• The Journal of the Korea Contents Association
• /
• v.17 no.1
• /
• pp.137-144
• /
• 2017

Face detection is still a challenging task under severe face pose variations in complex background. This paper proposes an effective algorithm which can detect single or multiple faces based on skin color detection and depth information. We introduce Gaussian mixture model(GMM) for skin color detection in a color image. The depth information is from three dimensional depth sensor of Kinect V2 device, and is useful in segmenting a human body from the background. Then, a labeling process successfully removes non-face region using several features. Experimental results show that the proposed face detection algorithm can provide robust detection performance even under variable conditions and complex background.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.12A
• /
• pp.1198-1204
• /
• 2006

In this paper, we extend SVR-MMSE detection scheme which is proposed in MIMO system to MIMO-OFDM system, and evaluate performance of the system in frequency selective fading channel. First of all, we explain about typical MIMO-OFDM system and detection scheme of constant modulus signals in this system. And compare proposed SVR-MMSE with Zero Forcing, Minimum Mean Square Error which is conventional detection scheme. we identify that the performance of the proposed system is shown different by varying doppler frequency in frequency selective fading channel using jakes channel model. The result of detection performance by the proposed SVR-MMSE in this simulation, it shows that proposed algorithm have a good performance in MIMO-OFDM systems.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.1057-1062
• /
• 2007

얼굴표정 인식은 심리학 연구, 얼굴 애니메이션 합성, 로봇공학, HCI(Human Computer Interaction) 등 다양한 분야에서 중요성이 증가하고 있다. 얼굴표정은 사람의 감정 표현, 관심의 정도와 같은 사회적 상호작용에 있어서 중요한 정보를 제공한다. 얼굴표정 인식은 크게 정지영상을 이용한 방법과 동영상을 이용한 방법으로 나눌 수 있다. 정지영상을 이용할 경우에는 처리량이 적어 속도가 빠르다는 장점이 있지만 얼굴의 변화가 클 경우 매칭, 정합에 의한 인식이 어렵다는 단점이 있다. 동영상을 이용한 얼굴표정 인식 방법은 신경망, Optical Flow, HMM(Hidden Markov Models) 등의 방법을 이용하여 사용자의 표정 변화를 연속적으로 처리할 수 있어 실시간으로 컴퓨터와의 상호작용에 유용하다. 그러나 정지영상에 비해 처리량이 많고 학습이나 데이터베이스 구축을 위한 많은 데이터가 필요하다는 단점이 있다. 본 논문에서 제안하는 실시간 얼굴표정 인식 시스템은 얼굴영역 검출, 얼굴 특징 검출, 얼굴표정 분류, 아바타 제어의 네 가지 과정으로 구성된다. 웹캠을 통하여 입력된 얼굴영상에 대하여 정확한 얼굴영역을 검출하기 위하여 히스토그램 평활화와 참조 화이트(Reference White) 기법을 적용, HT 컬러모델과 PCA(Principle Component Analysis) 변환을 이용하여 얼굴영역을 검출한다. 검출된 얼굴영역에서 얼굴의 기하학적 정보를 이용하여 얼굴의 특징요소의 후보영역을 결정하고 각 특징점들에 대한 템플릿 매칭과 에지를 검출하여 얼굴표정 인식에 필요한 특징을 추출한다. 각각의 검출된 특징점들에 대하여 Optical Flow알고리즘을 적용한 움직임 정보로부터 특징 벡터를 획득한다. 이렇게 획득한 특징 벡터를 SVM(Support Vector Machine)을 이용하여 얼굴표정을 분류하였으며 추출된 얼굴의 특징에 의하여 인식된 얼굴표정을 아바타로 표현하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.11C
• /
• pp.1161-1168
• /
• 2003

In this paper, we propose an improved statistical model-based voice activity detection algorithm and threshold update method. We first improve signal-to-noise ratio by using speech enhancement preprocessing algorithm combined power subtraction method and matched filter, then apply it to LLR test optimum decision rule for improving the performance even in low SNR conditions. And we propose an adaptive threshold update method that was not concerned in any papers. We also perform extensive computer simulations to demonstrate the performance improvement of the proposed VAD algorithm employing the proposed speech enhancement preprocessing algorithm and adaptive threshold update method under various background noise environments. Finally we verify our results by comparing ITU-T G.729 Annex B.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.913-915
• /
• 2005

