Human Ear Recognition Using Geometrical Features Extraction
TL;DR: A new algorithm for ear recognition based on geometrical features extraction like (shape, mean, centroid and Euclidean distance between pixels) is presented, which is invariant to scaling, translation and rotation.
Abstract: The biometrics recognition has been paid more attention by people with the advancement of technology nowadays. The human ear is a perfect source of data for passive person identification. Ear seems to be a good candidate solution since ear is visible, their images are easy to take and structure of ear does not change radically over time. Ear satisfies biometric characteristic (universality, distinctiveness, permanence and collectability). In this paper we presented a new algorithm for ear recognition based on geometrical features extraction like (shape, mean, centroid and Euclidean distance between pixels). Firstly, we made a pre-processing phase by making all images have the same size. Then we used the snake model to detect the ear, and we applied median filter to remove noise, also we converted the images to binary format. After that we used canny edge and made some enhancement on the image, largest boundary is calculated and distance matrix is created then we extracted the image features. Finally, the extracted features were classified by using nearest neighbor with absolute error distance. This method is invariant to scaling, translation and rotation. The experimental results showed that the proposed approach gives better results and obtained over all accuracy almost 98%.
Citations
More filters
[...]
01 Jan 2016
Abstract: Thank you for downloading elements of style. As you may know, people have search hundreds times for their chosen novels like this elements of style, but end up in malicious downloads. Rather than reading a good book with a cup of coffee in the afternoon, instead they are facing with some infectious bugs inside their desktop computer. elements of style is available in our digital library an online access to it is set as public so you can download it instantly. Our digital library spans in multiple locations, allowing you to get the most less latency time to download any of our books like this one. Merely said, the elements of style is universally compatible with any devices to read.
169 citations
01 Aug 2016
TL;DR: The proposed system for feature selection is proposed using a sine cosine algorithm and shows an advance over other search methods as particle swarm optimization (PSO) and genetic algorithm (GA) optimizers commonly used in this context using different evaluation indicators.
Abstract: Nowadays, a dataset includes a huge number of features with irrelevant and redundant ones. Feature selection is required for a better machine-learning algorithms' performance. A system for feature selection is proposed in this work using a sine cosine algorithm (SCA). SCA is a new stochastic search algorithm for optimization problems. SCA optimization adaptively balances the exploration and exploitation to find the optimal solution quickly. The SCA can quickly explore the feature space for optimal or near-optimal feature subset minimizing a given fitness function. The proposed fitness function used incorporates both classification accuracy and feature size reduction. The proposed system was tested on 18 datasets and shows an advance over other search methods as particle swarm optimization (PSO) and genetic algorithm (GA) optimizers commonly used in this context using different evaluation indicators.
94 citations
Cites background from "Human Ear Recognition Using Geometr..."
...Feature selection assists in understanding data, reducing the effect of a curse of dimensionality and improving the classification performance [2], [3]....
[...]
01 Jul 2016
TL;DR: MFO is exploited in this study as a searching method to find optimal feature set, maximizing classification performance, and the efficiency of the proposed algorithm is compared against particle swarm optimization (PSO) and genetic algorithms (GA).
Abstract: In this work, a feature selection algorithm based on moth-flame optimization (MFO) is proposed. Moth-flame optimization (MFO) is a recently proposed swarm intelligent optimization algorithm that mimics the motion of moths. The proposed algorithm is applied in the domain of machine learning for feature selection to find the optimal feature combination using wrapper-based feature selection mode. In wrapper-based feature selection, a machine learning technique is used in the evaluation step. Despite it is very costly in time, this technique proved to have a good performance in classification accuracy. MFO is exploited in this study as a searching method to find optimal feature set, maximizing classification performance. The proposed algorithm is compared against particle swarm optimization (PSO) and genetic algorithms (GA). A set of UCI data sets is used for comparison using different assessment indicators. Results prove the efficiency of the proposed algorithm in comparison to other algorithms.
79 citations
Cites methods from "Human Ear Recognition Using Geometr..."
...Classifiers do not use any model for KNN and the classification is based on the minimum distance from the query unknown instance to the training samples [12]....
[...]
01 Nov 2015
TL;DR: Antlion optimization (ALO) algorithm mimics the hunting mechanism of antlions in nature and is compared to two common search methods namely particle swarm optimization (PSO) and genetic algorithm (GA) and proves an advance in classification performance and selected feature set.
Abstract: In this work, a model for feature selection based on antlion optimization (ALO) is proposed. Feature sets always have redundant, dependant and correlated features that badly affect the classification performance and increases training time. Therefore, feature selection becomes a must to remove irrelevant features and enhances classification generalization. Wrapper-based feature selection is a method that selects a feature set maximizing a given classifier performance criteria and hence requires efficient searching method to find optimal feature combinations. Antlion optimization is a recently proposed swarm optimizer with good searching capability. ALO is exploited in this study as searching method to find optimal feature set maximizing classification performance. ALO algorithm mimics the hunting mechanism of antlions in nature. The proposed model is evaluated using different evaluation criteria on 18 different data sets and is compared to two common search methods namely particle swarm optimization (PSO) and genetic algorithm (GA) and proves an advance in classification performance and selected feature set.
