• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2002년도 춘계종합학술대회
• /
• pp.134-138
• /
• 2002

The human faces do not have distinct features unlike other general objects. In general the features of eyes, nose and mouth which are first recognized when human being see the face are defined. These features have different characteristics depending on different human face. In this paper, We propose a face recognition algorithm using the hidden Markov model(HMM). In the preprocessing stage, we find edges of a face using the locally adaptive threshold scheme and extract features based on generic knowledge of a face, then construct a database with extracted features. In training stage, we generate HMM parameters for each person by using the forward-backward algorithm. In the recognition stage, we apply probability values calculated by the HMM to input data. Then the input face is recognized by the euclidean distance of face feature vector and the cross-correlation between the input image and the database image. Computer simulation shows that the proposed HMM algorithm gives higher recognition rate compared with conventional face recognition algorithms.

• 한국산업정보학회논문지
• /
• 제13권3호
• /
• pp.54-62
• /
• 2008

가장 일반적이고 효과적으로 사용하는 혼합된 정보은닉 기술인 스테가노그래피에서 의사소통의 존재를 숨기면서 송수신하는 자료은닉 기술과 관련된 통계적 기법을 적용하는 연구가 필요하다. 즉, 인터넷상에 존재하는 임의의 원본이미지에 비밀(은닉) 메시지가 포함된 변조된 혼합이미지를 가장 효과적으로 관리하고 찾아내는 감지 기법의 연구가 필요하다. 이 논문에서 원본이미지에 비밀자료를 숨기기 위한 스테가노그래피에 RGB, DCT 및 EWM 통계기법을 이용하여 은닉자료를 감지하고 그 위치를 찾는 기법을 확인한다. 그리고 카이스퀘어 검정법을 이용하는 기존의 방법과 비교한다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.560-567
• /
• 1998

This paper concerned about a imputed color printed material image in camera to decrease noise and distortion by processing median filtering with input image to identical condition. Also this paper proposed the way of compares a normal printed material with an abnormal printed material color tone with trained a learning of the error back-propagation to block classification by extracting five place from identical block(3${\times}$3) of color printed material R, G, B value. As a representative algorithm of multi-layer perceptron the error Back-propagation technique used to solve complex problems. However, the Error Back-propagation is algorithm which basically used a gradient descent method which can be converged to local minimum and the Back Propagation train include problems, and that may converge in a local minimum rather than get a global minimum. The network structure appropriate for a given problem. In this paper, a good result is obtained by improve initial condition and adjust th number of hidden layer to solve the problem of real time process, learning and train.

• 한국멀티미디어학회논문지
• /
• 제22권5호
• /
• pp.547-557
• /
• 2019

To extract the depth map from a single image, a number of CNN-based deep learning methods have been performed in recent research. In this study, the GAN structure of Pix2Pix is maintained. this model allows to converge well, because it has the structure of the generator and the discriminator. But the convolution in this model takes a long time to compute. So we change the convolution form in the generator to a depthwise convolution to improve the speed while preserving the result. Thus, the seven down-sizing convolutional hidden layers in the generator U-Net are changed to depthwise convolution. This type of convolution decreases the number of parameters, and also speeds up computation time. The proposed model shows similar depth map prediction results as in the case of the existing structure, and the computation time in case of a inference is decreased by 64%.

• 로봇학회논문지
• /
• 제17권2호
• /
• pp.133-141
• /
• 2022

This paper introduces model compression algorithms which make a deep neural network smaller and faster for embedded systems. The model compression algorithms can be largely categorized into pruning, quantization and knowledge distillation. In this study, gradual pruning, quantization aware training, and knowledge distillation which learns the activation boundary in the hidden layer of the teacher neural network are integrated. As a large deep neural network is compressed and accelerated by these algorithms, embedded computing boards can run the deep neural network much faster with less memory usage while preserving the reasonable accuracy. To evaluate the performance of the compressed neural networks, we evaluate the size, latency and accuracy of the deep neural network, DenseNet201, for image classification with CIFAR-10 dataset on the NVIDIA Jetson Xavier.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권3호
• /
• pp.1390-1403
• /
• 2016

Facial expression recognition (FER) plays a very significant role in computer vision, pattern recognition, and image processing applications such as human computer interaction as it provides sufficient information about emotions of people. For video-based facial expression recognition, depth cameras can be better candidates over RGB cameras as a person's face cannot be easily recognized from distance-based depth videos hence depth cameras also resolve some privacy issues that can arise using RGB faces. A good FER system is very much reliant on the extraction of robust features as well as recognition engine. In this work, an efficient novel approach is proposed to recognize some facial expressions from time-sequential depth videos. First of all, efficient Local Binary Pattern (LBP) features are obtained from the time-sequential depth faces that are further classified by Generalized Discriminant Analysis (GDA) to make the features more robust and finally, the LBP-GDA features are fed into Hidden Markov Models (HMMs) to train and recognize different facial expressions successfully. The depth information-based proposed facial expression recognition approach is compared to the conventional approaches such as Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Linear Discriminant Analysis (LDA) where the proposed one outperforms others by obtaining better recognition rates.

