Eye feature points detection by CNN with strict geometric constraint

Meng, Chunning; Zhao, Xuepeng; Feng, Mingyue; Chang, Shengjiang

doi:10.1117/12.2245167

Cited by 1 publication

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the cascade structure leads to a decrease in the processing speed, and the geometric relationships between the feature points are not used. Geometric relationships are applied in CNN by Meng et al [20], but further researches are not implemented and detection accuracy can further be improved.…”

Section: Introductionmentioning

confidence: 99%

Eye feature point detection based on single convolutional neural network

Zhao

Meng²,

Feng³

et al. 2018

IET Computer Vision

Self Cite

View full text Add to dashboard Cite

Feature point detection based on convolutional neural network (CNN) has been studied widely. The effective approaches for improving detection accuracy are building a deeper network or using a multi-network cascade structure. However, some potential capacity of CNN has not been excavated. In this study, the authors mainly analyse several factors influencing CNN performance from two aspects: (i) the position relationships between feature points and (ii) the normalisation methods of coordinates. Whether the network can learn the position relationships is also studied. For extracting the deep features of images, a network containing three convolution layers is constructed. The specific geometric relationship constraints are applied during calibration to maximise the capability of the CNN for learning the position relationship between feature points. Considering that different feature points only appear in various local regions of an image, local normalisation is proposed, which increases the mapping scope of the feature points and decreases the mapping error. The experimental results prove that the specific position relationship and local normalisation obviously improve the feature point detection based on CNN. At the detection error of 5%, the average detection accuracy of eyelid feature points is improved by 7.1% and single-point detection receives a high accuracy of 97.96%.

show abstract

Section: Introductionmentioning

confidence: 99%