Ear Feature Research Articles

Anti-Software Attack Ear Identification System Using Deep Feature Learning and Blockchain Protection

Ear recognition has made good progress as an emerging biometric technology. However, the recognition performance, generalization ability, and feature robustness of ear recognition systems based on hand-crafted features are relatively poor. With the development of deep learning, these problems have been partly overcome. However, the recognition performance of existing ear recognition systems still needs to be improved when facing unconstrained ear databases in realistic scenarios. Another critical problem is that most systems with ear feature template databases are vulnerable to software attacks that disclose users’ privacy and even bring down the system. This paper proposes a software-attack-proof ear recognition system using deep feature learning and blockchain protection to address the problem that the recognition performance of existing systems is generally poor in the face of unconstrained ear databases in realistic scenarios. First, we propose an accommodative DropBlock (AccDrop) to generate drop masks with adaptive shapes. It has an advantage over DropBlock in coping with unconstrained ear databases. Second, we introduce a simple and parameterless attention module that uses 3D weights to refine the ear features output from the convolutional layer. To protect the security of the ear feature template database and the user’s privacy, we use Merkle tree nodes to store the ear feature templates, ensuring the determinism of the root node in the smart contract. We achieve Rank-1 (R1) recognition accuracies of 83.87% and 96.52% on the AWE and EARVN1.0 ear databases, which outperform most advanced ear recognition systems.

A Feature Fusion Human Ear Recognition Method Based on Channel Features and Dynamic Convolution

Ear images are easy to capture, and ear features are relatively stable and can be used for identification. The ear images are all asymmetric, and the asymmetry of the ear images collected in the unconstrained environment will be more pronounced, increasing the recognition difficulty. Most recognition methods based on hand-crafted features perform poorly in terms of recognition performance in the face of ear databases that vary significantly in terms of illumination, angle, occlusion, and background. This paper proposes a feature fusion human ear recognition method based on channel features and dynamic convolution (CFDCNet). Based on the DenseNet-121 model, the ear features are first extracted adaptively by dynamic convolution (DY_Conv), which makes the ear features of the same class of samples more aggregated and different types of samples more dispersed, enhancing the robustness of the ear feature representation. Then, by introducing an efficient channel attention mechanism (ECA), the weights of important ear features are increased and invalid features are suppressed. Finally, we use the Max pooling operation to reduce the number of parameters and computations, retain the main ear features, and improve the model’s generalization ability. We performed simulations on the AMI and AWE human ear datasets, achieving 99.70% and 72.70% of Rank-1 (R1) recognition accuracy, respectively. The recognition performance of this method is significantly better than that of the DenseNet-121 model and most existing human ear recognition methods.

Lightweight Human Ear Recognition Based on Attention Mechanism and Feature Fusion

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.

Lightweight YOLOv5s Human Ear Recognition Based on MobileNetV3 and Ghostnet

Ear recognition is a biometric identification technology based on human ear feature information, which can not only detect the human ear in the picture but also determine whose human ear it is, so human identity can be verified by human ear recognition. In order to improve the real-time performance of the ear recognition algorithm and make it better for practical applications, a lightweight ear recognition method based on YOLOv5s is proposed. This method mainly includes the following steps: First, the MobileNetV3 lightweight network is used as the backbone network of the YOLOv5s ear recognition network. Second, using the idea of the Ghostnet network, the C3 module and Conv module in the YOLOv5s neck network are replaced by the C3Ghost module and GhostConv module, and then the YOLOv5s-MG ear recognition model is constructed. Third, three distinctive human ear datasets, CCU-DE, USTB, and EarVN1.0, are collected. Finally, the proposed lightweight ear recognition method is evaluated by four evaluation indexes: mAP value, model size, computational complexity (GFLOPs), and parameter quantity (params). Compared with the best results of YOLOv5s, YOLOv5s-V3, YOLOv5s-V2, and YOLOv5s-G methods on the CCU-DE, USTB, and EarVN1.0 three ear datasets, the params, GFLOPS, and model size of the proposed method YOLOv5s-MG are increased by 35.29%, 38.24%, and 35.57% respectively. The FPS of the proposed method, YOLOv5s-MG, is superior to the other four methods. The experimental results show that the proposed method has the performance of larger FPS, smaller model, fewer calculations, and fewer parameters under the condition of ensuring the accuracy of ear recognition, which can greatly improve the real-time performance and is feasible and effective.

