• Journal of Plant Biotechnology
• /
• v.33 no.4
• /
• pp.277-281
• /
• 2006

Fourier transform - infrared spectroscopy (FT-IR) provides biochemical profiles containing overlapping signals from a majority of the compounds that are present when whole cell extracts are analyzed. We attempted to determine the ripeness of strawberry fruit flesh by FT-IR. Fruit ripeness was divided into four developmental stages based on fruit skin color: 'yellow-green', 'pink-green', 'pink', and 'red' stages. Principal component analysis of FT-IR data of inside fruit flesh extracts clustered samples of four different developmental stages into three discrete groups: (1) 'yellow-green' group, (2) 'pink-green' group, and (3) 'pink' and 'red' group. The most remarkable difference between four different developmental stages was found in the carbohydrate fingerprint region $(1,000-1,100cm^{-1})$ of the FT-IR spectrum, indicating that differences in carbohydrate compounds represented the ripeness of strawberry fruit. Overall results indicate that FT-IR in combination with PCA enables discrimination of the ripeness of strawberry fruit flesh.

• The Journal of the Korea Contents Association
• /
• v.8 no.9
• /
• pp.1-9
• /
• 2008

In this paper, we proposed automatic face detection and tracking which is robustness in rotation. To detect a face image in complicated background and various illuminating conditions, we used face skin color detection. we used Harris corner detector for extract facial feature points. After that, we need to track these feature points. In traditional method, Lucas-Kanade feature tracker doesn't delete useless feature points by occlusion in current scene (face rotation or out of camera). So we proposed the estimation function, which delete useless feature points. The method of delete useless feature points is estimation value at each pyramidal level. When the face was occlusion, we deleted these feature points. This can be robustness to face rotation and out of camera. In experimental results, we assess that using estimation function is better than traditional feature tracker.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.195-198
• /
• 2013

Recognition and Tracking of interesting object is the significant field in Computer Vision. Mean-Shift algorithm have chronic problems that some errors are occurred when histogram of tracking area is similar to another area. in this paper, we propose to solve the problem. Each algorithm blocks skin color filtering, face detect and Mean-Shift started consecutive order assists better operation of the next algorithm. Avoid to operations of the overhead of tracking area similar to a histogram distribution areas overlap only consider the number of white pixels by running the Viola-Jones algorithm, simple arithmetic increases the convergence of the Mean-Shift. The experimental results, it comes to 78% or more of white pixels in the Mean-Shift search area, only if the recognition of the face area when it is configured to perform a Viola-Jones algorithm is tracking the object, was 100 percent successful.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.3
• /
• pp.60-68
• /
• 2007

In this paper, we propose an automatic facial expressions recognition system to analyze facial expressions (happiness, disgust, surprise and neutral) using tree structures based on heuristic rules. The facial region is first obtained using skin-color model and connected-component analysis (CCs). Thereafter the origins of user's eyes are localized using neural network (NN)-based texture classifier, then the facial features using some heuristics are localized. After detection of facial features, the facial expression recognition are performed using decision tree. To assess the validity of the proposed system, we tested the proposed system using 180 facial image in the MMI, JAFFE, VAK DB. The results show that our system have the accuracy of 93%.

• Journal of Pharmacopuncture
• /
• v.18 no.4
• /
• pp.26-31
• /
• 2015

Objectives: This study used semiology based on traditional Chinese medicine (TCM) to investigate vital energy (Qi) behavior in women with abdominal myofascial pain syndrome (AMPS). Methods: Fifty women diagnosed with chronic pelvic pain (CPP) secondary to AMPS were evaluated by using a questionnaire based on the theories of "yin-yang," "zang-fu", and "five elements". We assessed the following aspects of the illness: symptomatology; specific location of myofascial trigger points (MTrPs); onset, cause, duration and frequency of symptoms; and patient and family history. The patients tongues, lips, skin colors, and tones of speech were examined. Patients were questioned on various aspects related to breathing, sweating, sleep quality, emotions, and preferences related to color, food, flavors, and weather or seasons. Thirst, gastrointestinal dysfunction, excreta (feces and urine), menstrual cycle, the five senses, and characteristic pain symptoms related to headache, musculoskeletal pain, abdomen, and chest were also investigated. Results: Patients were between 22 and 56 years old, and most were married (78%), possessed a elementary school (66%), and had one or two children (76%). The mean body mass index and body fat were 26.86 kg/cm2 (range: 17.7 - 39.0) and 32.4% (range: 10.7 - 45.7), respectively. A large majority of women (96%) exhibited alterations in the kidney meridian, and 98% had an altered gallbladder meridian. We observed major changes in the kidney and the gallbladder Qi meridians in 76% and 62% of patients, respectively. Five of the twelve meridians analyzed exhibited Qi patterns similar to pelvic innervation Qi and meridians, indicating that the paths of some of these meridians were directly related to innervation of the pelvic floor and abdominal region. Conclusion: The women in this study showed changes in the behavior of the energy meridians, and the paths of some of the meridians were directly related to innervation of the pelvic floor and abdominal region.

