• Phonetics and Speech Sciences
• /
• v.6 no.4
• /
• pp.127-132
• /
• 2014

This paper describes a robust speech recognition technique by reconstructing spectral components mismatched with a training environment. Although the cluster-based reconstruction method can compensate the unreliable components from reliable components in the same spectral vector by assuming an independent, identically distributed Gaussian-mixture process of training spectral vectors, the presented method exploits the temporal dependency of speech to reconstruct the components by introducing a hidden-Markov-model prior which incorporates an internal state transition plausible for an observed spectral vector sequence. The experimental results indicate that the described method can provide temporally consistent reconstruction and further improve recognition performance on average compared to the conventional method.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2355-2358
• /
• 2003

The purpose of this paper is to investigate two major feature extraction techniques based on generic modular face recognition system. Detailed algorithms are described for principal component analysis (PCA) and independent component analysis (ICA). PCA and ICA ate statistical techniques for feature extraction and their incorporation into a face recognition system requires numerous design decisions. We explicitly state the design decisions by introducing a modular-based face recognition system since some of these decision are not documented in the literature. We explored different implementations of each module, and evaluate the statistical feature extraction algorithms based on the FERET performance evaluation protocol (the de facto standard method for evaluating face recognition algorithms). In this paper, we perform two experiments. In the first experiment, we report performance results on the FERET database based on PCA. In the second experiment, we examine performance variations based on ICA feature extraction algorithm. The experimental results are reported using four different categories of image sets including front, lighting, and duplicate images.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2001.11b
• /
• pp.46-51
• /
• 2001

For Fast Real-time Recognition of Nonlinear Error Data, a new Neural Network algorithm which recognized the map in real time is proposed. The proposed neural network technique is the real time computation method through the inter-node diffusion, In the network, a node corresponds to a state in the quantized input space. Each node is composed of a processing unit and fixed weights from its neighbor nodes as well as its input terminal. The most reliable algorithm derived for real time recognition of map, is a dynamic programming based algorithm based on sequence matching techniques that would process the data as it arrives and could therefore provide continuously updated neighbor information estimates. Through several simulation experiments, real time reconstruction of the nonlinear map information is processed,

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.4
• /
• pp.1463-1480
• /
• 2014

It is well known that sparse code is effective for feature extraction of face recognition, especially sparse mode can be learned in the kernel space, and obtain better performance. Some recent algorithms made use of single kernel in the sparse mode, but this didn't make full use of the kernel information. The key issue is how to select the suitable kernel weights, and combine the selected kernels. In this paper, we propose a novel multiple kernel sparse representation based classification for face recognition (MKSRC), which performs sparse code and dictionary learning in the multiple kernel space. Initially, several possible kernels are combined and the sparse coefficient is computed, then the kernel weights can be obtained by the sparse coefficient. Finally convergence makes the kernel weights optimal. The experiments results show that our algorithm outperforms other state-of-the-art algorithms and demonstrate the promising performance of the proposed algorithms.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1001-1007
• /
• 2020

In recent years, machine learning algorithms are continuously being used and expanded in various fields, such as facial recognition, signal processing, personal authentication, and stock prediction. In particular, various algorithms, such as deep learning, reinforcement learning, and Q-learning, are continuously being improved. Among these algorithms, the expansion of deep learning is rapidly changing. Nevertheless, machine learning algorithms have not yet been applied in several fields, such as personal authentication technology. This technology is an essential tool in the digital information era, walking recognition technology as promising biometrics, and technology for solving state-space problems. Therefore, algorithm technologies of deep learning, reinforcement learning, and Q-learning, which are typical machine learning algorithms in various fields, such as agricultural technology, personal authentication, wireless network, game, biometric recognition, and image recognition, are being improved and expanded in this paper.

• Animal cells and systems
• /
• v.12 no.2
• /
• pp.93-96
• /
• 2008

In recent years, we frequently observed missmatched pairs between male Asian toads, Bufo gargarizans, and bullfrogs, Rana catesbeiana, at the toad breeding ponds, where scramble competition for mating occurred among the male toads. Thus, we performed two-choice experiments to investigate recognition ability of mates and species in male toads. The test males did not discriminate sexes, but the clasped stimulus males immediately produced release calls and stopped it while the clasped stimulus female did not. In addition, the test male toads did not discriminate reproductive state of females and even species. However, male toads chose larger individuals. The present results indicate that the main reason of missmatched amplexus by the male toads is due to 1) the lack of recognition cues of conspecifics, 2) the lack of communication tools like release calls, and 3) the larger size of bullfrogs than male toads themselves.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2001.11a
• /
• pp.46-51
• /
• 2001

For Fast Real-time Recognition of Nonlinear Error Data, a new Neural Network algorithm which recognized the map in real time is proposed. The proposed neural network technique is the real time computation method through the inter-node diffusion. In the network, a node corresponds to a state in the quantized input space. Each node is composed of a processing unit and fixed weights from its neighbor nodes as well as its input terminal. The most reliable algorithm derived for real time recognition of map, is a dynamic programming based algorithm based on sequence matching techniques that would process the data as it arrives and could therefore provide continuously updated neighbor information estimates. Through several simulation experiments, real time reconstruction of the nonlinear map information is processed.

• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.758-768
• /
• 2017

In this paper, we present a novel method to extract face representation based on multi-resolution spatial pyramid. In our method, a face is subdivided into increasingly finer sub-regions (local regions) and represented at multiple levels of histogram representations. To cope with misaligned problem, patch-based local descriptor extraction has been also developed in a novel way. To preserve multiple levels of detail in local characteristics and also encode holistic spatial configuration, histograms from all levels of spatial pyramid are integrated by using dimensionality reduction and feature combination, leading to our spatial-pyramid face feature representation. We incorporate our proposed face features into general face recognition pipeline and achieve state-of-the-art results on challenging face recognition problems.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.878-879
• /
• 2021

Most state-of-the-art CNNs for action recognition are based on a two-stream architecture: RGB frames stream represents the appearance and the optical flow stream interprets the motion of action. However, the cost of optical flow computation is very high and then it increases action recognition latency. We introduce a design strategy for action recognition inspired by a two-stream network and teacher-student architecture. There are two sub-networks in our neural networks, the optical flow sub-network as a teacher and the RGB frames sub-network as a student. In the training stage, we distill the feature from the teacher as a baseline to train student sub-network. In the test stage, we only use the student so that the latency reduces without computing optical flow. Our experiments show that its advantages over two-stream architecture in both speed and performance.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.1
• /
• pp.35-43
• /
• 2015

Over the past couple of years, tremendous progress has been made in applying deep learning (DL) techniques to computer vision. Especially, deep convolutional neural networks (DCNNs) have achieved state-of-the-art performance on standard recognition datasets and tasks such as ImageNet Large-Scale Visual Recognition Challenge (ILSVRC). Among them, GoogLeNet network which is a radically redesigned DCNN based on the Hebbian principle and scale invariance set the new state of the art for classification and detection in the ILSVRC 2014. Since there exist various deep learning techniques, this review paper is focusing on techniques directly related to DCNNs, especially those needed to understand the architecture and techniques employed in GoogLeNet network.