Method for wheat ear counting based on frequency domain decomposition of MSVF-ISCT

Wheat ear counting is a prerequisite for the evaluation of wheat yield. A wheat ear counting method based on frequency domain decomposition is proposed in this study to improve the accuracy of wheat yield estimation. The frequency domain decomposition of wheat ear image is completed by multiscale support value filter (MSVF) combined with improved sampled contourlet transform (ISCT). Support Vector Machine (SVM) is the classic classification and regression algorithm of machine learning. MSVF based on this has strong frequency domain filtering and generalization ability, which can effectively remove the complex background, while the multi-direction characteristics of ISCT enable it to represent the contour and texture information of wheat ears. In order to improve the level of wheat yield prediction, MSVF-ISCT method is used to decompose the ear image in multi-scale and multi direction in frequency domain, reduce the interference of irrelevant information, and generate the sub-band image with more abundant information components of ear feature information. Then, the ear feature is extracted by morphological operation and maximum entropy threshold segmentation, and the skeleton thinning and corner detection algorithms are used to count the results. The number of wheat ears in the image can be accurately counted. Experiments show that compared with the traditional algorithms based on spatial domain, this method significantly improves the accuracy of wheat ear counting, which can provide guidance and application for the field of agricultural precision yield estimation.

CG-ERNet: a lightweight Curvature Gabor filtering based ear recognition network for data scarce scenario

Recently biometric systems have shown improved capabilities because of the remarkable success of deep learning in solving various computer vision tasks. In ear recognition, the use of deep learning techniques is seldom due to training data scarcity. The existing work has shown poor performance as the majority of techniques are based on either handcraft features or pre-trained models. Besides this, transfer-learning has also shown poor performance because of the diversity among the tasks. To circumvent the existing issues, in this work, we have presented an end-to-end framework for ear recognition. It consist of the Ear Mask Extraction (EME) network to segment the ear, a normalization algorithm to align the ear, and a novel siamese-based CNN (CG-ERNet) for deep ear feature learning. CG-ERNet exploits domain-specific knowledge by using Curvature Gabor filters and uses triplet loss, triplet selection, and adaptive margin for better convergence of the loss. For comparative analysis, we trained state-of-the-art deep learning models like Face-Net, VGG19, ResNet50, Inception, Exception, and Mobile-Net for ear-recognition. The performance is assessed using five well-known evaluation metrics. In the extensive experimentation, our proposed model (CG-ERNet) outperformed the deep learning models and handcrafted feature based methods on four different, publicly available, benchmark datasets. To make the results more interpretable, we employ the t-SNE visualization of learned features. Additionally, our proposed method has shown robustness to various environmental challenges like Gaussian noise, Gaussian blur, up to ± 30 degrees of rotation, and 20% of occlusion.

Robust multimodal biometric authentication on IoT device through ear shape and arm gesture

Nowadays, authentication is required for both physical access to buildings and internal access to computers and systems. Biometrics are one of the emerging technologies used to protect these highly sensitive structures. However, biometric systems based on a single trait enclose several problems such as noise sensitivity and vulnerability to spoof attacks. In this regard, we present in this paper a fully unobtrusive and robust multimodal authentication system that automatically authenticates a user by the way he/she answers his/her phone, after extracting ear and arm gesture biometric modalities from this single action. To deal the challenges facing ear and arm gesture authentication systems in real-world applications, we propose a new method based on image fragmentation that makes the ear recognition more robust in relation to occlusion. The ear feature extraction process has been made locally using Local Phase Quantization (LPQ) in order to get robustness with respect to pose and illumination variation. We also propose a set of four statistical metrics to extract features from arm gesture signals. The two modalities are combined on score-level using a weighted sum. In order to evaluate our contribution, we conducted a set of experiments to demonstrate the contribution of each of the two biometrics and the advantage of their fusion on the overall performance of the system. The multimodal biometric system achieves an equal error rate (EER) of 5.15%.

