Standardized coordinate systems for solar image data

2002 ◽  
Vol 29 (12) ◽  
pp. 2093-2098 ◽  
Author(s):  
William T. Thompson
2006 ◽  
Vol 449 (2) ◽  
pp. 791-803 ◽  
Author(s):  
W. T. Thompson

Solar Physics ◽  
2013 ◽  
Vol 288 (1) ◽  
pp. 435-462 ◽  
Author(s):  
J. M. Banda ◽  
R. A. Angryk ◽  
P. C. H. Martens

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2592
Author(s):  
Xuemin Cheng ◽  
Yong Ren ◽  
Kaichang Cheng ◽  
Jie Cao ◽  
Qun Hao

In this study, we propose a method for training convolutional neural networks to make them identify and classify images with higher classification accuracy. By combining the Cartesian and polar coordinate systems when describing the images, the method of recognition and classification for plankton images is discussed. The optimized classification and recognition networks are constructed. They are available for in situ plankton images, exploiting the advantages of both coordinate systems in the network training process. Fusing the two types of vectors and using them as the input for conventional machine learning models for classification, support vector machines (SVMs) are selected as the classifiers to combine these two features of vectors, coming from different image coordinate descriptions. The accuracy of the proposed model was markedly higher than those of the initial classical convolutional neural networks when using the in situ plankton image data, with the increases in classification accuracy and recall rate being 5.3% and 5.1% respectively. In addition, the proposed training method can improve the classification performance considerably when used on the public CIFAR-10 dataset.


2013 ◽  
Vol 6 (4) ◽  
pp. 329-345 ◽  
Author(s):  
David C. Stenning ◽  
Thomas C. M. Lee ◽  
David A. van Dyk ◽  
Vinay Kashyap ◽  
Julia Sandell ◽  
...  

2019 ◽  
Vol 1 ◽  
pp. 1-2
Author(s):  
Akihiro Tsukamoto

<p><strong>Abstract.</strong> Museums, libraries, and other public research organizations have been creating digital archives of historical maps for some time. Initially, more work was required to archive historical maps than written documents, as they needed to be imaged in sections and then recombined. However, recent improvements in imaging technology and information devices have made it comparatively easy to create digital archives. In recent years, it has even become possible to view and download digital images of historical maps from sites run by the organizations possessing these maps, as well as from cross-searchable portal sites such as Old Maps Online (https://www.oldmapsonline.org) and Map Warper (https://mapwarper.net).</p><p>These portal sites provide terrestrial georeferencing functionality, in which historical maps are superimposed on a projected coordinate system. This allows the sharing of geometrically corrected historical maps and images, as well as linking table information for control points created during the georeferencing process. As progress is made creating and publishing digital archives of these historical maps, it will become increasingly important to increase both the depth and number of methodologies used to analyze historical maps using GIS.</p><p>In this study, I make use of image data from historical maps that have been geometrically corrected as well as control points created during the georeferencing process to conduct a GIS analysis of historicalmaps of several cities. My specific goal in this study is to analyze historical maps published for Edo, Osaka, and Kyoto, in order to quantitatively reveal differences in the shapes of cities drawn using the unique layouts of historical maps, which differ from modern projected coordinate systems (Table 1).</p>


Solar Physics ◽  
2012 ◽  
Vol 283 (1) ◽  
pp. 113-141 ◽  
Author(s):  
J. M. Banda ◽  
R. A. Angryk ◽  
P. C. H. Martens

Sign in / Sign up

Export Citation Format

Share Document