Lightweight YOLOv5s Human Ear Recognition Based on MobileNetV3 and Ghostnet

Lei, Yanmin; Pan, Dong; Feng, Zhibin; Qian, Junru

doi:10.3390/app13116667

Cited by 4 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…YOLOv5s-MG [17] is a lightweight YOLOv5s human ear recognition method based on MobileNetV3 and the idea of the Ghostnet. In this method, the backbone network of the YOLOv5s was replaced by the MobileNetV3 lightweight network and the C3 module and Conv module in the YOLOv5s neck network are replaced by the C3Ghost module and GhostConv module, which realizes the lightweight of feature extraction and feature fusion of YOLOv5s simultaneously.…”

Section: Yolov5s-mgmentioning

confidence: 99%

“…In order to train and test the model of the YOLOv5s-MG-CBAM-F method proposed in this paper, three different human ear datasets, namely, CCU-DE, USTB and EarVN1.0, were used. In order to facilitate the comparison of performance between different methods, the selection of three datasets is the same as that in Reference [17]. There are 3274, 7700 and 3201 pictures in the CCU-DE, USTB and EarVN1.0 human ear datasets, respectively.…”

Section: Human Ear Datasetsmentioning

confidence: 99%

“…The main parameters used in the model training are the following: the initial learning rate is 0.01, batch size is 16, weight attenuation coefficient is 0.0005, momentum coefficient is 0.937, learning rate reduction coefficient is 0.2 and optimizer is SGD with the momentum. The hardware, software and parameters of the experiment in this paper are the same as those in Reference [17].…”

Section: Experimental Settingmentioning

confidence: 99%

“…In order to compare the performance between the improved YOLOv5s-MG-CBAM and YOLOv5s-MG-CBAM-F methods and the YOLOv5s-MG [17] method, four evaluation indexes of mAP, model size/MB, GFLOPs/G and params/M are used [17].…”

Section: Evaluation Indicatorsmentioning

confidence: 99%

“…Common lightweight networks include MobileNet series, Shufflenet series and Ghostnet. In 2023, Lei, Y. et al [17] proposed the YOLOv5s-MG method which has better real-time performance than YOLOv5s-V3, YOLOv5s-V2 and YOLOv5s-G. However, while improving real-time performance, it may also reduce the accuracy of human ear recognition on some human ear datasets.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Lightweight Human Ear Recognition Based on Attention Mechanism and Feature Fusion

et al. 2023

Self Cite

View full text Add to dashboard Cite

With the development of deep learning technology, more and more researchers are interested in ear recognition. Human ear recognition is a biometric identification technology based on human ear feature information and it is often used for authentication and intelligent monitoring field, etc. In order to make ear recognition better applied to practical application, real time and accuracy have always been very important and challenging topics. Therefore, focusing on the problem that the mAP@0.5 value of the YOLOv5s-MG method is lower than that of the YOLOv5s method on the EarVN1.0 human ear dataset with low resolution, small target, rotation, brightness change, earrings, glasses and other occlusion, a lightweight ear recognition method is proposed based on an attention mechanism and feature fusion. This method mainly includes the following several steps: First, the CBAM attention mechanism is added to the connection between the backbone network and the neck network of the lightweight human ear recognition method YOLOv5s-MG, and the YOLOv5s-MG-CBAM human ear recognition network is constructed, which can improve the accuracy of the method. Second, the SPPF layer and cross-regional feature fusion are added to construct the YOLOv5s-MG-CBAM-F human ear recognition method, which further improves the accuracy. Three distinctive human ear datasets, namely, CCU-DE, USTB and EarVN1.0, are used to evaluate the proposed method. Through the experimental comparison of seven methods including YOLOv5s-MG-CBAM-F, YOLOv5s-MG-SE-F, YOLOv5s-MG-CA-F, YOLOv5s-MG-ECA-F, YOLOv5s, YOLOv7 and YOLOv5s-MG on the EarVN1.0 human ear dataset, it is found that the human ear recognition rate of YOLOv5s-MG-CBAM-F method is the highest. The mAP@0.5 value of the proposed YOLOv5s-MG-CBAM-F method on the EarVN1.0 ear dataset is 91.9%, which is 6.4% higher than that of the YOLOv5s-MG method and 3.7% higher than that of the YOLOv5s method. The params, GFLOPS, model size and the inference time per image of YOLOv5s-MG-CBAM-F method on the EarVN1.0 human ear dataset are 5.2 M, 8.3 G, 10.9 MB and 16.4 ms, respectively, which are higher than the same parameters of the YOLOv5s-MG method, but less than the same parameters of YOLOv5s method. The quantitative results show that the proposed method can improve the ear recognition rate while satisfying the real-time performance and it is especially suitable for applications where high ear recognition rates are required.

show abstract

Section: Yolov5s-mgmentioning

confidence: 99%

Section: Human Ear Datasetsmentioning

confidence: 99%

Section: Experimental Settingmentioning

confidence: 99%

Section: Evaluation Indicatorsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Lightweight Human Ear Recognition Based on Attention Mechanism and Feature Fusion

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

A supervised approach to automatic density and foreign-object detection in particleboard paving quality control

Yan,

Yang,

Zhang

et al. 2024

Wood Material Science & Engineering

View full text Add to dashboard Cite

CT scan pancreatic cancer segmentation and classification using deep learning and the tunicate swarm algorithm

Gandikota,

S.,

2023

PLoS ONE

View full text Add to dashboard Cite

Pancreatic cancer (PC) is a very lethal disease with a low survival rate, making timely and accurate diagnoses critical for successful treatment. PC classification in computed tomography (CT) scans is a vital task that aims to accurately discriminate between tumorous and non-tumorous pancreatic tissues. CT images provide detailed cross-sectional images of the pancreas, which allows oncologists and radiologists to analyse the characteristics and morphology of the tissue. Machine learning (ML) approaches, together with deep learning (DL) algorithms, are commonly explored to improve and automate the performance of PC classification in CT scans. DL algorithms, particularly convolutional neural networks (CNNs), are broadly utilized for medical image analysis tasks, involving segmentation and classification. This study explores the design of a tunicate swarm algorithm with deep learning-based pancreatic cancer segmentation and classification (TSADL-PCSC) technique on CT scans. The purpose of the TSADL-PCSC technique is to design an effectual and accurate model to improve the diagnostic performance of PC. To accomplish this, the TSADL-PCSC technique employs a W-Net segmentation approach to define the affected region on the CT scans. In addition, the TSADL-PCSC technique utilizes the GhostNet feature extractor to create a group of feature vectors. For PC classification, the deep echo state network (DESN) model is applied in this study. Finally, the hyperparameter tuning of the DESN approach occurs utilizing the TSA which assists in attaining improved classification performance. The experimental outcome of the TSADL-PCSC method was tested on a benchmark CT scan database. The obtained outcomes highlighted the significance of the TSADL-PCSC technique over other approaches to PC classification.

show abstract

Lightweight YOLOv5s Human Ear Recognition Based on MobileNetV3 and Ghostnet

Cited by 4 publications

References 22 publications

Lightweight Human Ear Recognition Based on Attention Mechanism and Feature Fusion

Lightweight Human Ear Recognition Based on Attention Mechanism and Feature Fusion

A supervised approach to automatic density and foreign-object detection in particleboard paving quality control

CT scan pancreatic cancer segmentation and classification using deep learning and the tunicate swarm algorithm

Contact Info

Product

Resources

About