• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.311-312
• /
• 2022

본 논문에서는 딥러닝 기반 욕창 감지를 위한 욕창 객체 탐지를 연구한다. 객체 탐지 딥러닝 기법으로 RCNN, Fast R-CNN, Faster R-CNN, YOLO 등 다양한 기법이 존재하며, 각 모델의 특징 또한 다르다. 욕창은 단계별로 피부, 조직에 손상의 정도가 다르다. 낮은 단계의 경우 일반적인 피부색과 유사하게 나타나며, 높은 단계의 경우 근육, 뼈, 지지 조직 등의 괴사로 인해 삼출물 또는 괴사조직이 나타난다. 논문에서는 One-Stage Detection 기법인 YOLO를 기반으로 욕창 이미지 내부에서 욕창 탐지를 진행한다. 현재 보유하고 있는 이미지 데이터 수가 많지 않아 데이터 증강기법을 통해 데이터를 증강하여 학습에 활용하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.413-415
• /
• 2021

This paper proposes a nail detection algorithm using OpenPose and implements virtual nail art using it. Based on the key points detected by OpenPose, the finger area is detected using skin color characteristics for each finger. The nail region is detected from the edge image of the detected finger region. Then, a virtual nail art is implemented by synthesizing nail tips in the nail area. In a somewhat controlled shooting environment, simulation results show that the proposed algorithm detects nail areas well and implements virtual nail art well.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.89-91
• /
• 2022

본 논문에서는 생체인식 수단 중 하나인 손금을 이용한 생체인식에서 Attention U-Net을 기반으로 손금을 추출하는 방법을 제안한다. 손바닥의 손금 중 주요선이라 불리는 생명선, 지능선, 감정선은 거의 변하지 않는 특징을 가지고 있다. 기존의 손금 추출 방법인 비슷한 색상에서 손금 추출, 제한된 Background에서 손금을 추출하는 것이 아닌 피부색과 비슷하거나, 다양한 Background에서 적용될 수 있다. 이를 통해 사용자를 인식하는 생체인식 방법에서 사용할 수 있다. 본 논문에서 사용된 Attention U-Net의 특징을 통해 손금의 Segmentation 영역을 Attention Coefficient를 업데이트하며 효율적으로 학습할 수 있음을 확인하였다.

• Annual Conference of KIPS
• /
• 2007.11a
• /
• pp.76-79
• /
• 2007

수화는 하나의 제스처가 하나의 단어를 나타내는 수화 단어와 한글을 알파벳으로 표현하는 지문자로 구성되어 있다. 본 논문에서는 USB 카메라로부터 촬영한 영상을 얻고 히스토그램을 이용하여 피부색 영역을 추출한다. 얼굴 영역 추적을 활용하여 이미지를 그리드화하고 지문자의 위치를 파악하여 초성, 중성, 종성을 구분하고 한글 음절을 구성하였다.

• Annual Conference of KIPS
• /
• 2007.11a
• /
• pp.121-123
• /
• 2007

현재까지 유해한 컨텐츠(Contents)를 차단하기 위한 활발한 연구가 있었으나, 사람의 사운드(sound)와 이미지(image)를 통합한 필터링(filtering) 기법에 대한 연구는 활발히 이루어지지 않은 측면이 있다. 본 논문은 이미지(image) 데이터 중 피부색 분포 비율과 사운드(sound) 데이터 중 주파수 분석을 통한 심층적인 기법을 활용하여 현재까지 진행되고 있는 이미지 필터링(image filtering)방법에 대한 수행 결과보다 획기적으로 개선된 성능을 보이고자 한다. 즉, 사운드와 이미지의 특징 정보를 이용한 성인 컨텐츠(Adult Contents)분류 기법을 활용하는 것으로 성인 컨텐츠(Adult Contents)에서 두드러지는 특징을 보이는 사운드 패턴을 분석하여 현재까지 한정된 자원인 이미지만을 활용한 기법보다는 현저한 향상된 수행능력을 예측해 볼 수 있다.