Human – Ear Recognition Using Scale Invariant Feature Transform

Biometrics techniques are the standard of a wide group of many applications for a human’s identification and verification issues. Because of this reason, a high scale of security needs to search for a new way to identify the person arises. In this paper, establish a human ear recognition system is proposed. This system combines four main phases: ear detection, ear feature extraction, ear recognition, and confirmation. The essential of the proposed system is to divide the ear image into the skin and non-skin pixels using a likelihood skin detector. The likelihood image processes by morphological operations to complete ear regions. Scale-invariant feature transform uses for extracting the fixed features of the ear. Ear recognition includes two modes identification mode and verification mode. Euclidean Distance Measure (EDM) uses for similarity measure between the first image in the database and a new image. According to the three experiments conducted in this paper, the results of the different datasets, the accuracy ratio are 100%, 92%.and 92% respectively.

Ear biometric verification approach based on morphological and geometric invariants

<p>Biometric verification based on ear features is modern filed for scientific research. As known, there are many biometric identifiers that can identify people such as fingerprints, iris and speech. In this paper, the focus is placed on the ear biometric model in order to verifying the identity of persons. The main idea is based on used the moments as ear feature extractors. The proposed approach included some operations as follow: image capturing, edge detection, erosion, feature extraction, and matching. The proposed approach has been tested using many images of the ears with different states. Experimental results using several trails verified that the proposed approach is achieved high accuracy level over a wide variety of ear images. Also, the verification process will be completed by matching query ear image with ear images that kept in database during real time.</p>

Ear recognition based on discriminant multi-resolution image representation

The multi-resolution analysis is more appropriate for extracting information from measured data, because it is generally multi-scale in nature. This paper proposes a new approach for ear representation, based on multi-resolution analysis framework. Such representation relies on significantly Gabor wavelet, local phase quantisation (LPQ) descriptor and spatial pyramid histogram (SPH) method. First, to capture the local structure in ear image, the Gabor wavelet function with two scales and four orientations is used. Second, to fully explore the blur invariant property and the texture information in different scales and directions spaces, the LPQ operator is applied on the image responses of Gabor filter to get label LPQ images. Third, the SPH of horizontal decomposition is applied for each of them, to obtain local ear feature descriptors. Next, the obtained histograms are normalised. Then, the global representation of ear image is obtained by concatenating all the local feature descriptors. After that, a discriminant representation of ear image is constructed using whitened linear discriminant analysis. Finally, the K-nearest neighbour classifier is used for identification. Experiments conducted on two ear databases (IIT Delhi-1 and IIT Delhi-2); show that the proposed approach provides a significant accuracy improvement compared to the state-of-the-art methods.

Ear recognition based on discriminant multi-resolution image representation

The multi-resolution analysis is more appropriate for extracting information from measured data, because it is generally multi-scale in nature. This paper proposes a new approach for ear representation, based on multi-resolution analysis framework. Such representation relies on significantly Gabor wavelet, local phase quantisation (LPQ) descriptor and spatial pyramid histogram (SPH) method. First, to capture the local structure in ear image, the Gabor wavelet function with two scales and four orientations is used. Second, to fully explore the blur invariant property and the texture information in different scales and directions spaces, the LPQ operator is applied on the image responses of Gabor filter to get label LPQ images. Third, the SPH of horizontal decomposition is applied for each of them, to obtain local ear feature descriptors. Next, the obtained histograms are normalised. Then, the global representation of ear image is obtained by concatenating all the local feature descriptors. After that, a discriminant representation of ear image is constructed using whitened linear discriminant analysis. Finally, the K-nearest neighbour classifier is used for identification. Experiments conducted on two ear databases (IIT Delhi-1 and IIT Delhi-2); show that the proposed approach provides a significant accuracy improvement compared to the state-of-the-art methods.

