Patient identification using a near-infrared laser scanner

Manit, Jirapong; Bremer, Christina; Schweikard, Achim; Ernst, Floris

doi:10.1117/12.2254963

Cited by 1 publication

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2017, we proposed an algorithm for verifying a patient's identity in cranial stereotactic radiotherapy by using a near‐infrared (NIR) laser‐based head tracking system [1]. We conjectured that the combined feature of forehead morphology and the underlying tissue thickness of an individual is different from the others, and the point cloud matching of the data acquired from the same person should result in the minimum error.…”

Section: Introductionmentioning

confidence: 99%

“…Although the performance of the algorithm shown in [1] was promising in terms of verification accuracy, there were still several drawbacks which are hindrances to real‐world applications. First, performing one‐to‐one matching against the entire references let the algorithm complexity be

O false(n false)

, and also employing the ICP registration algorithm to solve such tasks was computationally expensive.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Human forehead recognition: a novel biometric modality based on near‐infrared laser backscattering feature image using deep transfer learning

et al. 2019

Self Cite

View full text Add to dashboard Cite

Human recognition systems are an essential tool for identity verification. Though various parts of the human body have been widely used as input data for decades, developing new biometric technology is still necessary to enhance the security system complexity. This article presents a novel biometric modality based on forehead feature images acquired from a specially designed near-infrared laser scanning system. The authors selected state-of-the-art deep convolutional neural networks (CNN), including VGGNet, ResNet, and Inception-v3, to demonstrate the human forehead recognition task. Though large-scale training data is generally required for learning a promising CNN model, they showed the feasibility to transfer the feature representation knowledge of the networks that were pre-trained on the data from a different domain and fine-tuned the target network on the limited dataset of forehead feature images. This transfer learning approach establishes the usability of human forehead recognition and allows us to implement this biometric modality for real-world application.

show abstract

Section: Introductionmentioning

confidence: 99%