Search Word(s) in Title, Keywords, Authors, and Abstract: Feature Vector

Kernel Fisher Discriminant Analysis for Natural Gait Cycle Based Gait Recognition
Jun Huang, Xiuhui Wang and Jun Wang
Page: 957~966, Vol. 15, No.4, 2019
10.3745/JIPS.02.0115
Keywords: Gait Energy Image, Gait Recognition, Kernel Fisher Discriminant Analysis, Natural Gait Cycle
Show / Hide Abstract
This paper studies a novel approach to natural gait cycles based gait recognition via kernel Fisher discriminant analysis (KFDA), which can effectively calculate the features from gait sequences and accelerate the recognition process. The proposed approach firstly extracts the gait silhouettes through moving object detection and segmentation from each gait videos. Secondly, gait energy images (GEIs) are calculated for each gait videos, and used as gait features. Thirdly, KFDA method is used to refine the extracted gait features, and low-dimensional feature vectors for each gait videos can be got. The last is the nearest neighbor classifier is applied to classify. The proposed method is evaluated on the CASIA and USF gait databases, and the results show that our proposed algorithm can get better recognition effect than other existing algorithms.


DeepAct: A Deep Neural Network Model for Activity Detection in Untrimmed Videos
Yeongtaek Song and Incheol Kim
Page: 150~161, Vol. 14, No.1, 2018
10.3745/JIPS.04.0059
Keywords: Activity Detection, Bi-directional LSTM, Deep Neural Networks, Untrimmed Video
Show / Hide Abstract
We propose a novel deep neural network model for detecting human activities in untrimmed videos. The process of human activity detection in a video involves two steps: a step to extract features that are effective in recognizing human activities in a long untrimmed video, followed by a step to detect human activities from those extracted features. To extract the rich features from video segments that could express unique patterns for each activity, we employ two different convolutional neural network models, C3D and I-ResNet. For detecting human activities from the sequence of extracted feature vectors, we use BLSTM, a bi-directional recurrent neural network model. By conducting experiments with ActivityNet 200, a large-scale benchmark dataset, we show the high performance of the proposed DeepAct model.


Feature Subset for Improving Accuracy of Keystroke Dynamics on Mobile Environment
Sung-Hoon Lee, Jong-hyuk Roh, SooHyung Kim and Seung-Hun Jin
Page: 523~538, Vol. 14, No.2, 2018
10.3745/JIPS.03.0093
Keywords: Feature Subset, Keystroke Dynamics, Smartphone Sensor
Show / Hide Abstract
Keystroke dynamics user authentication is a behavior-based authentication method which analyzes patterns in how a user enters passwords and PINs to authenticate the user. Even if a password or PIN is revealed to another user, it analyzes the input pattern to authenticate the user; hence, it can compensate for the drawbacks of knowledge-based (what you know) authentication. However, users' input patterns are not always fixed, and each user's touch method is different. Therefore, there are limitations to extracting the same features for all users to create a user's pattern and perform authentication. In this study, we perform experiments to examine the changes in user authentication performance when using feature vectors customized for each user versus using all features. User customized features show a mean improvement of over 6% in error equal rate, as compared to when all features are used.


Speaker Verification with the Constraint of Limited Data
Thyamagondlu Renukamurthy Jayanthi Kumari and Haradagere Siddaramaiah Jayanna
Page: 807~823, Vol. 14, No.4, 2018
10.3745/JIPS.01.0030
Keywords: Gaussian Mixture Model (GMM), GMM-UBM, Multiple Frame Rate (MFR), Multiple Frame Size (MFS), MFSR, SFSR
Show / Hide Abstract
Speaker verification system performance depends on the utterance of each speaker. To verify the speaker, important information has to be captured from the utterance. Nowadays under the constraints of limited data, speaker verification has become a challenging task. The testing and training data are in terms of few seconds in limited data. The feature vectors extracted from single frame size and rate (SFSR) analysis is not sufficient for training and testing speakers in speaker verification. This leads to poor speaker modeling during training and may not provide good decision during testing. The problem is to be resolved by increasing feature vectors of training and testing data to the same duration. For that we are using multiple frame size (MFS), multiple frame rate (MFR), and multiple frame size and rate (MFSR) analysis techniques for speaker verification under limited data condition. These analysis techniques relatively extract more feature vector during training and testing and develop improved modeling and testing for limited data. To demonstrate this we have used mel-frequency cepstral coefficients (MFCC) and linear prediction cepstral coefficients (LPCC) as feature. Gaussian mixture model (GMM) and GMM-universal background model (GMM-UBM) are used for modeling the speaker. The database used is NIST-2003. The experimental results indicate that, improved performance of MFS, MFR, and MFSR analysis radically better compared with SFSR analysis. The experimental results show that LPCC based MFSR analysis perform better compared to other analysis techniques and feature extraction techniques.


