The unconstrained ear recognition challenge

Emeršič, Žiga; Štepec, Dejan; Štruc, Vitomir; Peer, Peter; George, Anjith; Ahmad, Adil M.; Omar, Elshibani; Boult, Terry; Safdaii, Reza; Zhou, Yuxiang; Zafeiriou, Stefanos; Yaman, Dogucan; Eyiokur, Fevziye Irem; Ekenel, Hazım Kemal

doi:10.1109/btas.2017.8272761

Cited by 61 publications

(87 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, recent advancement has pushed the research area to study the recognition performance under more challenging conditions commonly referred to as unconstrained or in the wild. However, moving from controlled to unconstrained image conditions represents the limitations for the existing ear recognition systems as reported by different evaluation groups [37,38]. Under the uncontrolled conditions, the recognition systems are confronted with real-world challenges such as variations in viewing angles, low resolution images, illumination variations, and occlusions caused by hair, earrings, and other objects.…”

Section: Related Workmentioning

confidence: 99%

Handcrafted versus CNN Features for Ear Recognition

et al. 2019

View full text Add to dashboard Cite

Ear recognition is an active research area in the biometrics community with the ultimate goal to recognize individuals effectively from ear images. Traditional ear recognition methods based on handcrafted features and conventional machine learning classifiers were the prominent techniques during the last two decades. Arguably, feature extraction is the crucial phase for the success of these methods due to the difficulty in designing robust features to cope with the variations in the given images. Currently, ear recognition research is shifting towards features extracted by Convolutional Neural Networks (CNNs), which have the ability to learn more specific features robust to the wide image variations and achieving state-of-the-art recognition performance. This paper presents and compares ear recognition models built with handcrafted and CNN features. First, we experiment with seven top performing handcrafted descriptors to extract the discriminating ear image features and then train Support Vector Machines (SVMs) on the extracted features to learn a suitable model. Second, we introduce four CNN based models using a variant of the AlexNet architecture. The experimental results on three ear datasets show the superior performance of the CNN based models by 22%. To further substantiate the comparison, we perform visualization of the handcrafted and CNN features using the t-distributed Stochastic Neighboring Embedding (t-SNE) visualization technique and the characteristics of features are discussed. Moreover, we conduct experiments to investigate the symmetry of the left and right ears and the obtained results on two datasets indicate the existence of a high degree of symmetry between the ears, while a fair degree of asymmetry also exists.

show abstract

Section: Related Workmentioning

confidence: 99%

Handcrafted versus CNN Features for Ear Recognition

et al. 2019

View full text Add to dashboard Cite

show abstract

“…However, to satisfy the input requirement of the used CNN architectures, cropped images are resized to 277x277 square pixels. Also, to further enhance the quality of each ear images, Contrast Limited Adaptive Histogram Equalization (CLAHE) [33], a derivative of histogram equalization is applied. To avoid overfitting and memorizing the exact details of each image by CNN architectures, each ear images are automatically resized by 30 pixels horizontally and vertically in all directions.…”

Section: B Ear Image Preprocessingmentioning

confidence: 99%

Unconstrained Ear Recognition through Domain Adaptive Deep Learning Models of Convolutional Neural Network

Alejo¹,

Hate²

2019

IJRTE

View full text Add to dashboard Cite

Limited ear dataset yields to the adaption of domain adaptive deep learning or transfer learning in the development of ear biometric recognition. Ear recognition is a variation of biometrics that is becoming popular in various areas of research due to the advantages of ears towards human identity recognition. In this paper, handpicked CNN architectures: AlexNet, GoogLeNet, Inception-v3, Inception-ResNet-v2, ResNet-18, ResNet-50, SqueezeNet, ShuffleNet, and MobileNet-v2 are explored and compared for use in an unconstrained ear biometric recognition. 250 unconstrained ear images are collected and acquired from the web through web crawlers and are preprocessed with basic image processing methods including the use of contrast limited adaptive histogram equalization for ear image quality improvement. Each CNN architecture is analyzed structurally and are fine-tuned to satisfy the requirements of ear recognition. Earlier layers of CNN architectures are used as feature extractors. Last 2-3 layers of each CNN architectures are fine-tuned thus, are replaced with layers of the same kind for ear recognition models to classify 10 classes of ears instead of 1000. 80 percent of acquired unconstrained ear images is used for training and the remaining 20 percent is reserved for testing and validation. Results of each architectures are compared in terms of their training time, training and validation outputs as such learned features and losses, and test results in terms of above-95% accuracy confidence. Above all the used architectures, ResNet, AlexNet, and GoogleNet achieved an accuracy confidence of 97-100% and is best for use in unconstrained ear biometric recognition while ShuffleNet, despite of achieving approximately 90%, shows promising result for use in mobile version of unconstrained ear biometric recognition.

show abstract

“…Existing solutions, therefore, commonly rely on hand-crafted image descriptors, such as Scale-Invariant Feature Transforms (SIFTs), Histograms of Oriented Gradients (HOGs), Local Binary Patterns (LBPs) and related descriptors from the literature [5,8,9]. These local descriptor-based approaches have dominated the field for some time, but, as indicated by recent trends in biometrics [11][12][13][14], are typically inferior to learned image descriptors based, for example, on Convolutional Neural Networks (CNNs).…”

Section: Introductionmentioning

confidence: 99%

Deep Sclera Segmentation and Recognition

Rot

Vitek

Grm

et al. 2019

Handbook of Vascular Biometrics

Self Cite

View full text Add to dashboard Cite

In this chapter, we address the problem of biometric identity recognition from the vasculature of the human sclera. Specifically, we focus on the challenging task of multi-view sclera recognition, where the visible part of the sclera vasculature changes from image to image due to varying gaze (or view) directions. We propose a complete solution for this task built around Convolutional Neural Networks (CNNs) and make several contributions that result in state-of-the-art recognition performance, i.e.: (i) we develop a cascaded CNN assembly that is able to robustly segment the sclera vasculature from the input images regardless of gaze direction, and (ii) we present ScleraNET, a CNN model trained in a multi-task manner (combining losses pertaining to identity and view-direction recognition) that allows for the extraction of discriminative vasculature descriptors that can be used for identity inference. To evaluate the proposed contributions, we also introduce a new dataset of ocular images, called the Sclera Blood Vessels, Periocular and Iris (SBVPI) dataset, which represents one of the few publicly available datasets suitable for research in multi-view sclera segmentation and recognition. The datasets come with a rich P. Rot and M. Vitek are first authors with equal contributions.

show abstract

The unconstrained ear recognition challenge

Cited by 61 publications

References 49 publications

Handcrafted versus CNN Features for Ear Recognition

Handcrafted versus CNN Features for Ear Recognition

Unconstrained Ear Recognition through Domain Adaptive Deep Learning Models of Convolutional Neural Network

Deep Sclera Segmentation and Recognition

Contact Info

Product

Resources

About