• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.186-188
• /
• 2005

Hand region detection in images is an important process in many computer vision applications. It is a process that usually starts at a pixel-level, and that involves a pre-process of color space transformation followed by a classification process. A color space transformation is assumed to increase separability between skin classes for hands and non-skin classes for other parts, to increase similarity among different skin tones, and to bring a robust performance under varying illumination conditions, without any sound reasonings. In this work, we examine if the color space transformation does bring those benefits to the problem of hand region detection on a dataset of images with different hand postures, backgrounds, people, and illuminations. Results indicate that best of the color space is the normalized RGB.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1689-1694
• /
• 2005

Face detection plays an important role in face recognition, video surveillance, and human computer interface. In this paper, we present a face detection system using eye detection with progressive thresholding from a digital camera. The face candidate is detected by using skin color segmentation in the YCbCr color space. The face candidates are verified by detecting the eyes that is located by iterative thresholding and correlation coefficients. Preprocessing includes histogram equalization, log transformation, and gray-scale morphology for the emphasized eyes image. The distance of the eye candidate points generated by the progressive increasing threshold value is employed to extract the facial region. The process of the face detection is repeated by using the increasing threshold value. Experimental results show that more enhanced face detection in real time.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 제14회 신호처리 합동 학술대회 논문집
• /
• pp.139-142
• /
• 2001

This paper presents a highly fast and accurate facial region extraction method by using the skin-color-reference map and motion information. First, we construct the robust skin-color-reference map and eliminate the background in image by this map. Additionally, we use the motion information for accurate and fast detection of facial region in image sequences. Then we further apply region growing in the remaining areas with the aid of proposed criteria. The simulation results show the improvement in execution time and accurate detection.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.579-582
• /
• 1999

In this paper, we propose a human face detection algorithm using adaptive skin color model and neural networks. To attain robustness in the changes of illumination and variability of human skin color, we perform a color segmentation of input image by thresholding adaptively in modified hue-saturation color space (TSV). In order to distinguish faces from other segmented objects, we calculate invariant moments for each face candidate and use the multilayer perceptron neural network of backpropagation algorithm. The simulation results show superior performance for a variety of poses and relatively complex backgrounds, when compared to other existing algorithm.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2009년도 학술대회
• /
• pp.193-196
• /
• 2009

단일 영상에서 피부색 영역을 추출하기 위해서 기존의 많은 방법들이 하나의 고정된 피부색 모델을 사용한다. 그러나 영상에 특성에 따라 영상에 포함된 피부색의 분포가 다양하기 때문에 이러한 방법을 이용하여 피부색을 검출할 경우 낮은 검출율이나 높은 긍정 오류율이 발생할 수 있다. 따라서 영상의 특징에 따라 적응적으로 피부색 영역을 추출할 수 있는 방법이 필요하다. 이에 본 논문에서는 영상의 특징에 따라 2단계의 과정을 거쳐 피부색 모델을 수정하는 방법으로, 다양한 조명과 환경 조건에서 높은 검출율과 낮은 긍정 오류율을 동시에 가지는 알고리즘을 제안한다.

• 한국항행학회논문지
• /
• 제24권2호
• /
• pp.148-154
• /
• 2020

주름은 피부의 노화도를 알 수 있는 주요한 특징 중의 하나이다. 기존의 영상처리기반 주름검출은 다양한 피부 영상에 효과적으로 대처하기 어렵다. 특히, 주름이 선명하지 않고 주변 피부와 유사한 경우 주름추출 성능은 급격히 떨어진다. 본 논문에서는 현미경 피부 영상에서 주름추출을 위해 딥러닝을 적용한다. 일반적으로 현미경 영상은 광각렌즈를 탑재하므로 영상 가장자리 영역의 밝기가 어둡다. 본 논문에서는 이를 해결하기 위해 피부 영상의 밝기를 추정하여 보정 한다. 또한, 주름추출에 적합한 의미분할 네트워크의 구조를 적용한다. 제안방법은 연구실에서 수집한 피부 영상에 대한 테스트 실험에서 99.6%의 정확도를 획득하였다.

