• The Journal of the Acoustical Society of Korea
• /
• v.26 no.1
• /
• pp.25-31
• /
• 2007

This paper describes an attempt to prevent the external acoustic noise from being misrecognized as the speech recognition target. For this, in the speech activity detection process for the speech recognition, it confirmed besides the acoustic energy to the lip movement image signal of a speaker. First of all, the successive images are obtained through the image camera for PC. The lip movement whether or not is discriminated. And the lip movement image signal data is stored in the shared memory and shares with the recognition process. In the meantime, in the speech activity detection Process which is the preprocess phase of the speech recognition. by conforming data stored in the shared memory the acoustic energy whether or not by the speech of a speaker is verified. The speech recognition processor and the image processor were connected and was experimented successfully. Then, it confirmed to be normal progression to the output of the speech recognition result if faced the image camera and spoke. On the other hand. it confirmed not to output of the speech recognition result if did not face the image camera and spoke. That is, if the lip movement image is not identified although the acoustic energy is inputted. it regards as the acoustic noise.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.979-980
• /
• 2011

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.17 no.5
• /
• pp.68-79
• /
• 2003

In this paper, we propose a system that detects the current speaker in multi-speaker video conference by using lip motion. First, the system detects the face and lip area of each of the speakers using face color and shape information. Then, to detect the current speaker, it calculates the change between the current frame and the previous frame. To accomplish this, we used two CCD cameras. One is a general CCD camera, the other is a PTZ camera controlled by RS-232C serial port. The result is a system capable of detecting the face of current speaker in a video feed with more than three people, regardless of orientation of the faces. With this system, it only takes 4 to 5 seconds to zoom in on the speaker from the initial image. Also, it is amore efficient image transmission system for such things as video conference and internet broadcasting because it offers a face area screen at a resolution of 320X240, while at the same time providing a whole background screen.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.431-438
• /
• 2020

In this paper, the method to extract lip contour by multiple threshold is proposed. Spyridonos et. el. proposed a method to extract lip contour. First step is get Q image from transform of RGB into YIQ. Second step is to find lip corner points by change point detection and split Q image into upper and lower part by corner points. The candidate lip contour can be obtained by apply threshold to Q image. From the candidate contour, feature variance is calculated and the contour with maximum variance is adopted as final contour. The feature variance 'D' is based on the absolute difference near the contour points. The conventional method has 3 problems. The first one is related to lip corner point. Calculation of variance depends on much skin pixels and therefore the accuracy decreases and have effect on the split for Q image. Second, there is no analysis for color systems except YIQ. YIQ is a good however, other color systems such as HVS, CIELUV, YCrCb would be considered. Final problem is related to selection of optimal contour. In selection process, they used maximum of average feature variance for the pixels near the contour points. The maximum of variance causes reduction of extracted contour compared to ground contours. To solve the first problem, the proposed method excludes some of skin pixels and got 30% performance increase. For the second problem, HSV, CIELUV, YCrCb coordinate systems are tested and found there is no relation between the conventional method and dependency to color systems. For the final problem, maximum of total sum for the feature variance is adopted rather than the maximum of average feature variance and got 46% performance increase. By combine all the solutions, the proposed method gives 2 times in accuracy and stability than conventional method.

• Archives of Plastic Surgery
• /
• v.34 no.2
• /
• pp.181-185
• /
• 2007

Purpose: Cleft lip and/or palate is the most common congenital facial anomaly whose incidence is about 1 in 500~1000 live births. As this anomaly may be associated with the serious chromosomal anomalies or the multiple organ abnormalities resulting in the fetal loss or perinatal maternal morbidity and mortality, careful prenatal counseling with early and accurate detection is important. Although conventional prenatal ultrasound(US) examination in midterm pregnancy has been applied for screening of cleft lip, there are definite limitations in the diagnosis of accompanying cleft palate or alveolar cleft. We applied high-resolution 3D US along the serial axial, coronal and sagittal plane so that we could diagnose the cleft palate and/or alveolar cleft in fetuses with cleft lip. Methods: From May 2005 to September 2005, 20 fetuses with cleft lip were examined with prenatal 3D US. Average maternal age was 28.8 years old(24-35 years old), and average gestational age was 24.8 weeks(17.6 to 34.2 weeks). Consecutive axial, coronal and sagittal multislice view were obtained via prenatal 3D US examination and diagnosis of cleft palate and/or alveolar cleft in cleft lip fetuses was followed. Results: With noninvasive and safe prenatal 3D US examination, 17 of 20 cleft lip fetuses were demonstrated to have cleft palate and/or alveolar cleft. Prenatal counseling according to the result was made. Conclusion: Existing prenatal US examination is suitable for screening the cleft lip fetuses but has limitation in identifying the related existence of cleft palate and/ or alveolar cleft. Authors verify the presence of cleft palate and/or alveolar cleft acquiring the successive multislice axial, coronal, and sagittal view with prenatal 3D US examination. Therefore, prenatal 3D US examination could be regarded as a noninvasive and secure screening modality in fetuses with cleft lip for confirming whether cleft palate and/or alveolar cleft is accompanied.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.375-382
• /
• 2003

