Cabanettes
Keyword(s):  
Open Source ◽  
Open Source Software ◽  
Software Package ◽  
Web Application ◽  
Source Code ◽  
Input Sequence ◽  
Image Alignment ◽  
Large Genome ◽  
Open Source Software Package ◽  
Large Genomes

Dot plots are widely used to quickly compare sequence sets. They provide a synthetic similarity overview, highlighting repetitions, breaks and inversions. Different tools have been developed to easily generated genomic alignment dot plots, but they are often limited in the input sequence size. D-GENIES is a standalone and WEB application performing large genome alignments using minimap2 software package and generating interactive dot plots. It enables users to sort query sequences along the reference, zoom in the plot and download several image, alignment or sequence files. D-GENIES is an easy to install open source software package (GPL) developed in Python and JavaScript. The source code is available at https://github.com/genotoul-bioinfo/dgenies and it can be tested at http://dgenies.toulouse.inra.fr/.

scholarly journals D-GENIES: dot plot large genomes in an interactive, efficient and simple way

PeerJ ◽  
2018 ◽  
Vol 6 ◽  
pp. e4958 ◽  
Author(s):  
Floréal Cabanettes ◽  
Christophe Klopp
Keyword(s):  
Open Source ◽  
Open Source Software ◽  
Software Package ◽  
Web Application ◽  
Source Code ◽  
Input Sequence ◽  
Image Alignment ◽  
Large Genome ◽  
Open Source Software Package ◽  
Large Genomes

Dot plots are widely used to quickly compare sequence sets. They provide a synthetic similarity overview, highlighting repetitions, breaks and inversions. Different tools have been developed to easily generated genomic alignment dot plots, but they are often limited in the input sequence size. D-GENIES is a standalone and web application performing large genome alignments using minimap2 software package and generating interactive dot plots. It enables users to sort query sequences along the reference, zoom in the plot and download several image, alignment or sequence files. D-GENIES is an easy-to-install, open-source software package (GPL) developed in Python and JavaScript. The source code is available at https://github.com/genotoul-bioinfo/dgenies and it can be tested at http://dgenies.toulouse.inra.fr/.

Sign in / Sign up

Export Citation Format

Share Document