• Journal of Korea Multimedia Society
• /
• v.13 no.7
• /
• pp.1000-1015
• /
• 2010

In this paper, we propose a novel algorithm for hand gesture recognition. The hand detection method is based on human skin color, and we use the boundary energy information to locate the hand region accurately, then the moment method will be employed to locate the hand palm center. Hand gesture recognition can be separated into 2 step: firstly, the hand posture recognition: we employ the parallel NNs to deal with problem of hand posture recognition, pattern of a hand posture can be extracted by utilize the fitting ellipses method, which separates the detected hand region by 12 ellipses and calculates the white pixels rate in ellipse line. the pattern will be input to the NNs with 12 input nodes, the NNs contains 4 output nodes, each output node out a value within 0~1, the posture is then represented by composed of the 4 output codes. Secondly, the hand gesture tracking and recognition: we employed the Kalman filter to predict the position information of gesture to create the position sequence, distance relationship between positions will be used to confirm the gesture. The simulation have been performed on Windows XP to evaluate the efficiency of the algorithm, for recognizing the hand posture, we used 300 training images to train the recognizing machine and used 200 images to test the machine, the correct number is up to 194. And for testing the hand tracking recognition part, we make 1200 times gesture (each gesture 400 times), the total correct number is 1002 times. These results shows that the proposed gesture recognition algorithm can achieve an endurable job for detecting the hand and its' gesture.

• Journal of Sasang Constitutional Medicine
• /
• v.12 no.1
• /
• pp.120-135
• /
• 2000

Objective ; The purpose of this study is to find out the constitutional symptomatic pattern of Soyangin and Taeumin through investigation of difference between two groups in stroke. Method ; 70 inpatients(Soyangin 31, Taeumin 39) in stroke, admitted into Kyung-Hee Oriental Hospital from 1. July. 1999 to 20. Sept. 1999, were investigated through questionnare which consists of 16 parts 155 questions, and the problems which have significant difference between Soyangin and Taeumin group were analyzed statistically. Result 1. The analysis of general characteristic difference between Soyangin and Taeumin group (1) The number of Soyangin patients is 31, Taeumin 39 and the number of Male patients 43, Female 27. (2) The mean weight of Taeumin group is heavier than that of Soyangin group and the degree of obesity of Taeumin group higher. (3) The number of patients who have smoking history is more at Soyangin group. (4) In neurological problem, dizziness is more complained of in Soyangin group. 2. The analysis about the result of Questionnare (1) In problems related with 'Sleeping', the time of going to bed and getting up and the duration of sleeping are more irregular in Taeumin group. (2) In problems related with 'Defecation', the shape of stool is more variable in Taeumin group. (3) In problems related with 'Urination', Soyangin group have more complaint. (4) In problems related with 'The condition of digestion', Taeumin group have a good appetite and more compalint in lower abdominal region, but on the contrary Soyangin group lose appetite and have more complaint in upper abdominal region. (5) In problems related with 'Head and Face', Soyangin group have more complaint. (6) In problems related with 'Eye, Ear and Nose', Soyangin group have more complaint at eye and ear. (7) In promlems related with 'Chest region', Soyangin group easily feel choked up and Taeumin group heart throbs. (8) In problems related with 'Skin', Taeumin group easily feel change of color tone at skin and Soyangin group dry.

• Journal of Internet Computing and Services
• /
• v.14 no.6
• /
• pp.117-124
• /
• 2013

In this paper, we present a new method which efficiently estimates a face direction from a sequences of input video images in real time fashion. For this work, the proposed method performs detecting the facial region and major facial features such as both eyes, nose and mouth by using the Haar-like feature, which is relatively not sensitive against light variation, from the detected facial area. Then, it becomes able to track the feature points from every frame using optical flow in real time fashion, and determine the direction of the face based on the feature points tracked. Further, in order to prevent the erroneously recognizing the false positions of the facial features when if the coordinates of the features are lost during the tracking by using optical flow, the proposed method determines the validity of locations of the facial features using the template matching of detected facial features in real time. Depending on the correlation rate of re-considering the detection of the features by the template matching, the face direction estimation process is divided into detecting the facial features again or tracking features while determining the direction of the face. The template matching initially saves the location information of 4 facial features such as the left and right eye, the end of nose and mouse in facial feature detection phase and reevaluated these information when the similarity measure between the stored information and the traced facial information by optical flow is exceed a certain level of threshold by detecting the new facial features from the input image. The proposed approach automatically combines the phase of detecting facial features and the phase of tracking features reciprocally and enables to estimate face pose stably in a real-time fashion. From the experiment, we can prove that the proposed method efficiently estimates face direction.

