• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권9호
• /
• pp.4412-4428
• /
• 2018

The purpose of this work is to solve the problem of representing an entire video using Convolutional Neural Network (CNN) features for human action recognition. Recently, due to insufficient GPU memory, it has been difficult to take the whole video as the input of the CNN for end-to-end learning. A typical method is to use sampled video frames as inputs and corresponding labels as supervision. One major issue of this popular approach is that the local samples may not contain the information indicated by the global labels and sufficient motion information. To address this issue, we propose a binary hashing method to enhance the local feature extractors. First, we extract the local features and aggregate them into global features using maximum/minimum pooling. Second, we use the binary hashing method to capture the motion features. Finally, we concatenate the hashing features with global features using different normalization methods to train the classifier. Experimental results on the JHMDB and MPII-Cooking datasets show that, for these new local features, binary hashing mapping on the sparsely sampled features led to significant performance improvements.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.439-441
• /
• 2019

딥러닝은 객체인식 분야에서에서 강력하고, 강건한 학습 알고리즘이다. 딥러닝에서 자주 활용되고, 객체인식 분야에서 최고의 성능을 보여주는 네트워크는 Convolutional Neural Network(CNN) 이다. 숫자 필기 인식을 위한 MNIST 데이터셋를 CNN으로 학습하면 성능이 매우 뛰어나다. 이는 MNIST 데이터 셋의 숫자들이 중앙에 잘 정렬되어 있기 때문이다. 하지만, 실제 데이터들은 중앙에 정렬이 잘 되어있지 않다. 이러한 경우에 CNN은 이전과 같이 우수한 성능을 보여주지 못한다. 이를 해결하기 위해, 우리는 FFT를 활용하여 이미지를 주파수 공간으로 변환하여 입력으로 주는 방법을 제안한다.

• 제어로봇시스템학회논문지
• /
• 제10권9호
• /
• pp.763-770
• /
• 2004

The important issue of emotion recognition from speech is a feature extracting and pattern classification. Features should involve essential information for classifying the emotions. Feature selection is needed to decompose the components of speech and analyze the relation between features and emotions. Specially, a pitch of speech components includes much information for emotion. Accordingly, this paper searches the relation of emotion to features such as the sound loudness, pitch, etc. and classifies the emotions by using the statistic of the collecting data. This paper deals with the method of recognizing emotion from the sound. The most important emotional component of sound is a tone. Also, the inference ability of a brain takes part in the emotion recognition. This paper finds empirically the emotional components from the speech and experiment on the emotion recognition. This paper also proposes the recognition method using these emotional components and the transition probability.

• BMB Reports
• /
• 제41권2호
• /
• pp.93-101
• /
• 2008

The major cell wall components of bacteria are lipopolysaccharide, peptidoglycan, and teichoic acid. These molecules are known to trigger strong innate immune responses in the host. The molecular mechanisms by which the host recognizes the peptidoglycan of Gram-positive bacteria and amplifies this peptidoglycan recognition signals to mount an immune response remain largely unclear. Recent, elegant genetic and biochemical studies are revealing details of the molecular recognition mechanism and the signalling pathways triggered by bacterial peptidoglycan. Here we review recent progress in elucidating the molecular details of peptidoglycan recognition and its signalling pathways in insects. We also attempt to evaluate the importance of this issue for understanding innate immunity.

• 디지털산업정보학회논문지
• /
• 제8권1호
• /
• pp.29-40
• /
• 2012

A challenging research issue that has been one of growing importance to those working in human-computer interaction are to endow a machine with an emotional intelligence. Thus, emotion recognition technology plays an important role in the research area of human-computer interaction, and it allows a more natural and more human-like communication between human and computer. In this paper, we propose the multimodal emotion recognition system using face and speech to improve recognition performance. The distance measurement of the face-based emotion recognition is calculated by 2D-PCA of MCS-LBP image and nearest neighbor classifier, and also the likelihood measurement is obtained by Gaussian mixture model algorithm based on pitch and mel-frequency cepstral coefficient features in speech-based emotion recognition. The individual matching scores obtained from face and speech are combined using a weighted-summation operation, and the fused-score is utilized to classify the human emotion. Through experimental results, the proposed method exhibits improved recognition accuracy of about 11.25% to 19.75% when compared to the most uni-modal approach. From these results, we confirmed that the proposed approach achieved a significant performance improvement and the proposed method was very effective.

