Ear Recognition Based on Supervised Learning Using Gabor Filters

2010 ◽  
Vol 29-32 ◽  
pp. 1127-1132
Author(s):  
Yong Liang Xiao ◽  
Shao Ping Zhu
Keyword(s):  
Feature Extraction ◽  
Supervised Learning ◽  
Extraction Method ◽  
Nearest Neighbor ◽  
Gabor Filters ◽  
Experimental Results ◽  
Feature Extraction Method ◽  
Nearest Neighbor Classifier ◽  
Ear Recognition ◽  
Neighbor Classifier

In this paper, we introduce a new ear recognition approach including a feature extraction method and the recognition framework. Firstly, we use a supervised kernel neighborhood preserving projection to extract discriminately ear feature, then we use generalized locally nearest neighbor classifier to recognize ear. Experimental results on USTB ear database show the effectiveness of our method.

scholarly journals A Novel Semi-Supervised Feature Extraction Method and Its Application in Automotive Assembly Fault Diagnosis Based on Vision Sensor Data

Sensors ◽  
2018 ◽  
Vol 18 (8) ◽  
pp. 2545 ◽  
Author(s):  
Xuan Zeng ◽  
Shi-Bin Yin ◽  
Yin Guo ◽  
Jia-Rui Lin ◽  
Ji-Gui Zhu
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Supervised Learning ◽  
Extraction Method ◽  
Global Structure ◽  
Experimental Results ◽  
Sensor Data ◽  
Feature Extraction Method ◽  
Fisher Discriminant ◽  
Automotive Assembly

The fault diagnosis of dimensional variation plays an essential role in the production of an automotive body. However, it is difficult to identify faults based on small labeled sample data using traditional supervised learning methods. The present study proposed a novel feature extraction method named, semi-supervised complete kernel Fisher discriminant (SS-CKFDA), and a new fault diagnosis flow for automotive assembly was introduced based on this method. SS-CKFDA is a combination of traditional complete kernel Fisher discriminant (CKFDA) and semi-supervised learning. It adjusts the Fisher criterion with the data global structure extracted from large unlabeled samples. When the number of labeled samples is small, the global structure that exists in the measured data can effectively improve the extraction effects of the projected vector. The experimental results on Tennessee Eastman Process (TEP) data demonstrated that the proposed method can improve diagnostic performance, when compared to other Fisher discriminant algorithms. Finally, the experimental results on the optical coordinate data proves that the method can be applied in the automotive assembly process, and achieve a better performance.

scholarly journals Pengenalan Wajah Menggunakan Metode Linear Discriminant Analysis dan k Nearest Neighbor

2017 ◽  
Vol 9 (1) ◽  
pp. 1-9
Author(s):  
Fandiansyah Fandiansyah ◽  
Jayanti Yusmah Sari ◽  
Ika Putri Ningrum
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Nearest Neighbor ◽  
Experimental Result ◽  
K Nearest Neighbor ◽  
Linear Discriminant ◽  
Nearest Neighbor Classifier ◽  
Neighbor Classifier

Face recognition is one of the biometric system that mostly used for individual recognition in the absent machine or access control. This is because the face is the most visible part of human anatomy and serves as the first distinguishing factor of a human being. Feature extraction and classification are the key to face recognition, as they are to any pattern classification task. In this paper, we describe a face recognition method based on Linear Discriminant Analysis (LDA) and k-Nearest Neighbor classifier. LDA used for feature extraction, which directly extracts the proper features from image matrices with the objective of maximizing between-class variations and minimizing within-class variations. The features of a testing image will be compared to the features of database image using K-Nearest Neighbor classifier. The experiments in this paper are performed by using using 66 face images of 22 different people. The experimental result shows that the recognition accuracy is up to 98.33%. Index Terms—face recognition, k nearest neighbor, linear discriminant analysis.