Texture Image Retrieval Using DTCWT-SVD and Local Binary Pattern Features
Dayou Jiang and Jongweon Kim
Page: 1628~1639, Vol. 13, No.6, 2017
10.3745/JIPS.02.0077
Keywords: Dual-Tree Complex Wavelet Transform, Image Retrieval, Local Binary Pattern, SVD, Texture Feature
Show / Hide Abstract
The combination texture feature extraction approach for texture image retrieval is proposed in this paper. Two kinds of low level texture features were combined in the approach. One of them was extracted from singular value decomposition (SVD) based dual-tree complex wavelet transform (DTCWT) coefficients, and the other one was extracted from multi-scale local binary patterns (LBPs). The fusion features of SVD based multi-directional wavelet features and multi-scale LBP features have short dimensions of feature vector. The comparing experiments are conducted on Brodatz and Vistex datasets. According to the experimental results, the proposed method has a relatively better performance in aspect of retrieval accuracy and time complexity upon the existing methods.


Fingerprint Matching Based on Dimension Reduced DCT Feature Vectors
Sangita Bharkad and Manesh Kokare
Page: 852~862, Vol. 13, No.4, 2017
10.3745/JIPS.02.0017
Keywords: Biometric, Discrete Cosine Transform, Fingerprint Identification, Similarity Measure
Show / Hide Abstract
In this work a Discrete Cosine Transform (DCT)-based feature dimensionality reduced approach for fingerprint matching is proposed. The DCT is applied on a small region around the core point of fingerprint image. The performance of our proposed method is evaluated on a small database of Bologna University and two large databases of FVC2000. A dimensionally reduced feature vector is formed using only approximately 19%, 7%, and 6% DCT coefficients for the three databases from Bologna University and FVC2000, respectively. We compared the results of our proposed method with the discrete wavelet transform (DWT) method, the rotated wavelet filters (RWFs) method, and a combination of DWT+RWF and DWT+(HL+LH) subbands of RWF. The proposed method reduces the false acceptance rate from approximately 18% to 4% on DB1 (Database of Bologna University), approximately 29% to 16% on DB2 (FVC2000), and approximately 26% to 17% on DB3 (FVC2000) over the DWT based feature extraction method.


Wireless Channel Identification Algorithm Based on Feature Extraction and BP Neural Network
Dengao Li*, Gang Wu, Jumin Zhao, Wenhui Niu and Qi Liu
Page: 141~151, Vol. 13, No.1, 2017
10.3745/JIPS.03.0063
Keywords: BP Neural Network, Channel Identification, Feature Extraction, Wireless Communication
Show / Hide Abstract
Effective identification of wireless channel in different scenarios or regions can solve the problems of multipath interference in process of wireless communication. In this paper, different characteristics of wireless channel are extracted based on the arrival time and received signal strength, such as the number of multipath, time delay and delay spread, to establish the feature vector set of wireless channel which is used to train backpropagation (BP) neural network to identify different wireless channels. Experimental results show that the proposed algorithm can accurately identify different wireless channels, and the accuracy can reach 97.59%.


Speech Query Recognition for Tamil Language Using Wavelet and Wavelet Packets
P. Iswarya and V. Radha
Page: 1135~1148, Vol. 13, No.5, 2017
10.3745/JIPS.02.0033
Keywords: De-noising, Feature Extraction, Speech Recognition, Support Vector Machine, Wavelet Packet
Show / Hide Abstract
Speech recognition is one of the fascinating fields in the area of Computer science. Accuracy of speech recognition system may reduce due to the presence of noise present in speech signal. Therefore noise removal is an essential step in Automatic Speech Recognition (ASR) system and this paper proposes a new technique called combined thresholding for noise removal. Feature extraction is process of converting acoustic signal into most valuable set of parameters. This paper also concentrates on improving Mel Frequency Cepstral Coefficients (MFCC) features by introducing Discrete Wavelet Packet Transform (DWPT) in the place of Discrete Fourier Transformation (DFT) block to provide an efficient signal analysis. The feature vector is varied in size, for choosing the correct length of feature vector Self Organizing Map (SOM) is used. As a single classifier does not provide enough accuracy, so this research proposes an Ensemble Support Vector Machine (ESVM) classifier where the fixed length feature vector from SOM is given as input, termed as ESVM_SOM. The experimental results showed that the proposed methods provide better results than the existing methods.