임의의 영상에서 얼굴을 검출하는 것은 얼굴을 인식하는데 있어서 선행되어야 할 필수과정이다. 본 논문은 조명의 변화가 심한 컬러영상에서 얼굴을 검출하는 것을 목적으로 한다. 본 논문은 기존의 기하학적 밝기분포 마스크만을 사용한 방법이 조명 변화에 취약한 단점을 보완하는데 중점을 두었다. 히스토그램 평활화(Histogram Equalization : HE)와 감마 크기 보정 (Gamma Intensity Correction : GIC) 방법을 이용해서 조명에 대한 간섭을 줄인 후, 영상 전체에서 피부 영역을 추출하고 이어서 눈 후보들을 검출한다. 검출된 눈 후보들로부터 기하학적 밝기분포 마스크를 적용하여 효과적으로 얼굴 후보들을 찾을 수 있고, 이렇게 찾아진 얼굴 후보들은 주성분분석법(Principal Component Analysis : PCA)를 이용해서 얼굴인지 여부를 판별하게 된다. 본 알고리즘은 조명 밝기 등으로 인해 검출률이 떨어졌던 단점을 보완할 수 있었고, 향후 얼굴 검출 분야에 있어서도 활용 가치가 있을 것으로 생각된다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.7 no.1
• /
• pp.55-60
• /
• 2014

In this paper, we proposed a method for face region extraction by skin-color hue, saturation and facial feature extraction in natural images. The proposed algorithm is composed of lighting correction and face detection process. In the lighting correction step, performing correction function for a lighting change. The face detection process extracts the area of skin color by calculating Euclidian distances to the input images using as characteristic vectors color and chroma in 20 skin color sample images. Eye detection using C element in the CMY color model and mouth detection using Q element in the YIQ color model for extracted candidate areas. Face area detected based on human face knowledge for extracted candidate areas. When an experiment was conducted with 10 natural images of face as input images, the method showed a face detection rate of 100%.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.45-46
• /
• 2021

본 논문에서는 제조산업의 제품 품질검사의 자동화를 위한 딥러닝 기법을 제안하고 모델의 성능 최적화를 위한 특징 추출 필터의 크기를 비교한다. 이미지 특징을 자동 추출할 수 있는 CNN을 사용하여 전문인력 없이 제품의 표면 결함을 검출하고 제품의 적합성을 판단할 수 있는 이미지 처리 알고리즘을 구축하고 산업 현장에 적용하기 위한 검증 지표로 검출 정확도와 연산속도를 측정하여 결함 검출 알고리즘의 성능을 확인한다. 또한 연산량에 따른 성능 비교를 위해 필터의 크기에 따른 CNN의 성능을 비교하여 결함 검출 알고리즘의 성능을 최적화한다. 본 논문에서는 커널의 크기를 다르게 적용했을 때 빠른 연산으로 높은 정확도의 검출 결과를 얻었다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.3
• /
• pp.8-14
• /
• 2009

A Hidden Markov Model(HMM)-based information extraction method is proposed in this paper. The proposed extraction method is applied to extraction of products' prices. The input of the proposed IESHMM is the URLs of a search engine's interface, which contains the names of the product types. The output of the system is the list of extracted slots of each product: name, price, image, and URL. With the observation data set Maximum Likelihood algorithm and Baum-Welch algorithm are used for the training of HMM and The Viterbi algorithm is then applied to find the state sequence of the maximal probability that matches the observation block sequence. When applied to practical problems, the proposed HMM-based system shows improved results over a conventional method, PEWEB, in terms of recall ration and accuracy.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1635-1640
• /
• 2017

In this paper, a hierarchical image tree model for weather classification is defined in a single outdoor image, and a weather classification algorithm using image intensity and k-mean segmentation image is proposed. In the first level of the hierarchical image tree model, the indoor and outdoor images are distinguished. Whether the outdoor image is daytime, night, or sunrise/sunset image is judged using the intensity and the k-means segmentation image at the second level. In the last level, if it is classified as daytime image at the second level, it is finally estimated whether it is sunny or foggy image based on edge map and fog rate. Some experiments are conducted so as to verify the weather classification, and as a result, the proposed method shows that weather features are effectively detected in a given image.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1581-1587
• /
• 2020

With the emergence of convolutional neural network in the field of machine learning, the model for solving image processing problems has seen rapid development. However, the computing resources required are also rising, making it difficult to learn from a typical environment. Attention mechanism is originally proposed to prevent the gradient vanishing problem of the recurrent neural network, but this can also be used in a direction favorable to learning of the convolutional neural network. In this paper, attention mechanism is applied to convolutional neural network, and the excellence of the proposed method is demonstrated through the comparison of learning time and performance difference at this time. The proposed model showed that both learning time and performance were superior in object detection based on YOLO compared to models without attention mechanism, and experimentally demonstrated that learning time could be significantly reduced. In addition, this is expected to increase accessibility to machine learning by end users.