Semantic ear feature reduction for source camera identification

Semantic ear feature reduction for source camera identification

Ear verification under uncontrolled conditions with convolutional neural networks

The capabilities of biometric systems have recently made extraordinary leaps by the emergence of deep learning. However, due to the lack of enough training data, the applications of the deep neural network in the ear recognition filed have run into the bottleneck. Moreover, the effect of fine-tuning from some pre-trained models is far less than expected due to the diversity among different tasks. Therefore, the authors propose a large-scale ear database and explore the robust convolutional neural network (CNN) architecture for the ear feature representation. The images in this USTB-Helloear database were taken under uncontrolled conditions with illumination, pose variation and different level of ear occlusions. Then they fine-tuned and modified some deep models on the proposed database through the ear verification experiments. First, they replaced the last pooling layers by spatial pyramid pooling layers to fit arbitrary data size and obtain multi-level features. In the training phase, the CNNs were trained both under the supervision of the softmax loss and centre loss to obtain more compact and discriminative features to identify unseen ears. Finally, three CNNs with different scales of ear images were assembled as the multi-scale ear representations for ear verification. The experimental results demonstrate the effectiveness of the proposed modified CNN deep model.

Multimodal Recognition Method based on Ear and Profile Face Feature Fusion

The performance of ear recognition is influenced by pose variation. For the similar position of ear and profile face, a multimodal recognition method is proposed based on the feature fusion of ear and profile face information. A model for ear and profile face feature fusion and recognition is built. The Log-Gabor features of ear and profile face are first extracted separately, and two features are integrated into a combined feature after two Log-Gabor features are standardized. Then combined feature is mapped to kernel space to fuse further, and acquired stronger discriminant feature for classification by kernel Fisher discriminant analysis (KFDA). The minimum distance classifier is finally used in recognition. Experimental results on the profile face database of Notre Dame University show that the fused method improves the recognition rate of pose variation, and the performance of multimodal recognition is better than unimodal recognition using either ear or profile face alone. The method of ear and profile face feature fusion and recognition is effective and robust for the pose variation.

External ear anthroposcopy in female students of the University of Szczecin

Background: Personal identification based on anthroposcopic characteristics, including the features of the external ear, has recently become highly desirable. This growing interest results from increasin public safety requirements, as well as the ever more numerous practical applications of somatometry and somatoscopy. Especially when there is no biological material necessary for DNA testing, and where instead there are photographs or surveillance footage, being able to identify a person based on anthroposcopic features is an attractive alternative.Aim:The aim of this paper is to investigate the structural diversity of the external ear among the female students of the University of Szczecin and to demonstrate the viability of external ear biometrics in personal identification.Materials and methods: a group of young women n = 65, students of the University of Szczecin, aged 21–29 years (x= 23.7). Structural differences were assessed based on photographs of the left and right ear. Individual characteristics describing the ear were classified according to the adopted criteria. The prevalence of each external ear feature included in the somatoscopic assessment was described as a percentage. Results: The majority of students included in the study had a moderately or prominently curled helix and a long crus of helix. The antihelix with its superior crus were often found to be prominent, as was the antitragus. The tragus was predominantly single and the intertragic notch – moderate. The lobe surface was observed to be rather underdeveloped; attached lobes were found in half of the participants, whereas the remainder had detached lobes.Conclusion:Ear somatoscopy may be an auxiliary method in personal identiication when video recordings or photographs are available.

