Adaptive Image Sampling Using Deep Learning and Its Application on X-Ray Fluorescence Image Reconstruction. Dai, Q., Chopp, H., Pouyet, E., Cossairt, O., Walton, M., & Katsaggelos, A. K. IEEE Transactions on Multimedia, 22(10):2564–2578, oct, 2020. ![Adaptive Image Sampling Using Deep Learning and Its Application on X-Ray Fluorescence Image Reconstruction [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex This paper presents an adaptive image sampling algorithm based on Deep Learning (DL). It consists of an adaptive sampling mask generation network which is jointly trained with an image inpainting network. The sampling rate is controlled by the mask generation network, and a binarization strategy is investigated to make the sampling mask binary. In addition to the image sampling and reconstruction process, we show how it can be extended and used to speed up raster scanning such as the X-Ray fluorescence (XRF) image scanning process. Recently XRF laboratory-based systems have evolved into lightweight and portable instruments thanks to technological advancements in both X-Ray generation and detection. However, the scanning time of an XRF image is usually long due to the long exposure requirements (e.g., 100 $μ$ s-1 ms per point). We propose an XRF image inpainting approach to address the long scanning times, thus speeding up the scanning process, while being able to reconstruct a high quality XRF image. The proposed adaptive image sampling algorithm is applied to the RGB image of the scanning target to generate the sampling mask. The XRF scanner is then driven according to the sampling mask to scan a subset of the total image pixels. Finally, we inpaint the scanned XRF image by fusing the RGB image to reconstruct the full scan XRF image. The experiments show that the proposed adaptive sampling algorithm is able to effectively sample the image and achieve a better reconstruction accuracy than that of existing methods.
@article{Qiqin2019,
abstract = {This paper presents an adaptive image sampling algorithm based on Deep Learning (DL). It consists of an adaptive sampling mask generation network which is jointly trained with an image inpainting network. The sampling rate is controlled by the mask generation network, and a binarization strategy is investigated to make the sampling mask binary. In addition to the image sampling and reconstruction process, we show how it can be extended and used to speed up raster scanning such as the X-Ray fluorescence (XRF) image scanning process. Recently XRF laboratory-based systems have evolved into lightweight and portable instruments thanks to technological advancements in both X-Ray generation and detection. However, the scanning time of an XRF image is usually long due to the long exposure requirements (e.g., 100\; $\mu$ s-1 ms per point). We propose an XRF image inpainting approach to address the long scanning times, thus speeding up the scanning process, while being able to reconstruct a high quality XRF image. The proposed adaptive image sampling algorithm is applied to the RGB image of the scanning target to generate the sampling mask. The XRF scanner is then driven according to the sampling mask to scan a subset of the total image pixels. Finally, we inpaint the scanned XRF image by fusing the RGB image to reconstruct the full scan XRF image. The experiments show that the proposed adaptive sampling algorithm is able to effectively sample the image and achieve a better reconstruction accuracy than that of existing methods.},
archivePrefix = {arXiv},
arxivId = {1812.10836},
author = {Dai, Qiqin and Chopp, Henry and Pouyet, Emeline and Cossairt, Oliver and Walton, Marc and Katsaggelos, Aggelos K.},
doi = {10.1109/TMM.2019.2958760},
eprint = {1812.10836},
issn = {1520-9210},
journal = {IEEE Transactions on Multimedia},
keywords = {Adaptive sampling,X-Ray fluorescence,convolutional neural network,inpainting},
month = {oct},
number = {10},
pages = {2564--2578},
title = {{Adaptive Image Sampling Using Deep Learning and Its Application on X-Ray Fluorescence Image Reconstruction}},
url = {https://ieeexplore.ieee.org/document/8930037/},
volume = {22},
year = {2020}
}
Downloads: 0
{"_id":"jGEzQ9wHjNeRk8uAE","bibbaseid":"dai-chopp-pouyet-cossairt-walton-katsaggelos-adaptiveimagesamplingusingdeeplearninganditsapplicationonxrayfluorescenceimagereconstruction-2020","author_short":["Dai, Q.","Chopp, H.","Pouyet, E.","Cossairt, O.","Walton, M.","Katsaggelos, A. K."],"bibdata":{"bibtype":"article","type":"article","abstract":"This paper presents an adaptive image sampling algorithm based on Deep Learning (DL). It consists of an adaptive sampling mask generation network which is jointly trained with an image inpainting network. The sampling rate is controlled by the mask generation network, and a binarization strategy is investigated to make the sampling mask binary. In addition to the image sampling and reconstruction process, we show how it can be extended and used to speed up raster scanning such as the X-Ray fluorescence (XRF) image scanning process. Recently XRF laboratory-based systems have evolved into lightweight and portable instruments thanks to technological