Wear Particles Recognition Based on Improved LBP

2013 ◽  
Vol 427-429 ◽  
pp. 1874-1878
Author(s):  
Guo De Wang ◽  
Zhi Sheng Jing ◽  
Guo Wei Qin ◽  
Shan Chao Tu
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Local Binary Pattern ◽  
Recognition Accuracy ◽  
Binary Sequence ◽  
Texture Feature ◽  
Experimental Results ◽  
Wear Particles ◽  
Texture Feature Extraction ◽  
Feature Extraction Method

Wear particles recognition is a key link in the process of Ferrography analysis. Different kinds of wear particles vary greatly in texture, texture feature is one of the most important feature in wear particles recognition. Local Binary Pattern (LBP) is an efficient operator for texture description. The binary sequence of traditional LBP operator is obtained by the comparison between the gray value of the neighborhood and the gray value of the center pixel of the neighborhood, the comparison is too simple to cause the loss of the texture. In this paper, an improved LBP operator is presented for texture feature extraction and it is applied to the recognition of severe sliding particles, fatigue spall particles and laminar particles. The experimental results show that our method is an effective feature extraction method and obtains better recognition accuracy compared with other methods.

scholarly journals On Improving the Classification of Imbalanced Data

2017 ◽  
Vol 17 (1) ◽  
pp. 45-62 ◽  
Author(s):  
Lincy Meera Mathews ◽  
Hari Seetha
Keyword(s):  
Nearest Neighbor ◽  
Imbalanced Data ◽  
Experimental Results ◽  
Minority Class ◽  
Nearest Neighbor Classifier ◽  
Neighbor Classifier

Abstract Mining of imbalanced data isachallenging task due to its complex inherent characteristics. The conventional classifiers such as the nearest neighbor severely bias towards the majority class, as minority class data are under-represented and outnumbered. This paper focuses on building an improved Nearest Neighbor Classifier foratwo class imbalanced data. Three oversampling techniques are presented, for generation of artificial instances for the minority class for balancing the distribution among the classes. Experimental results showed that the proposed methods outperformed the conventional classifier.

scholarly journals Sistem Identifikasi Relief pada Situs Bersejarah Menggunakan Perangkat Mobile Android (Studi Kasus Candi Borobudur)

2014 ◽  
Vol 10 (1) ◽  
pp. 133
Author(s):  
Rajif Agung Yunmar ◽  
Agus Harjoko
Keyword(s):  
Feature Extraction ◽  
Royal Society ◽  
Extraction Method ◽  
Nearest Neighbor ◽  
Life Story ◽  
Computation Time ◽  
Feature Extraction Method ◽  
Average Computation Time ◽  
The Temple ◽  
Image Object

Abstrak            Bangsa yang besar adalah bangsa yang menghargai sejarah dan asal usulnya. Relief yang terdapat pada candi Borobudur menggambarkan banyak cerita, termasuk sejarah dan asal usul bangsa ini. Mulai dari cerita kehidupan kalangan kerajaan, kehidupan masyarakat, dan adat istiadat pada saat bangunan candi tersebut dibuat, dsb.            Penelitian ini merancang sebuah perangkat lunak mobile Android untuk identifikasi citra relief Candi Borobudur sehingga dapat membantu wisatawan dalam menerjemahkan pesan dan informasi yang terkandung didalamnya. Metode ekstraksi ciri yang digunakan adalah Speeded-Up Robust Feature (SURF) dan hierarchical k-means tree nearest-neighbor untuk identifikasinya.            Pengujian identifikasi citra relief dilakukan dengan berbagai macam variasi, yaitu sudut, jarak, rotasi, intensitas cahaya dan keutuhan citra masukan untuk melihat pengaruhnya terhadap hasil pengenalan citra relief tersebut. Metode identifikasi yang diajukan memberikan hasil pengenalan sebesar 93.30% dengan rata-rata waktu komputasi 59.55 detik.  Abstract            The great nation built from people who can respects they history and origins. Reliefs at Borobudur temple contained many stories, including the history and origins of this nation. Starting from the life story of the royal, society, and customs at the time of the building of the temple was made, and so on.            This study develops mobile Android software for identification of Borobudur Temple relief image object so that it can help travelers in translating the story and the information contained therein. Feature extraction method used is speeded-Up Robust Feature (SURF) and hierarchical k-means tree nearest-neighbor for identification.            Identification testing of relief images is done by different variations, ie angle, distance, rotation, intensity of the light and wholeness of image input to see the effect on the relief image recognition results. The proposed identification method gives recognition results of 93.30% and the average computation time for 59.55 seconds.

