Human Recognition Based On Ear Shape Images Using PCA-Wavelets and Different Classification Methods

Mayya, Ali Mahmoud; Saii, Mariam

doi:10.15761/mdde.1000103

Cited by 4 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Ali et al [17] proposed a novel methodology for human recognition through the use of ear images. The approach involved two primary stages, namely ear segmentation and ear recognition.…”

Section: Handcrafted Featuresmentioning

confidence: 99%

Human Recognition Using Ear Features: A Review

Rajab,

Hashim

2023

J. Al-Qadisiyah Comp. Sci. Math.

View full text Add to dashboard Cite

Over the past few years, ear biometrics has attracted a lot of attention. It is a trusted biometric for the identification and recognition of humans due to its consistent shape and rich texture variation. The ear presents an attractive solution since it is visible, ear images are easily captured, and the ear structure remains relatively stable over time. In this paper, a comprehensive review of prior research was conducted to establish the efficacy of utilizing ear features for individual identification through the employment of both manually-crafted features and deep-learning approaches. The objective of this model is to present the accuracy rate of person identification systems based on either manually-crafted features such as DCT, DWT, DFT, PCA, LBP, SURF, SIFT, etc., or deep learning techniques such as CNN, DNN, Alex Net CNN, VGG-16, SVM, Squeeze Net, Google Net, MobileNetV2, etc. The effort will make it easier for researchers, especially those who are new to the field, to have a brief understanding of the trend of employing deep learning in a trustworthy biometric for the identification and recognition of human identification.

show abstract

“…• Ali et al [17] proposed a novel methodology for human recognition through the use of ear images. The approach involved two primary stages, namely ear segmentation and ear recognition.…”

Section: Handcrafted Featuresmentioning

confidence: 99%

Human Recognition Using Ear Features: A Review

Rajab,

Hashim

2023

J. Al-Qadisiyah Comp. Sci. Math.

View full text Add to dashboard Cite

show abstract

“…In addition, a person's ear outer structure stays the same over time or varies very little. To detect ear biometrics, several techniques can be used, such as feature-based template matching [1], [2], [3] and mathematical morphological operations [4], [5] including dilation, erosion, etc. Cropping ear images can benefit from computer vision because required details like shape, contour, edge, curves, and graphs are extracted through image processing; however, this process still necessitates a lot of manual image editing.…”

Section: Introductionmentioning

confidence: 99%

Comparison of YOLO (V3,V5) and MobileNet-SSD (V1,V2) for Person Identification Using Ear-Biometrics

Hossain,

Anzum,

Akhter

2024

IJCDS

View full text Add to dashboard Cite

The ear is a visible organ with a unique structure for each person. As a result, it can be used as a biometric to circumvent the constraints of person identification. Deep learning methods like You Only Look Once (YOLO) and MobileNet have recently significantly aided real-time biometric recognition. As a result, in this paper, we approach identifying a person using YOLOV3, YOLOV5, MobileNet-SSDV1, and MobileNet-SSDV2 deep learning algorithms using their ear biometrics. The used ear biometric is a standard dataset (EarVN1.0 Dataset) from 164 individuals with a total of 27,592 images. We chose 10 people at random, totaling 2057 pictures. Of these, 85% were used for training, 5% for validation, and 10% for testing. The performance of the algorithms is determined based on their accuracy and how smoothly the ear of a person is detected. The training accuracy of the algorithms is thresholded at 99.87%. MobileNet-SSDV1, MobileNet-SSDV2, YOLOV3, and YOLOV5 have testing accuracy that is 88%, 91%, 95%, and 96%, respectively. We concluded that the YOLOV5 model outperforms the others in terms of accuracy and size (16MB) for person identification using ear biometrics.

show abstract