发明名称 |
Depth-aware blur kernel estimation method for iris deblurring |
摘要 |
Estimating a blur kernel distribution for visual iris recognition includes determining a first mathematical relationship between an in-focus position of a camera lens and a distance between the lens and an iris whose image is to be captured by the lens. A second mathematical relationship between the in-focus position of the lens and a standard deviation defining a Gaussian blur kernel distribution is estimated. The first mathematical relationship is used to ascertain a desired focus position of the lens based upon the actual position of the living being's eye at the point in time. The second mathematical relationship is used to calculate a standard deviation defining a Gaussian blur kernel distribution. The produced image is digitally unblurred by using the blur kernel distribution defined by the calculated standard deviation. |
申请公布号 |
US9313460(B2) |
申请公布日期 |
2016.04.12 |
申请号 |
US201213525511 |
申请日期 |
2012.06.18 |
申请人 |
Robert Bosch GmbH |
发明人 |
Ren Liu;Huang Xinyu;Yang Ruigang |
分类号 |
G06K9/00;H04N7/18;G06T5/00 |
主分类号 |
G06K9/00 |
代理机构 |
Maginot, Moore & Beck LLP |
代理人 |
Maginot, Moore & Beck LLP |
主权项 |
1. A method of capturing an image of an iris, said method comprising the steps of:
using a camera lens with a focus position to produce an image of a living being's eye; sensing an actual position of the living being's eye at a point in time at which the camera lens produced the image of the living being's eye; and determining a Gaussian blur kernel distribution based upon:
the focus position of the camera lens; andthe actual position of the living being's eye at the point in time; and using the blur kernel distribution to digitally unblur the produced image. |
地址 |
Stuttgart DE |