advancements in both X-Ray generation and detection. However, the scanning time of an XRF image is usually long due to the long exposure requirements (e.g., 100 $μ$ s-1 ms per point). We propose an XRF image inpainting approach to address the long scanning times, thus speeding up the scanning process, while being able to reconstruct a high quality XRF image. The proposed adaptive image sampling algorithm is applied to the RGB image of the scanning target to generate the sampling mask. The XRF scanner is then driven according to the sampling mask to scan a subset of the total image pixels. Finally, we inpaint the scanned XRF image by fusing the RGB image to reconstruct the full scan XRF image. The experiments show that the proposed adaptive sampling algorithm is able to effectively sample the image and achieve a better reconstruction accuracy than that of existing methods.","archiveprefix":"arXiv","arxivid":"1812.10836","author":[{"propositions":[],"lastnames":["Dai"],"firstnames":["Qiqin"],"suffixes":[]},{"propositions":[],"lastnames":["Chopp"],"firstnames":["Henry"],"suffixes":[]},{"propositions":[],"lastnames":["Pouyet"],"firstnames":["Emeline"],"suffixes":[]},{"propositions":[],"lastnames":["Cossairt"],"firstnames":["Oliver"],"suffixes":[]},{"propositions":[],"lastnames":["Walton"],"firstnames":["Marc"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]}],"doi":"10.1109/TMM.2019.2958760","eprint":"1812.10836","issn":"1520-9210","journal":"IEEE Transactions on Multimedia","keywords":"Adaptive sampling,X-Ray fluorescence,convolutional neural network,inpainting","month":"oct","number":"10","pages":"2564–2578","title":"Adaptive Image Sampling Using Deep Learning and Its Application on X-Ray Fluorescence Image Reconstruction","url":"https://ieeexplore.ieee.org/document/8930037/","volume":"22","year":"2020","bibtex":"@article{Qiqin2019,\nabstract = {This paper presents an adaptive image sampling algorithm based on Deep Learning (DL). It consists of an adaptive sampling mask generation network which is jointly trained with an image inpainting network. The sampling rate is controlled by the mask generation network, and a binarization strategy is investigated to make the sampling mask binary. In addition to the image sampling and reconstruction process, we show how it can be extended and used to speed up raster scanning such as the X-Ray fluorescence (XRF) image scanning process. Recently XRF laboratory-based systems have evolved into lightweight and portable instruments thanks to technological advancements in both X-Ray generation and detection. However, the scanning time of an XRF image is usually long due to the long exposure requirements (e.g., 100\\; $\\mu$ s-1 ms per point). We propose an XRF image inpainting approach to address the long scanning times, thus speeding up the scanning process, while being able to reconstruct a high quality XRF image. The proposed adaptive image sampling algorithm is applied to the RGB image of the scanning target to generate the sampling mask. The XRF scanner is then driven according to the sampling mask to scan a subset of the total image pixels. Finally, we inpaint the scanned XRF image by fusing the RGB image to reconstruct the full scan XRF image. The experiments show that the proposed adaptive sampling algorithm is able to effectively sample the image and achieve a better reconstruction accuracy than that of existing methods.},\narchivePrefix = {arXiv},\narxivId = {1812.10836},\nauthor = {Dai, Qiqin and Chopp, Henry and Pouyet, Emeline and Cossairt, Oliver and Walton, Marc and Katsaggelos, Aggelos K.},\ndoi = {10.1109/TMM.2019.2958760},\neprint = {1812.10836},\nissn = {1520-9210},\njournal = {IEEE Transactions on Multimedia},\nkeywords = {Adaptive sampling,X-Ray fluorescence,convolutional neural network,inpainting},\nmonth = {oct},\nnumber = {10},\npages = {2564--2578},\ntitle = {{Adaptive Image Sampling Using Deep Learning and Its Application on X-Ray Fluorescence Image Reconstruction}},\nurl = {https://ieeexplore.ieee.org/document/8930037/},\nvolume = {22},\nyear = {2020}\n}\n","author_short":["Dai, Q.","Chopp, H.","Pouyet, E.","Cossairt, O.","Walton, M.","Katsaggelos, A. K."],"key":"Qiqin2019","id":"Qiqin2019","bibbaseid":"dai-chopp-pouyet-cossairt-walton-katsaggelos-adaptiveimagesamplingusingdeeplearninganditsapplicationonxrayfluorescenceimagereconstruction-2020","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/document/8930037/"},"keyword":["Adaptive sampling","X-Ray fluorescence","convolutional neural network","inpainting"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","E6Bth2QB5BYjBMZE7","nbnEjsN7MJhurAK9x","PNQZj6FjzoxxJk4Yi","7FpDWDGJ4KgpDiGfB","bod9ms4MQJHuJgPpp","QR9t5P2cLdJuzhfzK","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":["adaptive sampling","x-ray fluorescence","convolutional neural network","inpainting"],"search_terms":["adaptive","image","sampling","using","deep","learning","application","ray","fluorescence","image","reconstruction","dai","chopp","pouyet","cossairt","walton","katsaggelos"],"title":"Adaptive Image Sampling Using Deep Learning and Its Application on X-Ray Fluorescence Image Reconstruction","year":2020}