A Image Decomposition Method Based on Euler Mapping for Face Recognition

2014 ◽  
Vol 989-994 ◽  
pp. 4119-4122
Author(s):  
Zhao Kui Li ◽  
Yan Wang
Keyword(s):  
Feature Vector ◽  
State Of The Art ◽  
Image Decomposition ◽  
Feature Representation ◽  
Image Feature ◽  
Z Score ◽  
Linear Discriminant ◽  
Score Method ◽  
Representation Method ◽  
Low Dimensional

This paper presents a robust but simple image feature representation method, called image decomposition based on Euler mapping (IDEM). IDEM firstly captures the orientation information by implementing arctangent operator for each pixel. Then, the orientation image is decomposed into two mapping images by executing Euler mapping. Each mapping image is normalized using the “z-score” method, and all normalized vectors are concatenated into an augmented feature vector. The dimensionality of the augmented feature vector is reduced by linear discriminant analysis to yield a low-dimensional feature vector. Experimental results show that IDEM achieves better results in comparison with state-of-the-art methods.

A Robust Face Representation Method for Face Recognition

2014 ◽  
Vol 945-949 ◽  
pp. 1801-1804
Author(s):  
Zhao Kui Li
Keyword(s):  
Face Recognition ◽  
Feature Vector ◽  
State Of The Art ◽  
Linear Discriminant ◽  
Face Representation ◽  
Spatial Locality ◽  
Score Method ◽  
Robust Face Recognition ◽  
Representation Method ◽  
Low Dimensional

In this paper, a robust face representation method based on multiple gradient orientations for face recognition is proposed. We introduce multiple gradient orientations and compute multiple orientation images which display different spatial locality and orientation properties. Each orientation image is normalized using the “z-score” method, and all normalized vectors are concatenated into an augmented feature vector. The dimensionality of the augmented feature vector is reduced by linear discriminant analysis to yield a low-dimensional feature vector. Experimental results show that our method achieves state-of-the-art performance for difficult problems such as illumination and occlusion-robust face recognition.

Feature Representation Method Based on Kirsch Masks Filter for Face Recognition

2014 ◽  
Vol 989-994 ◽  
pp. 4209-4212
Author(s):  
Zhao Kui Li ◽  
Yan Wang
Keyword(s):  
Face Recognition ◽  
Local Binary Patterns ◽  
Feature Representation ◽  
Linear Discriminant ◽  
Robust Coding ◽  
Gabor Features ◽  
Robust Face Recognition ◽  
Representation Method ◽  
Low Dimensional ◽  
Direction Image

In this paper, a feature representation method based on Kirsch masks filter for face recognition is proposed. We firstly obtain eight direction images by performing Kirsch masks filter. For each direction image, the low-dimensional feature vector is computed by Linear Discriminant Analysisis. Then, a fusion strategy is used to combine different direction image according to their respective salience. Experimental results show that our methods significantly outperform popular methods such as Gabor features, Local Binary Patterns, Regularized Robust Coding (RRC), and achieve state-of-the-art performance for difficult problems such as illumination and occlusion-robust face recognition.

scholarly journals Redundancy Removal Adversarial Active Learning Based on Norm Online Uncertainty Indicator

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Jifeng Guo ◽  
Zhiqi Pang ◽  
Wenbo Sun ◽  
Shi Li ◽  
Yu Chen
Keyword(s):  
Active Learning ◽  
Feature Vector ◽  
State Of The Art ◽  
Representation Learning ◽  
The State ◽  
Feature Representation ◽  
Learning Ability ◽  
Redundancy Removal ◽  
Previous State ◽  
Uncertainty Score

Active learning aims to select the most valuable unlabelled samples for annotation. In this paper, we propose a redundancy removal adversarial active learning (RRAAL) method based on norm online uncertainty indicator, which selects samples based on their distribution, uncertainty, and redundancy. RRAAL includes a representation generator, state discriminator, and redundancy removal module (RRM). The purpose of the representation generator is to learn the feature representation of a sample, and the state discriminator predicts the state of the feature vector after concatenation. We added a sample discriminator to the representation generator to improve the representation learning ability of the generator and designed a norm online uncertainty indicator (Norm-OUI) to provide a more accurate uncertainty score for the state discriminator. In addition, we designed an RRM based on a greedy algorithm to reduce the number of redundant samples in the labelled pool. The experimental results on four datasets show that the state discriminator, Norm-OUI, and RRM can improve the performance of RRAAL, and RRAAL outperforms the previous state-of-the-art active learning methods.

scholarly journals Enhancing Classification Performance of fNIRS-BCI by Identifying Cortically Active Channels Using the z-Score Method

