Exploring deep learning image super-resolution for iris recognition. Ribeiro, E., Uhl, A., Alonso-Fernandez, F., & Farrugia, R. A. In 2017 25th European Signal Processing Conference (EUSIPCO), pages 2176-2180, Aug, 2017.
Paper doi abstract bibtex In this work we test the ability of deep learning methods to provide an end-to-end mapping between low and high resolution images applying it to the iris recognition problem. Here, we propose the use of two deep learning single-image super-resolution approaches: Stacked Auto-Encoders (SAE) and Convolutional Neural Networks (CNN) with the most possible lightweight structure to achieve fast speed, preserve local information and reduce artifacts at the same time. We validate the methods with a database of 1.872 near-infrared iris images with quality assessment and recognition experiments showing the superiority of deep learning approaches over the compared algorithms.
@InProceedings{8081595,
author = {E. Ribeiro and A. Uhl and F. Alonso-Fernandez and R. A. Farrugia},
booktitle = {2017 25th European Signal Processing Conference (EUSIPCO)},
title = {Exploring deep learning image super-resolution for iris recognition},
year = {2017},
pages = {2176-2180},
abstract = {In this work we test the ability of deep learning methods to provide an end-to-end mapping between low and high resolution images applying it to the iris recognition problem. Here, we propose the use of two deep learning single-image super-resolution approaches: Stacked Auto-Encoders (SAE) and Convolutional Neural Networks (CNN) with the most possible lightweight structure to achieve fast speed, preserve local information and reduce artifacts at the same time. We validate the methods with a database of 1.872 near-infrared iris images with quality assessment and recognition experiments showing the superiority of deep learning approaches over the compared algorithms.},
keywords = {feature extraction;image resolution;iris recognition;learning (artificial intelligence);neural nets;iris recognition problem;Stacked Auto-Encoders;Convolutional Neural Networks;quality assessment;deep learning methods;end-to-end mapping;low resolution images;high resolution images;lightweight structure;deep learning single-image super-resolution;CNN;SAE;Image resolution;Iris recognition;Training;Databases;Interpolation;Machine learning;Image reconstruction},
doi = {10.23919/EUSIPCO.2017.8081595},
issn = {2076-1465},
month = {Aug},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2017/papers/1570346942.pdf},
}
Downloads: 0
{"_id":"XKEm7enufs9pMRc2K","bibbaseid":"ribeiro-uhl-alonsofernandez-farrugia-exploringdeeplearningimagesuperresolutionforirisrecognition-2017","authorIDs":[],"author_short":["Ribeiro, E.","Uhl, A.","Alonso-Fernandez, F.","Farrugia, R. A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["E."],"propositions":[],"lastnames":["Ribeiro"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Uhl"],"suffixes":[]},{"firstnames":["F."],"propositions":[],"lastnames":["Alonso-Fernandez"],"suffixes":[]},{"firstnames":["R.","A."],"propositions":[],"lastnames":["Farrugia"],"suffixes":[]}],"booktitle":"2017 25th European Signal Processing Conference (EUSIPCO)","title":"Exploring deep learning image super-resolution for iris recognition","year":"2017","pages":"2176-2180","abstract":"In this work we test the ability of deep learning methods to provide an end-to-end mapping between low and high resolution images applying it to the iris recognition problem. Here, we propose the use of two deep learning single-image super-resolution approaches: Stacked Auto-Encoders (SAE) and Convolutional Neural Networks (CNN) with the most possible lightweight structure to achieve fast speed, preserve local information and reduce artifacts at the same time. We validate the methods with a database of 1.872 near-infrared iris images with quality assessment and recognition experiments showing the superiority of deep learning approaches over the compared algorithms.","keywords":"feature extraction;image resolution;iris recognition;learning (artificial intelligence);neural nets;iris recognition problem;Stacked Auto-Encoders;Convolutional Neural Networks;quality assessment;deep learning methods;end-to-end mapping;low resolution images;high resolution images;lightweight structure;deep learning single-image super-resolution;CNN;SAE;Image resolution;Iris recognition;Training;Databases;Interpolation;Machine learning;Image reconstruction","doi":"10.23919/EUSIPCO.2017.8081595","issn":"2076-1465","month":"Aug","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2017/papers/1570346942.pdf","bibtex":"@InProceedings{8081595,\n author = {E. Ribeiro and A. Uhl and F. Alonso-Fernandez and R. A. Farrugia},\n booktitle = {2017 25th European Signal Processing Conference (EUSIPCO)},\n title = {Exploring deep learning image super-resolution for iris recognition},\n year = {2017},\n pages = {2176-2180},\n abstract = {In this work we test the ability of deep learning methods to provide an end-to-end mapping between low and high resolution images applying it to the iris recognition problem. Here, we propose the use of two deep learning single-image super-resolution approaches: Stacked Auto-Encoders (SAE) and Convolutional Neural Networks (CNN) with the most possible lightweight structure to achieve fast speed, preserve local information and reduce artifacts at the same time. We validate the methods with a database of 1.872 near-infrared iris images with quality assessment and recognition experiments showing the superiority of deep learning approaches over the compared algorithms.},\n keywords = {feature extraction;image resolution;iris recognition;learning (artificial intelligence);neural nets;iris recognition problem;Stacked Auto-Encoders;Convolutional Neural Networks;quality assessment;deep learning methods;end-to-end mapping;low resolution images;high resolution images;lightweight structure;deep learning single-image super-resolution;CNN;SAE;Image resolution;Iris recognition;Training;Databases;Interpolation;Machine learning;Image reconstruction},\n doi = {10.23919/EUSIPCO.2017.8081595},\n issn = {2076-1465},\n month = {Aug},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2017/papers/1570346942.pdf},\n}\n\n","author_short":["Ribeiro, E.","Uhl, A.","Alonso-Fernandez, F.","Farrugia, R. A."],"key":"8081595","id":"8081595","bibbaseid":"ribeiro-uhl-alonsofernandez-farrugia-exploringdeeplearningimagesuperresolutionforirisrecognition-2017","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2017/papers/1570346942.pdf"},"keyword":["feature extraction;image resolution;iris recognition;learning (artificial intelligence);neural nets;iris recognition problem;Stacked Auto-Encoders;Convolutional Neural Networks;quality assessment;deep learning methods;end-to-end mapping;low resolution images;high resolution images;lightweight structure;deep learning single-image super-resolution;CNN;SAE;Image resolution;Iris recognition;Training;Databases;Interpolation;Machine learning;Image reconstruction"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2017url.bib","creationDate":"2021-02-13T16:38:25.747Z","downloads":0,"keywords":["feature extraction;image resolution;iris recognition;learning (artificial intelligence);neural nets;iris recognition problem;stacked auto-encoders;convolutional neural networks;quality assessment;deep learning methods;end-to-end mapping;low resolution images;high resolution images;lightweight structure;deep learning single-image super-resolution;cnn;sae;image resolution;iris recognition;training;databases;interpolation;machine learning;image reconstruction"],"search_terms":["exploring","deep","learning","image","super","resolution","iris","recognition","ribeiro","uhl","alonso-fernandez","farrugia"],"title":"Exploring deep learning image super-resolution for iris recognition","year":2017,"dataSources":["2MNbFYjMYTD6z7ExY","uP2aT6Qs8sfZJ6s8b"]}