Content-Based Image Retrieval Using Combined Color and Texture Features Extracted by Multi-resolution Multi-direction Filtering
Hee-Hyung Bu, Nam-Chul Kim, Chae-Joo Moon and Jong-Hwa Kim
Page: 464~475, Vol. 13, No.3, 2017
10.3745/JIPS.02.0060
Keywords: Color and Texture Feature, Content-Based Image Retrieval, HSV Color Space, Multi-resolution Multi-direction Filtering
Show / Hide Abstract
In this paper, we present a new texture image retrieval method which combines color and texture features extracted from images by a set of multi-resolution multi-direction (MRMD) filters. The MRMD filter set chosen is simple and can be separable to low and high frequency information, and provides efficient multi- resolution and multi-direction analysis. The color space used is HSV color space separable to hue, saturation, and value components, which are easily analyzed as showing characteristics similar to the human visual system. This experiment is conducted by comparing precision vs. recall of retrieval and feature vector dimensions. Images for experiments include Corel DB and VisTex DB; Corel_MR DB and VisTex_MR DB, which are transformed from the aforementioned two DBs to have multi-resolution images; and Corel_MD DB and VisTex_MD DB, transformed from the two DBs to have multi-direction images. According to the experimental results, the proposed method improves upon the existing methods in aspects of precision and recall of retrieval, and also reduces feature vector dimensions.


A Multiple Features Video Copy Detection Algorithm Based on a SURF Descriptor
Yanyan Hou, Xiuzhen Wang and Sanrong Liu
Page: 502~510, Vol. 12, No.3, 2016
10.3745/JIPS.02.0042
Keywords: Local Invariant Feature, Speeded-Up Robust Features, Video Copy Detection
Show / Hide Abstract
Considering video copy transform diversity, a multi-feature video copy detection algorithm based on a Speeded-Up Robust Features (SURF) local descriptor is proposed in this paper. Video copy coarse detection is done by an ordinal measure (OM) algorithm after the video is preprocessed. If the matching result is greater than the specified threshold, the video copy fine detection is done based on a SURF descriptor and a box filter is used to extract integral video. In order to improve video copy detection speed, the Hessian matrix trace of the SURF descriptor is used to pre-match, and dimension reduction is done to the traditional SURF feature vector for video matching. Our experimental results indicate that video copy detection precision and recall are greatly improved compared with traditional algorithms, and that our proposed multiple features algorithm has good robustness and discrimination accuracy, as it demonstrated that video detection speed was also improved.


A Dataset of Online Handwritten Assamese Characters
Udayan Baruah and Shyamanta M. Hazarika
Page: 325~341, Vol. 11, No.3, 2015
10.3745/JIPS.02.0008
Keywords: Assamese, Character Recognition, Dataset Collection, Data Verification, Online Handwriting, Support Vector Machine
Show / Hide Abstract
This paper describes the Tezpur University dataset of online handwritten Assamese characters. The online data acquisition process involves the capturing of data as the text is written on a digitizer with an electronic pen. A sensor picks up the pen-tip movements, as well as pen-up/pen-down switching. The dataset contains 8,235 isolated online handwritten Assamese characters. Preliminary results on the classification of online handwritten Assamese characters using the above dataset are presented in this paper. The use of the support vector machine classifier and the classification accuracy for three different feature vectors are explored in our research.


Classification of Textured Images Based on Discrete Wavelet Transform and Information Fusion
Chaimae Anibou, Mohammed Nabil Saidi and Driss Aboutajdine
Page: 421~437, Vol. 11, No.3, 2015
10.3745/JIPS.02.0028
Keywords: Discrete Wavelet Transform, Feature Extraction, Fuzzy Set Theory, Information Fusion, Probability Theory, Segmentation, Supervised Classification
Show / Hide Abstract
This paper aims to present a supervised classification algorithm based on data fusion for the segmentation of the textured images. The feature extraction method we used is based on discrete wavelet transform (DWT). In the segmentation stage, the estimated feature vector of each pixel is sent to the support vector machine (SVM) classifier for initial labeling. To obtain a more accurate segmentation result, two strategies based on infor- mation fusion were used. We first integrated decision-level fusion strategies by combining decisions made by the SVM classifier within a sliding window. In the second strategy, the fuzzy set theory and rules based on probability theory were used to combine the scores obtained by SVM over a sliding window. Finally, the per- formance of the proposed segmentation algorithm was demonstrated on a variety of synthetic and real images and showed that the proposed data fusion method improved the classification accuracy compared to applying a SVM classifier. The results revealed that the overall accuracies of SVM classification of textured images is 88%, while our fusion methodology obtained an accuracy of up to 96%, depending on the size of the data base.


