• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.4
• /
• pp.262-268
• /
• 2017

Intelligent video surveillance systems have been developed to monitor global areas and find specific target objects using a large-scale database. However, person re-identification presents some challenges, such as pose change and occlusions. To solve the problems, this paper presents an improved person re-identification method using sparse representation and saliency-based dictionary construction. The proposed method consists of three parts: i) feature description based on salient colors and textures for dictionary elements, ii) orthogonal atom selection using cosine similarity to deal with pose and viewpoint change, and iii) measurement of reconstruction error to rank the gallery corresponding a probe object. The proposed method provides good performance, since robust descriptors used as a dictionary atom are generated by weighting some salient features, and dictionary atoms are selected by reducing excessive redundancy causing low accuracy. Therefore, the proposed method can be applied in a large scale-database surveillance system to search for a specific object.

• Proceeding of Spring/Autumn Annual Conference of KHA
• /
• 2003.11a
• /
• pp.301-306
• /
• 2003

The main gate of university is a symbolic role to grasp the its activities within a limited area. The form or shape is various at its circumstances such as activity type, region, etc. The study aimed at offering the information to grasp the fixed quantity to an university gate plan which analyzed a psychological judgment criteria according to form or shape characteristics of the university main gate. It selected ten universities through a classification of the types. The twenty adjective phrases were extracted by review of the further research. After then, it extracted to draw high adjective in observers visual image formation. This study analyzed the preference, symbolized representation of the university main gate. The results are summarized as follows : 1. The symbol and representation of form has a high correlation. In other words, the symbolic scale would be high positively when the representation scale be high. 2. Eight items among the twenty adjective items appeared to explain the university main gates. The twelve items of them wouldn't be related to grasp the main gate

• Journal of KIISE:Software and Applications
• /
• v.31 no.10
• /
• pp.1412-1417
• /
• 2004

Sparse coding or independent component analysis (ICA) which is a holistic representation, was successfully applied to elucidate early auditor${\gamma}$ processing and to the task of sound classification. In contrast, parts-based representation is an alternative way o) understanding object recognition in brain. In this thesis we employ the non-negative matrix factorization (NMF) which learns parts-based representation in the task of sound classification. Methods of feature extraction from the spectro-temporal sounds using the NMF in the absence or presence of noise, are explained. Experimental results show that NMF-based features improve the performance of sound classification over ICA-based features.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.12
• /
• pp.5464-5484
• /
• 2016

Few samples face recognition has become a highly challenging task due to the limitation of available labeled samples. As two popular paradigms in face image representation, sparse component analysis is highly robust while parts-based paradigm is particularly flexible. In this paper, we propose a probabilistic generative model to incorporate the strengths of the two paradigms for face representation. This model finds a common spatial partition for given images and simultaneously learns a sparse component analysis model for each part of the partition. The two procedures are built into a probabilistic generative model. Then we derive the score function (i.e. feature mapping) from the generative score space. A similarity measure is defined over the derived score function for few samples face recognition. This model is driven by data and specifically good at representing face images. The derived generative score function and similarity measure encode information hidden in the data distribution. To validate the effectiveness of the proposed method, we perform few samples face recognition on two face datasets. The results show its advantages.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.90-98
• /
• 2018

A Multilinear LDA Method of Tensor Representation for ECG Signal Based Individual Identification Electrocardiogram signals, included in the cardiac electrical activity, are often analyzed and used for various purposes such as heart rate measurement, heartbeat rhythm test, heart abnormality diagnosis, emotion recognition and biometrics. The objective of this paper is to perform individual identification operation based on Multilinear Linear Discriminant Analysis (MLDA) with the tensor feature. The MLDA can solve dimensional aspects of classification problems in high-dimensional tensor, and correlated subspaces can be used to distinguish between different classes. In order to evaluate the performance, we used MPhysionet's MIT-BIH database. The experimental results on this database showed that the individual identification by MLDA outperformed that by PCA and LDA.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.2093-2108
• /
• 2017

In this paper, we describe a novel method for recognizing human actions from different views via view knowledge transfer. Our approach is characterized by two aspects: 1) We propose a unsupervised topic transfer model (TTM) to model two view-dependent vocabularies, where the original bag of visual words (BoVW) representation can be transferred into a bag of topics (BoT) representation. The higher-level BoT features, which can be shared across views, can connect action models for different views. 2) Our features make it possible to obtain a discriminative model of action under one view and categorize actions in another view. We tested our approach on the IXMAS data set, and the results are promising, given such a simple approach. In addition, we also demonstrate a supervised topic transfer model (STTM), which can combine transfer feature learning and discriminative classifier learning into one framework.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.6
• /
• pp.1964-1981
• /
• 2014

An improved Mean-Shift (MS) tracker called joint CB-LBWH, which uses a combined weighted-histogram scheme of CBWH (Corrected Background-Weighted Histogram) and LBWH (likelihood-based Background-Weighted Histogram), is presented. Joint CB-LBWH is based on the notion that target representation employs both feature saliency and confidence to form a compound weighted histogram criterion. As the more prominent and confident features mean more significant for tracking the target, the tuned histogram by joint CB-LBWH can reduce the interference of background in target localization effectively. Comparative experimental results show that the proposed joint CB-LBWH scheme can significantly improve the efficiency and robustness of MS tracker when heavy occlusions and complex scenes exist.

• Journal of Biomedical Engineering Research
• /
• v.21 no.2
• /
• pp.165-174
• /
• 2000

본 논문에서는 M 채널 필터 뱅크를 이용하여 심전도 자동 진단 시스템에서 매우 중요한 파라미터로 사용되는 QRS complex 검출을 실시하였다. 제안된 알고리즘에서는 심전도 신호를 M개의 균일한 주파수 대역으로 분할(decomposition)하고, 분할된 서브밴드(subband) 신호들 중에서 QRS complex의 에너지 분포가 가장 많이 존재하는 5∼25Hz 영역의 서브밴드 신호들을 선택하여 feature를 계산함으로써 QRS complex 검출을 실시하였다. 제안된 알고리즘의 성능 비교를 위하여 MIT-BIH arrhythmia database를 사용하였으며, sensitivity는 99.82%, positive predictivity는 99.82, 평균 검출율은 99.67%로 기존의 알고리즘에 비해 높은 검출 성능을 나타내었다. 또한 polyphase representation을 이용하여 M 채널 필터 뱅크를 구현한 결과 연산 시간이 단추되어 실시간 검출이 가능함을 확인하였다.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.327-338
• /
• 2022

Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.4
• /
• pp.210-216
• /
• 2005

We Propose a new feature normalization scheme based on eigenspace for achieving robust speech recognition. In general, mean and variance normalization (MVN) is Performed in cepstral domain. However, another MVN approach using eigenspace was recently introduced. in that the eigenspace normalization Procedure Performs normalization in a single eigenspace. This Procedure consists of linear PCA matrix feature transformation followed by mean and variance normalization of the transformed cepstral feature. In this method. 39 dimensional feature distribution is represented using only a single eigenspace. However it is observed to be insufficient to represent all data distribution using only a sin91e eigenvector. For more specific representation. we apply unique na independent eigenspaces to cepstra, delta and delta-delta cepstra respectively in this Paper. We also normalize training data in eigenspace and get the model from the normalized training data. Finally. a feature space rotation procedure is introduced to reduce the mismatch of training and test data distribution in noisy condition. As a result, we obtained a substantial recognition improvement over the basic eigenspace normalization.