78 citations
TL;DR: The authors propose a deep learning-based averaging ensemble to reduce the effect of over-fitting on unconstrained ear recognition datasets as compared to DNN feature-extraction based models and single fine-tuned models.
Abstract: The authors perform unconstrained ear recognition using transfer learning with deep neural networks (DNNs). First, they show how existing DNNs can be used as a feature extractor. The extracted features are used by a shallow classifier to perform ear recognition. Performance can be improved by augmenting the training dataset with small image transformations. Next, they compare the performance of the feature-extraction models with fine-tuned networks. However, because the datasets are limited in size, a fine-tuned network tends to over-fit. They propose a deep learning-based averaging ensemble to reduce the effect of over-fitting. Performance results are provided on unconstrained ear recognition datasets, the AWE and CVLE datasets as well as a combined AWE + CVLE dataset. They show that their ensemble results in the best recognition performance on these datasets as compared to DNN feature-extraction based models and single fine-tuned models.
66 citations
References
More filters
TL;DR: It is found that recognition performance is not significantly different between the face and the ear, for example, 70.5 percent versus 71.6 percent in one experiment and multimodal recognition using both the ear and face results in statistically significant improvement over either individual biometric.
Abstract: Researchers have suggested that the ear may have advantages over the face for biometric recognition. Our previous experiments with ear and face recognition, using the standard principal component analysis approach, showed lower recognition performance using ear images. We report results of similar experiments on larger data sets that are more rigorously controlled for relative quality of face and ear images. We find that recognition performance is not significantly different between the face and the ear, for example, 70.5 percent versus 71.6 percent, respectively, in one experiment. We also find that multimodal recognition using both the ear and face results in statistically significant improvement over either individual biometric, for example, 90.9 percent in the analogous experiment.
597 citations
Proceedings Article•
18 Jun 2004TL;DR: A brief overview of biometric methods, both unimodal and multimodal, and their advantages and disadvantages, will be presented.
Abstract: Biometric recognition refers to an automatic recognition of individuals based on a feature vector (s) derived from their physiological and/or behavioral characteristic. Biometric recognition systems should provide a reliable personal recognition schemes to either confirm or determine the identity of an individual. Applications of such a system include computer systems security, secure electronic banking, mobile phones, credit cards, secure access to buildings, health and social services. By using biometrics a person could be identified based on "who she/he is" rather then "what she/he has" (card, token, key) or "what she/he knows" (password, PIN). In this paper, a brief overview of biometric methods, both unimodal and multimodal, and their advantages and disadvantages, will be presented.
435 citations
TL;DR: This work confirms not only that ears do indeed appear to have potential as a biometric, but also that the new approach is well suited to their description, being robust especially in the presence of noise, and having the advantages that the ear does not need to be explicitly extracted from the background.
Abstract: The overall objective in defining feature space is to reduce the dimensionality of the original pattern space, whilst maintaining discriminatory power for classification. To meet this objective in the context of ear biometrics a new force field transformation treats the image as an array of mutually attracting particles that act as the source of a Gaussian force field. Underlying the force field there is a scalar potential energy field, which in the case of an ear takes the form of a smooth surface that resembles a small mountain with a number of peaks joined by ridges. The peaks correspond to potential energy wells and to extend the analogy the ridges correspond to potential energy channels. Since the transform also turns out to be invertible, and since the surface is otherwise smooth, information theory suggests that much of the information is transferred to these features, thus confirming their efficacy. We previously described how field line feature extraction, using an algorithm similar to gradient descent, exploits the directional properties of the force field to automatically locate these channels and wells, which then form the basis of characteristic ear features. We now show how an analysis of the mechanism of this algorithmic approach leads to a closed analytical description based on the divergence of force direction, which reveals that channels and wells are really manifestations of the same phenomenon. We further show that this new operator, with its own distinct advantages, has a striking similarity to the Marr-Hildreth operator, but with the important difference that it is non-linear. As well as addressing faster implementation, invertibility, and brightness sensitivity, the technique is also validated by performing recognition on a database of ears selected from the XM2VTS face database, and by comparing the results with the more established technique of Principal Components Analysis. This confirms not only that ears do indeed appear to have potential as a biometric, but also that the new approach is well suited to their description, being robust especially in the presence of noise, and having the advantages that the ear does not need to be explicitly extracted from the background.
255 citations
05 Oct 1999
TL;DR: A new multiple identification method, which combines the results obtained by several neural classifiers using, respectively, features outer ear points, information obtained from ear shape and wrinkles, and macrofeatures extracted by a compression network, is presented.
Abstract: In this paper we investigate the use of outer ear images for human identification. From the point of view of image processing, ears offer several advantages over complete faces: reduced spatial resolution, a more uniform distribution of colour, and less variability with expressions and orientation of the face. These advantages together with its identification richness, make ear images appropriate to be used as input data for a connectionist system. A new multiple identification method, which combines the results obtained by several neural classifiers using, respectively, features outer ear points, information obtained from ear shape and wrinkles, and macrofeatures extracted by a compression network, is presented. Experimental results yields higher identification rates as well as a more robust framework using this approach as a component of a more general face identification system especially in security applications.
182 citations