Multimodal Biometric Using a Hierarchical Fusion of a Person’s Face, Voice, and Online Signature
Youssef Elmir, Zakaria Elberrichi and Réda Adjoudj
Page: 555~567, Vol. 10, No.4, 2014
10.3745/JIPS.02.0007
Keywords: Hierarchical Fusion, LDA, Multimodal Biometric Fusion, PCA
Show / Hide Abstract
Biometric performance improvement is a challenging task. In this paper, a hierarchical strategy fusion based on multimodal biometric system is presented. This strategy relies on a combination of several biometric traits using a multi-level biometric fusion hierarchy. The multi-level biometric fusion includes a pre-classification fusion with optimal feature selection and a post-classification fusion that is based on the similarity of the maximum of matching scores. The proposed solution enhances biometric recognition performances based on suitable feature selection and reduction, such as principal component analysis (PCA) and linear discriminant analysis (LDA), as much as not all of the feature vectors components support the performance improvement degree.


Optical Character Recognition for Hindi Language Using a Neural-network Approach
Divakar Yadav, Sonia Sánchez-Cuadrado and Jorge Morato
Page: 117~140, Vol. 9, No.1, 2013
10.3745/JIPS.2013.9.1.117
Keywords: OCR, Pre-processing, Segmentation, Feature Vector, Classification, Artificial Neural Network (ANN)
Show / Hide Abstract
Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document"'"s textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.


The Use of MSVM and HMM for Sentence Alignment
Mohamed Abdel Fattah
Page: 301~314, Vol. 8, No.2, 2012
10.3745/JIPS.2012.8.2.301
Keywords: Sentence Alignment, English/ Arabic Parallel Corpus, Parallel Corpora, Machine Translation, Multi-Class Support Vector Machine, Hidden Markov model
Show / Hide Abstract
In this paper, two new approaches to align English-Arabic sentences in bilingual parallel corpora based on the Multi-Class Support Vector Machine (MSVM) and the Hidden Markov Model (HMM) classifiers are presented. A feature vector is extracted from the text pair that is under consideration. This vector contains text features such as length, punctuation score, and cognate score values. A set of manually prepared training data was assigned to train the Multi-Class Support Vector Machine and Hidden Markov Model. Another set of data was used for testing. The results of the MSVM and HMM outperform the results of the length based approach. Moreover these new approaches are valid for any language pairs and are quite flexible since the feature vector may contain less, more, or different features, such as a lexical matching feature and Hanzi characters in Japanese-Chinese texts, than the ones used in the current research


Iris Recognition Using Ridgelets
Lenina Birgale and Manesh Kokare
Page: 445~458, Vol. 8, No.3, 2012
10.3745/JIPS.2012.8.3.445
Keywords: Ridgelets, Texture, Wavelets, Biometrics, Features, Database
Show / Hide Abstract
Image feature extraction is one of the basic works for biometric analysis. This paper presents the novel concept of application of ridgelets for iris recognition systems. Ridgelet transforms are the combination of Radon transforms and Wavelet transforms. They are suitable for extracting the abundantly present textural data that is in an iris. The technique proposed here uses the ridgelets to form an iris signature and to represent the iris. This paper contributes towards creating an improved iris recognition system. There is a reduction in the feature vector size, which is 1X4 in size. The False Acceptance Rate (FAR) and False Rejection Rate (FRR) were also reduced and the accuracy increased. The proposed method also avoids the iris normalization process that is traditionally used in iris recognition systems. Experimental results indicate that the proposed method achieves an accuracy of 99.82%, 0.1309% FAR, and 0.0434% FRR.


ECG Denoising by Modeling Wavelet Sub-Band Coefficients using Kernel Density Estimation
Shubhada Ardhapurkar, Ramchandra Manthalkar and Suhas Gajre
Page: 669~684, Vol. 8, No.4, 2012
10.3745/JIPS.2012.8.4.669
Keywords: Kernel Density Estimation, Discrete Wavelet Transform, Probability Density Function (PDF), Signal to Noise Ratio
Show / Hide Abstract
Discrete wavelet transforms are extensively preferred in biomedical signal processing for denoising, feature extraction, and compression. This paper presents a new denoising method based on the modeling of discrete wavelet coefficients of ECG in selected sub-bands with Kernel density estimation. The modeling provides a statistical distribution of information and noise. A Gaussian kernel with bounded support is used for modeling sub-band coefficients and thresholds and is estimated by placing a sliding window on a normalized cumulative density function. We evaluated this approach on offline noisy ECG records from the Cardiovascular Research Centre of the University of Glasgow and on records from the MIT-BIH Arrythmia database. Results show that our proposed technique has a more reliable physical basis and provides improvement in the Signal-to-Noise Ratio (SNR) and Percentage RMS Difference (PRD). The morphological information of ECG signals is found to be unaffected after employing denoising. This is quantified by calculating the mean square error between the feature vectors of original and denoised signal. MSE values are less than 0.05 for most of the cases.