A Fast Iris Segmentation Algorithm based on Faster R-CNN
碩士 === 國立中央大學 === 資訊工程學系 === 106 === Iris segmentation is a critical step in the entire iris recognition procedure. Most of the state-of-the-art iris segmentation algorithms are based on edge information. However, a large number of noisy edge points created by a normal edge-based detector in an imag...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2018
|
Online Access: | http://ndltd.ncl.edu.tw/handle/9crz9c |
id |
ndltd-TW-106NCU05392119 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-106NCU053921192019-11-28T05:22:16Z http://ndltd.ncl.edu.tw/handle/9crz9c A Fast Iris Segmentation Algorithm based on Faster R-CNN 一種基於Faster R-CNN的快速虹膜切割演算法 Po-Jen Huang 黃柏仁 碩士 國立中央大學 資訊工程學系 106 Iris segmentation is a critical step in the entire iris recognition procedure. Most of the state-of-the-art iris segmentation algorithms are based on edge information. However, a large number of noisy edge points created by a normal edge-based detector in an image with specular reflection or other obstacles will mislead the pupillary boundary and limbus boundary localization. In this paper, we present a combination method of learning-based and edge-based algorithms for iris segmentation. A well-designed Faster R-CNN with only six layers is built to locate and classify the eye. With the bounding box found by Faster R-CNN, the pupillary region is located using a Gaussian mixture model. Then, the circular boundary of the pupillary region is fit according to five key boundary points. The enhanced version of MIGREP and a boundary point selection algorithm are used to find the boundary points of limbus, and the circular boundary of limbus is constructed using these bounding points. Experimental results showed that the proposed iris segmentation method achieved 95.49% accuracy on the challenging CASIA-Iris-Thousand database. Yung-Hui Li 栗永徽 2018 學位論文 ; thesis 37 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中央大學 === 資訊工程學系 === 106 === Iris segmentation is a critical step in the entire iris recognition procedure. Most of the state-of-the-art iris segmentation algorithms are based on edge information. However, a large number of noisy edge points created by a normal edge-based detector in an image with specular reflection or other obstacles will mislead the pupillary boundary and limbus boundary localization. In this paper, we present a combination method of learning-based and edge-based algorithms for iris segmentation. A well-designed Faster R-CNN with only six layers is built to locate and classify the eye. With the bounding box found by Faster R-CNN, the pupillary region is located using a Gaussian mixture model. Then, the circular boundary of the pupillary region is fit according to five key boundary points. The enhanced version of MIGREP and a boundary point selection algorithm are used to find the boundary points of limbus, and the circular boundary of limbus is constructed using these bounding points. Experimental results showed that the proposed iris segmentation method achieved 95.49% accuracy on the challenging CASIA-Iris-Thousand database.
|
author2 |
Yung-Hui Li |
author_facet |
Yung-Hui Li Po-Jen Huang 黃柏仁 |
author |
Po-Jen Huang 黃柏仁 |
spellingShingle |
Po-Jen Huang 黃柏仁 A Fast Iris Segmentation Algorithm based on Faster R-CNN |
author_sort |
Po-Jen Huang |
title |
A Fast Iris Segmentation Algorithm based on Faster R-CNN |
title_short |
A Fast Iris Segmentation Algorithm based on Faster R-CNN |
title_full |
A Fast Iris Segmentation Algorithm based on Faster R-CNN |
title_fullStr |
A Fast Iris Segmentation Algorithm based on Faster R-CNN |
title_full_unstemmed |
A Fast Iris Segmentation Algorithm based on Faster R-CNN |
title_sort |
fast iris segmentation algorithm based on faster r-cnn |
publishDate |
2018 |
url |
http://ndltd.ncl.edu.tw/handle/9crz9c |
work_keys_str_mv |
AT pojenhuang afastirissegmentationalgorithmbasedonfasterrcnn AT huángbǎirén afastirissegmentationalgorithmbasedonfasterrcnn AT pojenhuang yīzhǒngjīyúfasterrcnndekuàisùhóngmóqiègēyǎnsuànfǎ AT huángbǎirén yīzhǒngjīyúfasterrcnndekuàisùhóngmóqiègēyǎnsuànfǎ AT pojenhuang fastirissegmentationalgorithmbasedonfasterrcnn AT huángbǎirén fastirissegmentationalgorithmbasedonfasterrcnn |
_version_ |
1719297848629002240 |