scholarly journals Local Binary Pattern Based Iris Recognition Model

2020 ◽  
pp. 19-22
Keyword(s):  
Human Physiology ◽  
Iris Recognition ◽  
Local Binary Pattern ◽  
Nearest Neighbor ◽  
Hamming Distance ◽  
Experimental Results ◽  
Recognition Model ◽  
Nearest Neighbor Classifier ◽  
Texture Information ◽  
Neighbor Classifier

Iris is a unique biometric tool, secure and reliable in recognizing an individual based on the texture information of human physiology. The Local Binary Pattern method uses descriptors based on histograms of Local Binary Pattern. In developed algorithm, Local Binary Pattern (LBP) histograms of iris images are extracted and concatenated into single enhanced histogram. It can be computed by nearest neighbor classifier and iris recognition is performed using Hamming distance as dissimilarity measure. We have conducted experimentation on CASIA dataset. From the experimental results, it is proved that the Robust LBP technique for iris recognition is more accurate than the conventional LBP.

scholarly journals Double Feature Extraction Method of Ship-Radiated Noise Signal Based on Slope Entropy and Permutation Entropy

Entropy ◽  
2021 ◽  
Vol 24 (1) ◽  
pp. 22
Author(s):  
Yuxing Li ◽  
Peiyuan Gao ◽  
Bingzhao Tang ◽  
Yingmin Yi ◽  
Jianjun Zhang
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Nearest Neighbor ◽  
Recognition Rate ◽  
Noise Signal ◽  
Permutation Entropy ◽  
K Nearest Neighbor ◽  
Feature Extraction Method ◽  
Radiated Noise ◽  
Single Feature

In order to accurately identify various types of ships and develop coastal defenses, a single feature extraction method based on slope entropy (SlEn) and a double feature extraction method based on SlEn combined with permutation entropy (SlEn&PE) are proposed. Firstly, SlEn is used for the feature extraction of ship-radiated noise signal (SNS) compared with permutation entropy (PE), dispersion entropy (DE), fluctuation dispersion entropy (FDE), and reverse dispersion entropy (RDE), so that the effectiveness of SlEn is verified, and SlEn has the highest recognition rate calculated by the k-Nearest Neighbor (KNN) algorithm. Secondly, SlEn is combined with PE, DE, FDE, and RDE, respectively, to extract the feature of SNS for a higher recognition rate, and SlEn&PE has the highest recognition rate after the calculation of the KNN algorithm. Lastly, the recognition rates of SlEn and SlEn&PE are compared, and the recognition rates of SlEn&PE are higher than SlEn by 4.22%. Therefore, the double feature extraction method proposed in this paper is more effective in the application of ship type recognition.

FPGA-Based Implementation of Face Recognition Based on Gabor and DCT

2012 ◽  
Vol 241-244 ◽  
pp. 1741-1744
Author(s):  
Guo Hong Lai ◽  
Luo Min ◽  
Song Liu ◽  
Xiao Fang Wang
Keyword(s):  
Face Recognition ◽  
Discrete Cosine Transform ◽  
Nearest Neighbor ◽  
Experimental Results ◽  
Gabor Transform ◽  
Face Database ◽  
Recognition Method ◽  
Cosine Transform ◽  
Nearest Neighbor Classifier ◽  
Neighbor Classifier

A face recognition method based on discrete cosine transform and Gabor transform is proposed. A FPGA-based platform on DE2-115 board is designed by SOPC. We compared our methods with the method based on PC. In the experiments, the nearest neighbor classifier is used to recognize different faces from the Yale face database. Experimental results show that the proposed

Sign in / Sign up

Export Citation Format

Share Document