• Journal of Bio-Environment Control
• /
• v.29 no.2
• /
• pp.120-129
• /
• 2020

In Yesan-gun, Korea's main apple-producing region, the area of apple cultivation and yield are declining. In particular, the worsening quality of fruits due to unusually high temperatures amid recent climate change has also become a major challenge for apple orchards located on flatlands. The objective of this research is to investigate quality changes of apples according to different growing environments, depending on the shade of the sun, by covering the trees with different colors of wind nets. A white and blue wind nets with a hole size of 2 × 2 mm is installed on two experimental trees, 17-year-old 'Fuji' and 'Hongro', which are planted 1.5 m × 3.5 m in the north-south direction. Treatment of wind nets effectively lowered fruit surface temperature regardless of apple variety. When measuring the temperature of the fruit surface at 2 pm, the temperature of the air was 34.8℃, but the 'Fuji' of the untreated blocks was the highest at 40.0℃, while the blue wind net and the white wind net were significantly lower at 34.9℃ and 36.6℃, respectively. In 'Hongro', the results showed that the surface temperature was effectively lowered by recording 38.3℃ for the blue wind net and 38.5℃ for the white wind net treatment when the untreated one was 44.2℃. According to the color difference in 'Fuji', the skin redness (a^⁎) was the lowest with untreated control at 16.5, but the blue and white wind net treatment higher at 18.0 and 19.3, respectively. In 'Hongro', the white wind net treated fruit also showed a much higher skin redness than the untreated control of 28.1, showing much higher a^⁎ of 34.9. Sunburn damage in 'Fuji' apples amounted to 9.4% in untreated control. However, the blue and white wind net treatment revealed to 3.8% and 4.2%, respectively. In 'Hongro', those damage in the fruits treated with blue or white wind net, accounted for only 8.8% and 12.4%, respectively, significantly lower than 28.8% occurrence of untreated one. And, these results were understood to be the result of low UV radiation being blocked by the treatment of wind nets.

• Journal of Acupuncture Research
• /
• v.17 no.1
• /
• pp.27-41
• /
• 2000

The meridian system is the most essential and basic connecting structure that maintains the vital activities of viscera and bowels by connecting them with each part of body's surface. Doctors can understand the healthy condition, and the region and deficiency-excessiveness of disease by observing the condition of Qi flowing. Deficiency and excessiveness could be differentiated by various symptoms expressed in meridian system. Especially there could be several clues like pain, heat-cold, protuberance-depression, change of color and shine in the line of channel leads to the judgment of deficiency-excessiveness The diagnosis of deficiency and excessiveness can be generalized by quantification of elastic status in skin surface along the meridian system. By comparing data from measurement of elastic condition with those from traditional deficiency and excessiveness, it could be utilized for the development of oriental medicine. All biological activities in the human body are based on meridian system according to the oriental medicine. Also the meridian system is viewed as basic and essential structure connecting internal viscera and each part of body. The areas of expressed channel phenomena are muscle to bone, muscle to muscle and bone to bone. These areas are called depression where meridian system is present and any changing state on those points can be measured. It could be difficult in diagnosing the reaction of meridian system because doctor can depend on his own judgment. Therefore, it is necessary to quantify and indexate channel reactions. To quantify the channel reactions, specially manufactured instrument was used to quantify the protuberance and depression to differentiate the deficiency and excessiveness. The results follow as below; 1. The elastic index measurement by the equipment proved a pattern of agreement showing the values that ranged within standard deviation 0.05kgf/cm throughout the experiment except few cases' measurement in CV-17. 2. To evaluate the state of deficiency & excessiveness of elastic index measurements in frontal point, elastic index measurements in the front paint were compared to the elastic index measured surrounding the point within 2.5 cm. Such result of indexing procedure was closely matched to the concept of palpitation. 3. If the elastic index values in the surrounding front point closely located to the elastic index values in the front point, the judgement on the state of deficiency and excessiveness was delayed. Otherwise, it was judged as deficiency or excessiveness. 4. Out of total 12 cases of comparing the elastic index values to the elastic index values in the surrounding front point, Three to nine front points were judged as either in the state of deficiency or excessiveness. 5. Among the nine front points judged as either in the state of deficiency or excessiveness, Four cases were matched to the electric index measured by EAV that evaluating the internal organs by five different phases. If more clinical cases are accumulated, it is expected to systematically theorize and improve the concept of deficiency and excessiveness in the internal organs using the front point.