• The Journal of Korean Medicine Ophthalmology and Otolaryngology and Dermatology
• /
• v.37 no.2
• /
• pp.113-122
• /
• 2024

Objectives : To report the R/O CRPS patient after Korean medicine treatment, suffering severe buring pain and insomnia. Methods : The patient was a 56-year-old female patient and treated with herbal medicines and acupuncture in 32 days. The treatment effect was evaluated by measuring VNRS of pain, sleeping time and change in mood status. Results : The Korean Medical therapy had good effect on the patient. Especially, relaxing mental treatment is effective in improving and maintaining symptoms. Conclusions : The Korean medical treatments appeared to be effective in reducing R/O CRPS symptoms. Further clinical research of patients with CRPS is needed.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.41-50
• /
• 2022

In this paper, a method to directly calculate the major elements of skin color such as melanin and hemoglobin from the RGB signal of the camera is proposed. The main elements of skin color typically measure spectral reflectance using specific equipment, and reconfigure the values at some wavelengths of the measured light. The values calculated by this method include such things as melanin index and erythema index, and require special equipment such as a spectral reflectance measuring device or a multi-spectral camera. It is difficult to find a direct calculation method for such component elements from a general digital camera, and a method of indirectly calculating the concentration of melanin and hemoglobin using independent component analysis has been proposed. This method targets a region of a certain RGB image, extracts characteristic vectors of melanin and hemoglobin, and calculates the concentration in a manner similar to that of Principal Component Analysis. The disadvantage of this method is that it is difficult to directly calculate the pixel unit because a group of pixels in a certain area is used as an input, and since the extracted feature vector is implemented by an optimization method, it tends to be calculated with a different value each time it is executed. The final calculation is determined in the form of an image representing the components of melanin and hemoglobin by converting it back to the RGB coordinate system without using the feature vector itself. In order to improve the disadvantages of this method, the proposed method is to calculate the component values of melanin and hemoglobin in a feature space rather than an RGB coordinate system using a feature vector, and calculate the spectral reflectance corresponding to the skin color using a general digital camera. Methods and methods of calculating detailed components constituting skin pigments such as melanin, oxidized hemoglobin, deoxidized hemoglobin, and carotenoid using spectral reflectance. The proposed method does not require special equipment such as a spectral reflectance measuring device or a multi-spectral camera, and unlike the existing method, direct calculation of the pixel unit is possible, and the same characteristics can be obtained even in repeated execution. The standard diviation of density for melanin and hemoglobin of proposed method was 15% compared to conventional and therefore gives 6 times stable.

• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.853-862
• /
• 2002

Face Detection can be defined as follows : Given a digitalized arbitrary or image sequence, the goal of face detection is to determine whether or not there is any human face in the image, and if present, return its location, direction, size, and so on. This technique is based on many applications such face recognition facial expression, head gesture and so on, and is one of important qualify factors. But face in an given image is considerably difficult because facial expression, pose, facial size, light conditions and so on change the overall appearance of faces, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact face detection which overcomes some restrictions by using neural network. The proposed system can be face detection irrelevant to facial expression, background and pose rapidily. For this. face detection is performed by neural network and detection response time is shortened by reducing search region and decreasing calculation time of neural network. Reduced search region is accomplished by using skin color segment and frame difference. And neural network calculation time is decreased by reducing input vector sire of neural network. Principle Component Analysis (PCA) can reduce the dimension of data. Also, pose estimates in extracted facial image and eye region is located. This result enables to us more informations about face. The experiment measured success rate and process time using the Squared Mahalanobis distance. Both of still images and sequence images was experimented and in case of skin color segment, the result shows different success rate whether or not camera setting. Pose estimation experiments was carried out under same conditions and existence or nonexistence glasses shows different result in eye region detection. The experiment results show satisfactory detection rate and process time for real time system.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.26 no.1
• /
• pp.133-143
• /
• 2002

