• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.403-410
• /
• 2004

Bimodal speech recognition systems have been proposed for enhancing recognition rate of ASR under noisy environments. Visual feature extraction is very important to develop these systems. To extract visual features, it is necessary to detect exact lip position. This paper proposed the method that detects a lip position using color similarity model and SVM. Face/Lip color distribution is teamed and the initial lip position is found by using that. The exact lip position is detected by scanning neighbor area with SVM. By experiments, it is shown that this method detects lip position exactly and fast.

• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.227-232
• /
• 2010

This paper proposes the real time lip reading method in the embedded environment. The embedded environment has the limited sources to use compared to existing PC environment, so it is hard to drive the lip reading system with existing PC environment in the embedded environment in real time. To solve the problem, this paper suggests detection methods of lip region, feature extraction of lips, and awareness methods of phonetic words suitable to the embedded environment. First, it detects the face region by using face color information to find out the accurate lip region and then detects the exact lip region by finding the position of both eyes from the detected face region and using the geometric relations. To detect strong features of lighting variables by the changing surroundings, histogram matching, lip folding, and RASTA filter were applied, and the properties extracted by using the principal component analysis(PCA) were used for recognition. The result of the test has shown the processing speed between 1.15 and 2.35 sec. according to vocalizations in the embedded environment of CPU 806Mhz, RAM 128MB specifications and obtained 77% of recognition as 139 among 180 words were recognized.

• Journal of Advanced Navigation Technology
• /
• v.15 no.4
• /
• pp.672-679
• /
• 2011

In this paper, detection algorithm of face region based on skin color of in the TV images is proposed. In the first, reference image is set to the sampled skin color, and then the extracted of face region is candidated using the Euclidean distance between the pixels of TV image. The eye image is detected by using the mean value and standard deviation of the component forming color difference between Y and C through the conversion of RGB color into CMY color model. Detecting the lips image is calculated by utilizing Q component through the conversion of RGB color model into YIQ color space. The detection of the face region is extracted using basis of knowledge by doing logical calculation of the eye image and lips image. To testify the proposed method, some experiments are performed using front color image down loaded from TV color image. Experimental results showed that face region can be detected in both case of the irrespective location & size of the human face.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.478-484
• /
• 2009

Automatic speech recognition(ASR) is attractive technique in trend these day that seek convenient life. Although many approaches have been proposed for ASR but the performance is still not good in noisy environment. Now-a-days in the state of art in speech recognition, ASR uses not only the audio information but also the visual information. In this paper, We present a novel lip detection method for visual speech recognition in mobile environment. In order to apply visual information to speech recognition, we need to extract exact lip regions. Because eye-detection is more easy than lip-detection, we firstly detect positions of left and right eyes, then locate lip region roughly. After that we apply K-means clustering technique to devide that region into groups, than two lip corners and lip center are detected by choosing biggest one among clustered groups. Finally, we have shown the effectiveness of the proposed method through the experiments based on samsung AVSR database.

• The KIPS Transactions:PartB
• /
• v.10B no.4
• /
• pp.465-472
• /
• 2003

For an effective pre-treatment process of a face input image, it is necessary to detect each of face components, calculate the face area, and estimate the rotary angle of the face. A proposed method of this study can estimate an robust result under such renditions as some different levels of illumination, variable fate sizes, fate rotation angels, and background color similar to skin color of the face. The first step of the proposed method detects the estimated face area that can be calculated by both adapted skin color Information of the band-wide HSV color coordinate converted from RGB coordinate, and skin color Information using histogram. Using the results of the former processes, we can detect a lip area within an estimated face area. After estimating a rotary angle slope of the lip area along the X axis, the method determines the face shape based on face information. After detecting eyes in face area by matching a partial template which is made with both eyes, we can estimate Y axis rotary angle by calculating the eye´s locations in three dimensional space in the reference of the face area. As a result of the experiment on various face images, the effectuality of proposed algorithm was verified.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.741-744
• /
• 2002

본 논문에서는 3D 모델의 눈 변형을 계산하기 위해 검출된 눈 형태를 이용한 눈 움직임 합성 방법을 제안하였다. 얼굴 특징들의 정확한 위치 측정과 추적은 MPEG-4 코딩 시스템을 기반으로 한 고품질 모델 개발에 중요하다. 매우 낮은 비트율의 영상회의 응용에서 시간의 경과에 따라 눈과 입술의 움직임을 정확히 추적하기 위해 얼굴 특징들의 정확한 위치 측정과 추적이 필요하다. 이들의 움직임은 코딩되어지고 원격지로 전송되어 질 수 있다. 애니메이션 기술은 얼굴 모델에서 움직임을 합성하는데 이용되어진다. 본 논문에서는 얼굴 특징 검출과 추적 알고리즘으로 잘 알려지고, 효과적으로 향상시킬 수 있는 휴리스틱 방법을 제안하겠다. 본 논문에서는 눈 움직임의 검출뿐만 아니라 추적, 모델링에도 초점을 두었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.313-315
• /
• 2006

본 연구에서는 실내에서 입력받은 영상의 조명과 크기 변화 등에 강인한 얼굴 검출 기법을 소개한다. 제안된 얼굴 검출 기법은 후보 영역 선정 과정과 얼굴패턴 검출 과정, 얼굴 영역 보정 과정으로 이루어진다. 후보 영역 선정 과정에서는 조명보정과 색상 필터, 움직임 필터를 이용하여 얼굴패턴의 후보 영역을 선정한다. 얼굴패턴 검출 과정에서는 CNN을 이용하여 특징을 추출하고, WFMM 신경망을 이용하여 얼굴 패턴을 검증한다. 얼굴 영역 보정 과정은 형태학적 연산 등의 영상 처리를 이용하여 눈 영역과 입술 영역의 위치를 판별한 후 최종적인 얼굴 영역을 결정한다.

• The KIPS Transactions:PartB
• /
• v.8B no.2
• /
• pp.183-188
• /
• 2001

이 논문은 눈의 형태에 대한 정보를 이용하여 눈동자를 효과적으로 찾는 방법과 얼굴 특성을 반영하는 평가함수를 이용하여 눈동자, 입의 위치와 같은 얼굴 특징들을 인식하는 방법을 제안하였다. 색 정보를 이용하여 입술과 얼굴 영역을 추출하고 눈동자와 흰자위간의 명도 차를 이용하는 함수를 사용하여 눈동자를 인식하였다. 마지막으로 얼굴 특성을 반영하느 평가함수를 정의하고 이를 이용하여 최종적인 얼굴과 눈, 입을 인식하였다. 제안한 방법을 사용하여 여러 영상들에 대해 실험하여 좋은 결과를 얻었다.

• Journal of Korea Multimedia Society
• /
• v.8 no.11
• /
• pp.1439-1448
• /
• 2005

In this paper, after similarity of color information in above toro and geometry position analysis of important characteristic information in face and abstraction object that is inputted detects face area using comparison, describe about method to do user certification using ratio information and hair spring degree. Face abstraction algorithm that use color information has comparative advantages than face abstraction algorithm that use form information because have advantage that is not influenced facial degree or site etc. that tip. Because is based on color information, change of lighting or to keep correct performance because is sensitive about color such as background similar to complexion is difficult. Therefore, can be used more efficiently than method to use color information as that detect characteristic information of eye and lips etc. that is facial importance characteristic element except color information and similarity for each object achieves comparison. This paper proposes system that eye and mouth's similarity that calculate characteristic that is ratio red of each individual after divide face by each individual and is segmentalized giving weight in specification calculation recognize user confirming similarity through search. Could experiment method to propose and know that the awareness rate through analysis with the wave rises.