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6995
Author(s):  
Hammad Nazeer ◽  
Noman Naseer ◽  
Aakif Mehboob ◽  
Muhammad Jawad Khan ◽  
Rayyan Azam Khan ◽  
...  
Keyword(s):  
Open Access ◽  
Motor Imagery ◽  
Mental Arithmetic ◽  
State Of The Art ◽  
Brain Activity ◽  
Channel Selection ◽  
Classification Performance ◽  
Finger Tapping ◽  
Z Score ◽  
Score Method

A state-of-the-art brain–computer interface (BCI) system includes brain signal acquisition, noise removal, channel selection, feature extraction, classification, and an application interface. In functional near-infrared spectroscopy-based BCI (fNIRS-BCI) channel selection may enhance classification performance by identifying suitable brain regions that contain brain activity. In this study, the z-score method for channel selection is proposed to improve fNIRS-BCI performance. The proposed method uses cross-correlation to match the similarity between desired and recorded brain activity signals, followed by forming a vector of each channel’s correlation coefficients’ maximum values. After that, the z-score is calculated for each value of that vector. A channel is selected based on a positive z-score value. The proposed method is applied to an open-access dataset containing mental arithmetic (MA) and motor imagery (MI) tasks for twenty-nine subjects. The proposed method is compared with the conventional t-value method and with no channel selected, i.e., using all channels. The z-score method yielded significantly improved (p < 0.0167) classification accuracies of 87.2 ± 7.0%, 88.4 ± 6.2%, and 88.1 ± 6.9% for left motor imagery (LMI) vs. rest, right motor imagery (RMI) vs. rest, and mental arithmetic (MA) vs. rest, respectively. The proposed method is also validated on an open-access database of 17 subjects, containing right-hand finger tapping (RFT), left-hand finger tapping (LFT), and dominant side foot tapping (FT) tasks.The study shows an enhanced performance of the z-score method over the t-value method as an advancement in efforts to improve state-of-the-art fNIRS-BCI systems’ performance.

scholarly journals Hyperspectral Remote Sensing Image Feature Representation Method Based on CAE-H with Nuclear Norm Constraint

Electronics ◽  
2021 ◽  
Vol 10 (21) ◽  
pp. 2667
Author(s):  
Xiaodong Yu ◽  
Rui Ding ◽  
Jingbo Shao ◽  
Xiaohui Li
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Image ◽  
Hyperspectral Remote Sensing ◽  
Feature Representation ◽  
Nuclear Norm ◽  
Image Feature ◽  
Frobenius Norm ◽  
Representation Method ◽  
Norm Constraint ◽  
Hyperspectral Remote Sensing Image

Due to the high dimensionality and high data redundancy of hyperspectral remote sensing images, it is difficult to maintain the nonlinear structural relationship in the dimensionality reduction representation of hyperspectral data. In this paper, a feature representation method based on high order contractive auto-encoder with nuclear norm constraint (CAE-HNC) is proposed. By introducing Jacobian matrix in the CAE of the nuclear norm constraint, the nuclear norm has better sparsity than the Frobenius norm and can better describe the local low dimension of the data manifold. At the same time, a second-order penalty term is added, which is the Frobenius norm of the Hessian matrix expressed in the hidden layer of the input, encouraging a smoother low-dimensional manifold geometry of the data. The experiment of hyperspectral remote sensing image shows that CAE-HNC proposed in this paper is a compact and robust feature representation method, which provides effective help for the ground object classification and target recognition of hyperspectral remote sensing image.

scholarly journals DETECTING AND DISCARDING OF SHADOWS IN IMAGE USING GEOMETRIC CONTOURS AND REGION BASED SEGMENTATION USING THRESHOLDING APPROACH

2015 ◽  
Vol 3 (2) ◽  
pp. 13-19
Author(s):  
Shanthi S ◽  
Vinothini K. R ◽  
Manikandan
Keyword(s):  
Image Matching ◽  
Feature Vector ◽  
Active Contours ◽  
Feature Representation ◽  
Shadow Detection ◽  
Image Feature ◽  
Traditional Model ◽  
Image Feature Extraction ◽  
Segmentation Methods ◽  
Geometric Active Contours

Shadow detection and removal is an important task when dealing with color outdoor images. Shadows are generated by a local and relative absence of light. Most shadow detection and segmentation methods are based on image analysis. However, some factors will affect the detection result due to the complexity of the circumstances.In this paper, a new algorithm for shadow detection and isolation of buildings in high-resolution panchromatic satellite imagery is proposed. This algorithm is based on tailoring the traditional model of the geometric active contours such that the new model of the contours is systematically biased toward segmenting the shadow and the dark regions in the image. Feature extraction a type of dimensionality reduction that efficiently represents interesting parts of an image as a compact feature vector. This approach is useful when image sizes are large and a reduced feature representation is required to quickly complete tasks such as image matching and retrieval.