• 전기학회논문지
• /
• 제63권6호
• /
• pp.813-819
• /
• 2014

The purpose of this study was to extract accurate parameters of facial movement features using 3-D motion capture system in speech recognition technology through lip-reading. Instead of using the features obtained through traditional camera image, the 3-D motion system was used to obtain quantitative data for actual facial movements, and to analyze 11 variables that exhibit particular patterns such as nose, lip, jaw and cheek movements in monosyllable vocalizations. Fourteen subjects, all in 20s of age, were asked to vocalize 11 types of Korean vowel monosyllables for three times with 36 reflective markers on their faces. The obtained facial movement data were then calculated into 11 parameters and presented as patterns for each monosyllable vocalization. The parameter patterns were performed through learning and recognizing process for each monosyllable with speech recognition algorithms with Hidden Markov Model (HMM) and Viterbi algorithm. The accuracy rate of 11 monosyllables recognition was 97.2%, which suggests the possibility of voice recognition of Korean language through quantitative facial movement analysis.

• 한국통신학회논문지
• /
• 제30권2C호
• /
• pp.31-40
• /
• 2005

오류 역전파 알고리즘의 문제점과 ART 신경회로망의 문제점을 개선하기 위해 Jacobs가 제안한 delta-bar-delta 방법과 신경회로망을 결합한 자가 생성 지도 학습 알고리듬을 제안한다. 입력층과 은닉층에서는 ART-1과 ART-2 알고리듬을 이용하고, winner-take-all 방식은 완전 연결 구조이나 연결된 가중치만을 조정하도록 채택하였다. 실험을 위해 학생증, 주민등록증, 컨테이너의 영상으로 추출한 패턴을 신경회로망의 은닉층 노드에 대해 실험하였고, 실험결과 제안된 자기 생성 지도 학습알고리듬이 지역최소화, 학습 속도, 정체 현상이 기존의 방법보다 성능이 개선된 것을 확인하였다.

• 한국산업정보학회논문지
• /
• 제15권3호
• /
• pp.51-57
• /
• 2010

스테가노그래피는 이미지의 외적인 면에서 미세한 변화를 가진 디지털 이미지에 자료를 은닉하기 위해 사용된다. 은닉이미지가 의심되는 스테고 신호 분석에서 개선된 통계량을 이용하여 갑작스러운 변화를 신속, 정확하게 감지하는 기법의 개발이 필요하다. 이 논문에서는 축차적인 스테가노그래피에서 은닉된 메시지를 감지하고 그 위치를 찾아내는 방법을 제시한다. 즉, 검사하는 이미지에 은닉메시지의 존재 유무를 결정하고 그 위치를 찾아낼 때까지 CUSUM-SPRT 스테간 분석을 기반으로 하는 통계적 검정을 반복한다. 논문에서 일반화된 수식을 위해 개선된 $S^{t^*}_j$를 이용한 통계량 $g_t$를 사용한다.

• 한국멀티미디어학회논문지
• /
• 제7권3호
• /
• pp.327-339
• /
• 2004

본 논문에서는 반복적인 에러 최소화 기법을 이용한 하프톤 영상의 워터마킹 알고리즘을 제안하였다. 워터마크는 하프톤 영상의 랜덤한 위치의 픽셀값으로 저장된다. 삽입된 워터마크로 인한 하프톤 영상의 왜곡을 최소화하고 비가시성을 증대하기 위하여 반복적인 에러 최소화 기법이 사용된다. 원영상과 HVS(Human Visual System) 필터 처리된 하프톤 영상과의 차이를 하프토닝 에러로 정의하고 반복적으로 각각의 픽셀 위치에서 이 하프토닝 에러를 최소화할 수 있는 픽셀 패턴을 찾아서 이것으로 원래의 픽셀패턴을 대치한다. 절단이나 회전과 같은 기하학적인 변형에 견고하게 하기 위하여 동일한 워터마크를 반복하여 하프톤 영상안에 삽입하였다. 실제 인쇄 및 스캐닝 실험을 통하여 제안된 알고리즘이 기하학적 변형에 견고함을 보였고 또한 기존과 방법과 비교하여 제안된 방법이 많은 양의 워터마크 정보에도 불구하고 우수한 품질의 하프톤 영상을 생성함을 보였다.