The textile industry is petting increased effort to manufacture the value-added products that gives the differentiated characters at every level of fiber and fabric production. The color is an important element to be used strategically in order to push up the value-added design. The colors of apparel products have a close relationship with the skin colors of consumers and their preference colors. This study was carried out to cluster the skin colors of the Korean women into several similar skin colors and to analyze their preference colors by the classified groups. We measured the skin colors of 354 Korean women. With color spectrometer, JX-777, we measured 4 points of the body; cheek with removing cosmetics off, forehead, rear neck and arm on the interior part near elbow. All subjects had been shown with 40 color chips and answered the preference colors and preference colors of apparel. Data were analysed to classify skin colors using K-means Cluster Analysis and Duncan test, Frequency and Chi square test on the preference colors about the clustered 3 groups. In doing so, we used in SPSS Win 10 statistical package. Findings were as fellows: 1) The skin colors of the Korean women were clustered into YR, R, and Y skin colors. The majority of the subjects, 324 observations had YR skin colors and the subjects were classified into 3 kinds of skin color groups who had YR skin colors. 2) The average skin colors of total 324 subjects was 5.23YR 6.49/4.09 in Munsell Color System(MCS), 66.56 in L value, 10.53 in a value, and 20.67 in b value. 3) The average skin color of Type 1 was 7.98YR 6.24/4.14 in MCS, 64.10 in L value, 15.05 in a value, and 24.0 in b value. For Type 2 was 7.30 YR 6.56/3.28 in MCS, 67.24 in L value, 6.89 in a value, and 18.4 in b value, and Type 3 was 7.01 YR 7.20/4.38 in MCS, 73.53 in L value, L 16.04 in a value, and 24.87 in b value. 4) The average face color of total 324 subjects was 7.31YR 6.65/3.56 in MCS, 68.13 in L value, 9.53 in a value, and 20.18 in b value. 5) The average face color of Type 1 was 4.19 YR 6.92/5.05 in MCS, 70.78 in L value, 13.2 in a value, and 25.32 in b value. For Type 2 was 5.24YR 6.33/3.79 in MCS, 64.94 in L value, 9.84 in a value, and 19.08 in b value. Type 3 was 5.4YR 6.85/4.68 in MCS, 70.1 in L value, 11.73 in a value, and 23.92 in b value. 6) The difference of mean values between the clustered 3 skin color groups showed significantly different except the a value of neck and H value of cheeks and H value of foreheads. 7) All 3 groups showed that the most preference colors and the most preference colors of apparel was 5R 4/14. and their preference colors were much more than the preference colors of apparel.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.38 no.1
• /
• pp.43-50
• /
• 2012

The safety of cosmetics or cosmetic ingredients on human skin is generally evaluated by visual assessment but some early subtle skin changes may not be noticed by the naked eyes. Thus, the present study was conducted to detect skin reactions induced by mildly irritating cosmetic ingredients by using a laser Doppler perfusion imager (LDPI) method that measures blood flow, a $Vapometer^{(R)}$ that measure strans epidermal water loss (TEWL), and a spectrophotometer that measures the skin color as the erythema values ($a^*$). Visual assessment showed that all tested oils and humectants except propylene glycol belong to the low skin irritation ranges (grades 0+ to 2.9+) while all tested surfactants and propylene glycol belong to the moderate-to strong-skin irritation ranges (grades 3+ to 5+). Among three instrumental methods, TEWL assessment appeared to be more sensitive than spectrophotometric or LDPI method and suitable for the detection of subtle skin response invisible to the naked eye (grades 0+ to 2.9+). Skin reactions of grade 3+ to 5+ could be detected by all three instrumental methods. In conclusion, the current study suggested that the sub-clinical skin reactions due to mild irritants contained in cosmetics can be best assessed by TEWL measurements.