Lip-reading technique based on bimodal is to enhance speech recognition rate in noisy environment. It is most important to detect the correct lip-image. But it is hard to estimate stable performance in dynamic environment, because of many factors to deteriorate Lip-reading's performance. There are illumination change, speaker's pronunciation habit, versatility of lips shape and rotation or size change of lips etc. In this paper, we propose the IIR filtering in time-domain for the stable performance. It is very proper to remove the noise of speech, to enhance performance of recognition by digital filtering in time domain. While the lip-reading technique in whole lip image makes data massive, the Principal Component Analysis of pre-process allows to reduce the data quantify by detection of feature without loss of image information. For the observation performance of speech recognition using only image information, we made an experiment on recognition after choosing 22 words in available car service. We used Hidden Markov Model by speech recognition algorithm to compare this words' recognition performance. As a result, while the recognition rate of lip-reading using PCA is 64%, Time-domain filter applied to lip-reading enhances recognition rate of 72.4%.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.05a
• /
• pp.341-342
• /
• 2010

• Archives of Plastic Surgery
• /
• v.43 no.2
• /
• pp.153-159
• /
• 2016

Background The prenatal ultrasound detection of cleft lip with or without cleft palate (CL/P) and its continuous management in the prenatal, perinatal, and postnatal periods using a multidisciplinary team approach can be beneficial for parents and their infants. In this report, we share our experiences with the prenatal detection of CL/P and the multidisciplinary management of this malformation in our institution's Congenital Disease Center. Methods The multidisciplinary team of the Congenital Disease Center for mothers of children with CL/P is composed of obstetricians, plastic and reconstructive surgeons, pediatricians, and psychiatrists. A total of 11 fetuses were diagnosed with CL/P from March 2009 to December 2013, and their mothers were referred to the Congenital Disease Center of our hospital. When CL/P is suspected in the prenatal ultrasound screening examination, the pregnant woman is referred to our center for further evaluation. Results The abortion rate was 28% (3/11). The concordance rate of the sonographic and final diagnoses was 100%. Ten women (91%) reported that they were satisfied with the multidisciplinary management in our center. Conclusions Although a child with a birth defect is unlikely to be received well, the women whose fetuses were diagnosed with CL/P on prenatal ultrasound screening and who underwent multidisciplinary team management were more likely to decide to continue their pregnancy.

• Clinical and Experimental Pediatrics
• /
• v.61 no.2
• /
• pp.43-48
• /
• 2018

Purpose: Human adenovirus infection mimics Kawasaki disease (KD) but can be detected in KD patients. The aim of this study was to determine the clinical differences between KD with adenovirus infection and only adenoviral infection and to identify biomarkers for prediction of adenovirus-positive KD from isolated adenoviral infection. Methods: A total of 147 patients with isolated adenovirus were identified by quantitative polymerase chain reaction. In addition, 11 patients having KD with adenovirus, who were treated with intravenous immunoglobulin therapy during the acute phase of KD were also evaluated. Results: Compared with the adenoviral infection group, the KD with adenovirus group was significantly associated with frequent lip and tongue changes, skin rash and changes in the extremities. In the laboratory parameters, higher C-reactive protein (CRP) level and presence of hypoalbuminemia and sterile pyuria were significantly associated with the KD group. In the multivariate analysis, lip and tongue changes (odds ratio [OR], 1.416; 95% confidence interval [CI], 1.151-1.741; P=0.001), high CRP level (OR, 1.039; 95% CI 1.743-1.454; P= 0.021) and sterile pyuria (OR 1.052; 95% CI 0.861-1.286; P=0.041) were the significant predictive factors of KD. In addition, the cutoff CRP level related to KD with adenoviral detection was 56 mg/L, with a sensitivity of 81.8% and a specificity of 75.9%. Conclusion: Lip and tongue changes, higher serum CRP level and sterile pyuria were significantly correlated with adenovirus-positive KD.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.173-176
• /
• 2009

본 논문에서는 피부색 정보와 눈, 입의 위치를 찾아 실시간으로 얼굴을 인식하는 랩을 제안한다. 먼저 노이즈를 제거하여 얼굴 후보 영역을 지정한다. 지정된 얼굴 후보 영역에서 눈과 입을 찾고, 찾은 눈과 입 사이의 영역에서 에지를 탐색하여 코의 존재 유무를 검증하고 이를 바탕으로 얼굴인지 판단하는 절차를 따른다. 제안한 기법은 피부색 검출을 위해 YCbCr 을 이용하여 피부 영역을 찾고 지정한 피부 영역에서 노이즈를 제거한 후, Eye Map의 EyeMapC 연산을 통해 눈을 Lip Map을 통해 입을 찾는다. 찾아낸 눈과 입의 사이의 영역에서 Canny Edge 연산을 수행하여 코의 존재 유무를 판단하여 최종적인 얼굴 영역을 판별하는 방법을 제안한다.