• Journal of Dental Anesthesia and Pain Medicine
• /
• 제18권6호
• /
• pp.361-365
• /
• 2018

Background: Recently, we examined the effects of 2% lidocaine gel on the tactile sensory and pain thresholds of the face, tongue and hands of symptom-free individuals using quantitative sensory testing (QST); its effect was less on the skin of the face and hands than on the tongue. Consequently, instead of 2% lidocaine gel, we examined the effect of 8% lidocaine spray on the tactile sensory and pain thresholds of the skin of the face and hands of healthy volunteers. Methods: Using Semmes-Weinstein monofilaments, QST of the skin of the cheek and palm (thenar skin) was performed in 20 healthy volunteers. In each participant, two topical sprays were applied. On one side, 0.2 mL of 8% lidocaine pump spray was applied, and on the other side, 0.2 mL of saline pump spray was applied as control. In each participant, QST was performed before and 15 min after each application. Pain intensity was measured using a numeric rating scale (NRS). Results: Both the tactile detection threshold and filament-prick pain detection threshold of the cheek and thenar skin increased significantly after lidocaine application. A significant difference between the effect of lidocaine and saline applications was found on the filament-prick pain detection threshold only. NRS of the cheek skin and thenar skin decreased after application of lidocaine, and not after application of saline. Conclusion: The significant effect of applying an 8% lidocaine spray on the sensory and pain thresholds of the skin of the face and hands can be objectively scored using QST.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅲ
• /
• pp.1545-1548
• /
• 2003

This paper presents a method for detecting skin tumors on chicken carcasses using hyperspectral images. It utilizes both fluorescence and reflectance image information in hyperspectral images. A detection system that is built on this concept can increase detection rate and reduce processing time. Chicken carcasses are examined first using band ratio FCM information of fluorescence image and it results in candidate regions for skin tumor. Next classifier selects the real tumor spots using PCA components information of reflectance image from the candidate regions.

• Nutritional Sciences
• /
• 제2권2호
• /
• pp.119-124
• /
• 1999

Food allergies play an important role in Atopic Dermatitis (AD). Dietary manipulation is essential in the management of AD. However, there has been a paucity of data reporting the prevalence of food allergies in AD patients in Korea. In this study, the Food Open Challenge Tests (FOCT) were conducted to investigate food allergies in AD patients. The skin-prick test and the detection of specific IgE, as well as allergy history of patient were used to detect food allergies in all AD patients. Elimination diet was conducted for two weeks prior to FOCTs. The prevalence of food allergies by FOCT is as follows: milk (67.3%); chicken (64.2%); pork (62.8%); eggs (61.0%); beef(55.4%) ; wheat (52.0%) and soybean (45.2%). Allergenic food items in Korean AD patients were different from people in other foreign countries. The seven major foods those tested positively by FOCTs were completely eliminated from the replaced diets for two weeks, and were subsequently reintroduced one at a time. Results from FOCTs were not comparable with allergy history or skin-prick tests or specific IgE detection. The sensitivity and specificity of skin-prick tests and specific IgE detection were lower than FOCTs. Allergy history, skin-prick tests, and specific IgE detection are useful for the identification of food allergen but its clinical significance differed according to food items. Therefore, we conclude that even though a 10-day delay was necessary after food challenge, FOCT is a useful and valid method to confirm food allergies and may be essential for the effective control of food allergies for treatment of AD.

• 한국정보전자통신기술학회논문지
• /
• 제6권4호
• /
• pp.249-254
• /
• 2013

In the area of computer vision, face recognition is being intensively researched. It is generally known that before a face is recognized it must be localized. Skin-color information is an important feature to segment skin-color regions. To extract skin-color regions the skin-color model based on multi-layer perceptron has been proposed. Extracted regions are analyzed to emphasize ellipsoidal regions. The results from this study show good accuracy for our vehicle driver face detection system.