scholarly journals Things are Looking up: Differential Decline in Face Recognition following Pitch and Yaw Rotation

Perception ◽  
10.1068/p5637 ◽  
2007 ◽  
Vol 36 (9) ◽  
pp. 1334-1352 ◽  
Author(s):  
Simone K Favelle ◽  
Stephen Palmisano ◽  
Ryan T Maloney

Previous research into the effects of viewpoint change on face recognition has typically dealt with rotations around the head's vertical axis (yaw). Another common, although less studied, source of viewpoint variation in faces is rotation around the head's horizontal pitch axis (pitch). In the current study we used both a sequential matching task and an old/new recognition task to examine the effect of viewpoint change following rotation about both pitch and yaw axes on human face recognition. The results of both tasks showed that recognition performance was better for faces rotated about yaw compared to pitch. Further, recognition performance for faces rotated upwards on the pitch axis was better than for faces rotated downwards. Thus, equivalent angular rotations about pitch and yaw do not produce equivalent viewpoint-dependent declines in recognition performance.


1992 ◽  
pp. 1595-1598 ◽  
Author(s):  
Hazem Bouattour ◽  
Francoise Fogelman Soulié ◽  
Emmanuel Viennet


Author(s):  
WEI-LI FANG ◽  
YING-KUEI YANG ◽  
JUNG-KUEI PAN

Several 2DPCA-based face recognition algorithms have been proposed hoping to achieve the goal of improving recognition rate while mostly at the expense of computation cost. In this paper, an approach named SI2DPCA is proposed to not only reduce the computation cost but also increase recognition performance at the same time. The approach divides a whole face image into smaller sub-images to increase the weight of features for better feature extraction. Meanwhile, the computation cost that mainly comes from the heavy and complicated operations against matrices is reduced due to the smaller size of sub-images. The reduced amount of computation has been analyzed and the integrity of sub-images has been discussed thoroughly in the paper. The experiments have been conducted to make comparisons among several better-known approaches and SI2DPCA. The experimental results have demonstrated that the proposed approach works well on reaching the goals of reducing computation cost and improving recognition performance simultaneously.



Author(s):  
Marcus Butavicius ◽  
Chloë Mount ◽  
Veneta MacLeod ◽  
Robyn Vast ◽  
Ian Graves ◽  
...  


Author(s):  
Rachmat Muwardi ◽  
Huangyao Qin ◽  
Hongmin Gao ◽  
Harun Usman Ghifarsyam ◽  
Muhammad Hafizd Ibnu Hajar ◽  
...  






Author(s):  
Yuri Lipin ◽  
Sergey Storozhev ◽  
Ian Iakubchik


Sign in / Sign up

Export Citation Format

Share Document