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

Manit, Jirapong; Preuße, Luise; Schweikard, Achim; Ernst, Floris

doi:10.1049/iet-bmt.2019.0015

Cited by 6 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three VGG models, 53 VGGNet 2020 Jirapong et al 86 Self-created Implementation in biometric modality Human forehead recognition many image classification problems are still using this model. Nonetheless, small and portable models are always preferable, such as SqueezeNet, 61 GoogLeNet, 47 etc.…”

Section: Vgg (Visual Geometric Group) Net: Vgg16 and Vgg19mentioning

confidence: 99%

Convolutional neural network and its pretrained models for image classification and object detection: A survey

Jena

Nayak

Saxena

2021

Concurrency and Computation

View full text Add to dashboard Cite

At present, in the age of computers and automation of services, deep learning (DL) technology, mainly the subset of machine learning (ML) and artificial intelligence (AI), is expressively used in innumerable domains of computer vision such as data analysis, image recognition, classification, natural language processing, and many more. It has become the foremost choice of researchers as of its effectiveness in producing decent results. This paper presents detailed and analytical literature starting from the very elementary level to the recent trends of this trending technology while focusing on the most used DL model, that is, convolutional neural network and its pretrained models for image classification and object detection. It also reviews diverse existing current literature based on this. Further, a brief introduction of AI, ML, and DL has also been presented, making the foundation for the readers. As pretrained models continuously give an upper edge to DL over ML and other technologies, 23 most popular pretrained models with their architectural diagrams have also been presented. This paper aims to summarize and analyze all the concepts used to formulate DL and its models. Also, we have emphasized more on the GoogleNet models and the entire Inception modules in detail. Finally, the fascinating applications and discussion on integral components of DL have been presented. This paper will definitely draw the attention of the students and researchers working in the area of DL and its models.

show abstract

Section: Vgg (Visual Geometric Group) Net: Vgg16 and Vgg19mentioning

confidence: 99%

Convolutional neural network and its pretrained models for image classification and object detection: A survey

Jena

Nayak

Saxena

2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…CNN is a deep learning method widely used for target classification, target detection, and target recognition [22][23][24]. In recent years, CNN has been successfully utilized for the LIBS quantification due to its outstanding capability of feature extraction [19,25].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Quantitative analysis modeling for the ChemCam spectral data based on laser-induced breakdown spectroscopy using convolutional neural network

Cao¹,

Zhang²,

Wu³

et al. 2020

Plasma Sci. Technol.

View full text Add to dashboard Cite

Laser-induced breakdown spectroscopy (LIBS) has been applied to many fields for the quantitative analysis of diverse materials. Improving the prediction accuracy of LIBS regression models is still of great significance for the Mars exploration in the near future. In this study, we explored the quantitative analysis of LIBS for the one-dimensional ChemCam (an instrument containing a LIBS spectrometer and a Remote Micro-Imager) spectral data whose spectra are produced by the ChemCam team using LIBS under the Mars-like atmospheric conditions. We constructed a convolutional neural network (CNN) regression model with unified parameters for all oxides, which is efficient and concise. CNN that has the excellent capability of feature extraction can effectively overcome the chemical matrix effects that impede the prediction accuracy of regression models. Firstly, we explored the effects of four activation functions on the performance of the CNN model. The results show that the CNN model with the hyperbolic tangent (tanh) function outperforms the CNN models with the other activation functions (the rectified linear unit function, the linear function and the Sigmoid function). Secondly, we compared the performance among the CNN models using different optimization methods. The CNN model with the stochastic gradient descent optimization and the initial learning rate=0.0005 achieves satisfactory performance compared to the other CNN models. Finally, we compared the performance of the CNN model, the model based on support vector regression (SVR) and the model based on partial least square regression (PLSR). The results exhibit the CNN model is superior to the SVR model and the PLSR model for all oxides. Based on the above analysis, we conclude the CNN regression model can effectively improve the prediction accuracy of LIBS.

show abstract

“…[ 14 ] We, therefore, aim at the forehead region and design skin electrodes for multimodal sensing of neural signals. [ 15 ] Ultra‐high conductivity and skin conformability are two prerequisites for high‐fidelity EEG recording, where they contribute to high electron transport ability with low motion artifact. [ 16 ] Metal electrodes are not allowed in the MRI machine.…”

Section: Introductionmentioning

confidence: 99%

An Ultra‐Thin MXene Film for Multimodal Sensing of Neuroelectrical Signals with Artifacts Removal

Song

Jang

et al. 2023

Advanced Materials

View full text Add to dashboard Cite

Neuroelectrical signals transmitted onto the skin tend to decay to an extremely weak level, making them highly susceptible to interference from the environment and body movement. Meanwhile, for comprehensively understanding cognitive nerve conduction, multimodal sensing of neural signals, such as magnetic resonance imaging (MRI) and functional near‐infrared spectroscopy (fNIRS), is highly required. Previous metal or polymer conductors cannot either provide a seamless on‐skin feature for accurate sensing of neuroelectrical signals or be compatible with multimodal imaging techniques without opto‐ and magnet‐ artifacts. Herein, we report a ∼ 20 nm thick MXene film that is able to simultaneously detect electrophysiological signals and perform imaging by MRI and fNIRS with high fidelity. The ultrathin film is made of crosslinked Ti3C2Tx film via poly (3,4‐ethylene dioxythiophene): polystyrene sulfonate (PEDOT:PSS), showing a record high electroconductivity and transparency combination (11000 S/cm @89%). Among them, PEDOT:PSS not only plays a cross‐linking role to stabilize MXene film but also shortens the interlayer distance for effective charge transfer and high transparency. Thus, it can achieve a low interfacial impedance with skin or neural surfaces for accurate recording of electrophysiological signals with low motion artifacts. Besides, the high transparency originating from the ultrathin feature leads to good compatibility with fNIRS and MRI without optical and magnetic artifacts, enabling multimodal cognitive neural monitoring during prolonged use.This article is protected by copyright. All rights reserved

show abstract

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

Cited by 6 publications

References 22 publications

Convolutional neural network and its pretrained models for image classification and object detection: A survey

Convolutional neural network and its pretrained models for image classification and object detection: A survey

Quantitative analysis modeling for the ChemCam spectral data based on laser-induced breakdown spectroscopy using convolutional neural network

An Ultra‐Thin MXene Film for Multimodal Sensing of Neuroelectrical Signals with Artifacts Removal

Contact Info

Product

Resources

About