Analysis of the formation of the Lop Nur Ear feature using multisource satellite imagery

Lop Nur, as the center of China and Eurasia, has a special position in geoscience research. The objective of this paper is to give a comprehensive and reasonable explanation of how the unique Lop Nur Ear feature formed. Because of the severe natural environment, the extensive area, and the difficult field work conditions, remote sensing data are highly suitable for the study of the Lop Nur lake basin. Three types of multisource remote sensing data are applied in this study. Combined with field investigations and laboratory measurements, the causes of the “Ear” feature are explored from different points of view. The results indicate that surface roughness is the most direct cause, while the salinity and depth of the subsurface dry medium layer are the root causes, and topography is an important environmental factor for the formation of the Lop Nur Ear feature. The results of this study help to solve a geological mystery and also provide a new insight into climate change and the demise of ancient civilizations.

Fusion of shape of the ear and tragus – A unique feature extraction method for ear authentication system

In the current scenario to access the data securely from wireless network, e-commerce and internet have become a great concern. As the technologies become commercialized in high markets growth, there is a need for effective and secure implementation to authenticate the identity of the people. Several biometric techniques that exploit physiological and behavioral traits of people have been developed for verification and identification of the individuals to make the system more reliable and secure. In this paper a unique method is used to extract the tragus feature of the ear. The proposed method used is an enhanced edge detection method. A line is drawn connecting the maximum coordinate, midpoint and the minimum coordinate. The mid region of this line gives the tragus of the ear. The ear feature tragus is taken because it is almost free from occlusions. In order to develop an efficient ear authentication system the feature level fusion is applied. The shape of the ear is also extracted. Then the tragus and the shape of the ear are combined together to form the fused template. The authentication rate of the system with the features of tragus, shape of the ear and the fused template is calculated using the Hamming distance technique and Euclidean distance method. The experimental result is carried out on two databases of IIT Delhi ear database and Mathematical Analysis of Images (AMI) ear database including occlusion. The proposed system is to prove that the accuracy of the ear biometric authentication system using Hamming distance technique in fused feature is better than the individual feature of tragus and the ear shape. When a single feature tragus is considered tragus is better than the ear shape as it is a unique feature of the ear.

Ear recognition based on Gabor features and KFDA.

We propose an ear recognition system based on 2D ear images which includes three stages: ear enrollment, feature extraction, and ear recognition. Ear enrollment includes ear detection and ear normalization. The ear detection approach based on improved Adaboost algorithm detects the ear part under complex background using two steps: offline cascaded classifier training and online ear detection. Then Active Shape Model is applied to segment the ear part and normalize all the ear images to the same size. For its eminent characteristics in spatial local feature extraction and orientation selection, Gabor filter based ear feature extraction is presented in this paper. Kernel Fisher Discriminant Analysis (KFDA) is then applied for dimension reduction of the high-dimensional Gabor features. Finally distance based classifier is applied for ear recognition. Experimental results of ear recognition on two datasets (USTB and UND datasets) and the performance of the ear authentication system show the feasibility and effectiveness of the proposed approach.

An Improved Normalization Method for Ear Feature Extraction

As a new biometric identification technology, the theory and application research of ear recognition has attracted more and more attention of scholars in recent years. Imagepreprocessing and normalization of ear image is very important for the feature extraction. In this paper we apply the improved morphological filtering method to preprocessing the ear image. And we propose the angle normalization method by geometrical parameters. This method has the advantages of scaling invariance, translation invariance and rotation invariance. The normalization results are reasonable and good for later feature extraction.

Ear recognition with feed-forward artificial neural networks

Biometrics has become one of the most important techniques in recognizing a person’s identity. A person’s face, iris and fingerprint are mostly used in biometrics today. It has been established that there are no two ears exactly alike, even in the cases of identical twins. In this paper, we define a 7-element ear feature set and design and train a feed-forward artificial neural network to recognize a human ear. We train and test the network with 51 ear pictures from 51 different persons. Simulation experiments with various networks with various number of layers and number of neurons per layer and with and without noise are conducted. Results indicate that a 95 % ear recognition accuracy is achieved with a simple 3-layer feed-forward neural network with only a total of 18 neurons even in the presence of some noise. This design outstands previous work in simplicity and implementation cost.