• 방송공학회논문지
• /
• 제25권1호
• /
• pp.105-108
• /
• 2020

본 논문은 초고해상도 기법을 이용한 실시간 저해상도 얼굴 인식 시스템을 제안한다. 기존의 비대면 얼굴인식은 거리에 따라 해상도가 저하되면서 얼굴인식의 성능이 저하되는 한계가 있다. 이러한 문제를 해결하기 위해서 초고해상도 기법에 대한 연구도 진행되었으나 비대면 얼굴인식 전 과정에 대한 통합적인 설계에 관한 연구는 미흡하다. 제안한 비대면 얼굴인식은 저해상도 영상으로 키프레임 검출, 얼굴검출, 초고해상도 기법, 특징추출 및 얼굴인식 결과까지 약 2초 이내에 수행함으로써 먼 거리에서도 비대면 얼굴인식의 성능을 향상하였다. 다양한 형태의 영상에 대한 실험을 통해 제안한 방법은 기존 방법에 비해 실시간 및 성능측면에서 저해상도 얼굴 인식이 우수함을 확인하였다.

• 한국간호교육학회지
• /
• 제18권2호
• /
• pp.276-283
• /
• 2012

Purpose: This study was carried out to identify the effects of classroom lectures on adolescent nursing education in distance education. Method: The design of this study was a quasi-experimental research with nonequivalent control group, pretest-posttest design. The subjects of this study were 434 nurses in K open university. Data were collected from April to June, 2009 by the adolescent delinquency measurement scale and questionnaire for awareness of the issue in adolescent health education. Result: The both groups perceived the biggest problem as the lack of assigned education time in adolescent health education. After receiving education, the experimental group improved significantly more than the control group in recognition of adolescent problem behavior which is in interpersonal, intermaterial, order, drug, sex, position, alcohol/smoking delinquency and psychiatric problem. Conclusion: This adolescent nursing education is an effective education for nurses and could improve their recognition of adolescent problem behavior.

• 한국콘텐츠학회논문지
• /
• 제2권4호
• /
• pp.46-50
• /
• 2002

본 논문은 지문 영상의 전처리중 이진화 수행과정에서 지문 영상의 국부적 밝기 차이에 따른 가장 큰 애로점인 임계치(threshold value) 설정을 대상 지문 영역의 밝기 등에 스스로 적응할 수 있도록 Silt Sum 방법을 응용한 적을 이진화를 수행하였다. 기존의 방법과 비교하여 본 연구에서 제시한 개선된 전처리 방법은 보다 높은 인식 정확도를 제공하며, 이에 따라 실험 결과에서 보는 바와 같이 지문 인식을 위한 특징점 추출 알고리즘에 적용될 수 있다.

• 한국멀티미디어학회논문지
• /
• 제19권4호
• /
• pp.681-688
• /
• 2016

In the intelligent video surveillance, recognizing the moving objects is important issue. However, the conventional moving object recognition methods have some problems, that is, the influence of light, the distinguishing between similar colors, and so on. The recognition methods for the moving objects using depth information have been also studied, but these methods have limit of accuracy because the depth camera cannot measure the depth value accurately. In this paper, we propose a recognition method for the moving objects by using both the depth and the color information. The depth information is used for extracting areas of moving object and then the color information for correcting the extracted areas. Through tests with typical videos including moving objects, we confirmed that the proposed method could extract areas of moving objects more accurately than a method using only one of two information. The proposed method can be not only used in CCTV field, but also used in other fields of recognizing moving objects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권4호
• /
• 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.