scholarly journals Cube of Space Sampling for 3D Model Retrieval

2021 ◽  
Vol 11 (23) ◽  
pp. 11142
Author(s):  
Zong-Yao Chen ◽  
Chih-Fong Tsai ◽  
Wei-Chao Lin
Keyword(s):  
3D Model ◽  
State Of The Art ◽  
3D Models ◽  
3D Model Retrieval ◽  
Feature Representation ◽  
Direct Extraction ◽  
Feature Descriptors ◽  
Model Retrieval ◽  
Representation Method ◽  
Global And Local

Since the number of 3D models is rapidly increasing, extracting better feature descriptors to represent 3D models is very challenging for effective 3D model retrieval. There are some problems in existing 3D model representation approaches. For example, many of them focus on the direct extraction of features or transforming 3D models into 2D images for feature extraction, which cannot effectively represent 3D models. In this paper, we propose a novel 3D model feature representation method that is a kind of voxelization method. It is based on the space-based concept, namely CSS (Cube of Space Sampling). The CSS method uses cube space 3D model sampling to extract global and local features of 3D models. The experiments using the ESB dataset show that the proposed method to extract the voxel-based features can provide better classification accuracy than SVM and comparable retrieval results using the state-of-the-art 3D model feature representation method.

Face Image Feature Extraction and Feature Selection

2013 ◽  
Vol 432 ◽  
pp. 587-591 ◽  
Author(s):  
Yang Meng Tian ◽  
Yu Duo Zheng ◽  
Wei Jin ◽  
Gai Hong Du
Keyword(s):  
Feature Extraction ◽  
Feature Selection ◽  
Nearest Neighbor ◽  
Feature Vector ◽  
Dimensional Space ◽  
Face Image ◽  
Image Feature ◽  
High Dimensional ◽  
Gabor Feature ◽  
Low Dimensional

In order to solve the problem of face recognition, the method of feature extraction and feature selection is presented in this paper. First using Gabor filters and face image as the convolution Operator to extract the Gabor feature vector of the image and also to uniform sampling; then using the PCA + LDA method to reduce the dimension for high-dimensional Gabor feature vector; Finally, using the nearest neighbor classifier to discriminate and determine the identity of a face image. The result I get is that the sampled Gabor feature in high-dimensional space can be projected onto low-dimensional space though the method of feature selection and compression. The new and original in this paper is that the method of PCA + LDA overcomes the problem of the spread matrix singular in the class and matrix too large which is brought by directly use the LDA.

scholarly journals Integrating multi-network topology for gene function prediction using deep neural networks

2019 ◽  
Author(s):  
Hansheng Xue ◽  
Jiajie Peng ◽  
Xuequn Shang
Keyword(s):  
Neural Network ◽  
Gene Function ◽  
State Of The Art ◽  
Feature Learning ◽  
Function Prediction ◽  
Feature Representation ◽  
Superior Performance ◽  
Gene Function Prediction ◽  
Multiple Networks ◽  
Low Dimensional

AbstractMotivationThe emerging of abundant biological networks, which benefit from the development of advanced high-throughput techniques, contribute to describing and modeling complex internal interactions among biological entities such as genes and proteins. Multiple networks provide rich information for inferring the function of genes or proteins. To extract functional patterns of genes based on multiple heterogeneous networks, network embedding-based methods, aiming to capture non-linear and low-dimensional feature representation based on network biology, have recently achieved remarkable performance in gene function prediction. However, existing methods mainly do not consider the shared information among different networks during the feature learning process. Thus, we propose a novel multi-networks embedding-based function prediction method based on semi-supervised autoencoder and feature convolution neural network, named DeepMNE-CNN, which captures complex topological structures of multi-networks and takes the correlation among multi-networks into account.ResultsWe design a novel semi-supervised autoencoder method to integrate multiple networks and generate a low-dimensional feature representation. Then we utilize a convolutional neural network based on the integrated feature embedding to annotate unlabeled gene functions. We test our method on both yeast and human dataset and compare with four state-of-the-art methods. The results demonstrate the superior performance of our method over four state-of-the-art algorithms. From the future explorations, we find that semi-supervised autoencoder based multi-networks integration method and CNN-based feature learning methods both contribute to the task of function prediction.AvailabilityDeepMNE-CNN is freely available at https://github.com/xuehansheng/DeepMNE-CNN

Sign in / Sign up

Export Citation Format

Share Document