• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.165-170
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1312-1317
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• Korean Journal of Agricultural Science
• /
• v.38 no.3
• /
• pp.465-471
• /
• 2011

The commercial Korean native chickens (WR_CC) was developed by crossing a few native chicken breeds in Korea. In order to investigate the breed identification markers, SNPs from TYR gene and MC1R gene, which are associated with skin and feather colors respectively, were initially identified. In case of 3 identified SNPs in the TYR gene, yellow shank color was identified in Loss, Harvard, AA, RIR and CC, which have the fixed SNPs in most of the animals. On the other hand, SNP variations were observed in KNC_RB, C_B, WR_CC and HH_CC, which have the black, yellow and mixed color with black and yellow shank colors. Also, the investigation of 3 SNPs in the MC1R gene indicated that there were associations between shank and feather colors in RIR, SF, KNC_B, C_B and RIR. However, these results are not consistent among breeds. These SNP type inconsistencies within breeds suggested that the selection was performed based on the phenotypes, which is not include the genotype information. Thus, selection based on genetic information is required in the future.

• Science of Emotion and Sensibility
• /
• v.10 no.4
• /
• pp.571-581
• /
• 2007

This Braille System for color recognition was designed for those who have lost eye sight after birth. This system was based on the idea that these people had the understanding of colours before they went blind. So when they touch the braille, they can feel and recognize colours. This system adopted the Munsell's hue circle system which is used worldwide for its simple way of colour identification. It also used some texture to help people in need identify the brightness and saturation of colors. In spite of its simple structure, this system has a range of up to 153 different colours. For a friendly use, minimal changes were made by modifying location and height of dots of the braille system which blind people are already accustomed to. Because of it's simplicity, this colour braille system can be used easily and broadly. I believe that many acquired blind people can feel colour again through using this system and get benefits of social and cultural communication.

• Journal of Biosystems Engineering
• /
• v.29 no.1
• /
• pp.71-78
• /
• 2004

Real time and robust algorithm to extract the features of watermelon was developed from the remotely transmitted image of the watermelon. Features of the watermelon at the cultivation site such as size and shape including position are crucial to the successful tole-robotic operation and development of the cultivation data base. Algorithm was developed based on the concept of task sharing between the computer and the operator utilizing man-computer interface. Task sharing was performed based on the functional characteristics of human and computer. Identifying watermelon from the image transmitted from the cultivation site is very difficult because of the variable light condition and the complex image contents such as soil, mulching vinyl, straws on the ground, irregular leaves and stems. Utilizing operator's teaching through the touch screen mounted on the image monitor, the complex time consuming image processing process and instability of processing results in the watermelon identification has been avoided. Color and brightness characteristics were analyzed from the image area specified by the operator's teaching. Watermelon segmentation was performed using the brightness and color distribution of the specified imae processing area. Modified general Hough transform was developed to extract the shape, major and minor axes, and the position, of the watermelon. It took less than 100 msec of the image processing time, and was a lot faster than conventional approach. The proposed method showed the robustness and practicability in identifying watermelon from the wireless transmitted color image of the cultivation site.

• Proceedings of the Ginseng society Conference
• /
• 2002.10a
• /
• pp.467-476
• /
• 2002

A large number of individual ginseng plants have been selected in the farmer's fields to develop new ginseng varieties with desirable traits since 1970s. Among them, Hwangsukjong with green stem and yellow berry was selected as a ginseng germplasm. The phenotype of Hwangsukjong is quite different from Jakyungjong that has violet stem and red berry and has been cultivated in most of ginseng fields. Therefore, Hwangsukjong was crossed with Jakyungjong to clarify the inheritance of stem color and then the characteristics of $F_1\;and\;F_2$ hybrids were investigated. $F_1$ hybrid plants were similar to Jakyungjong in most of aerial part characters and showed hybrid vigor in fresh weight of root and weight of 100 seeds. In $F_2$ generation, the stem color was segregated in a ratio of 3 violet to 1 green. From this result, it was elucidated that violet color was controlled by single dominant gene. In another experiment, DNA was extracted from parents (Jakyungjong and Hwangsukjong) and $F_1$ hybrid. For each primer evaluated, multiple band profile was produced comprising from one to five major bands plus a varying number of minor bands and amplified bands were detected among most primers. In case of UBC primer number 13, 17, 30, 31, and 43, band patterns of parents and $F_1$ hybrid were very similar, but the others were not. Especially, in {\sharp}1$, {\sharp}4$, and {\sharp}33$, specific band was produced in Hwangsukjong and $F_1$ hybrid while in {\sharp}6$, another specific band was produced in Jakyungjong and $F_1$ hybrid. Therefore, $F_1$ hybrid had all specific bands at these primers. So, these selective markers could be used for identification of characteristics of $F_2$ hybrids

• Journal of Radiopharmaceuticals and Molecular Probes
• /
• v.4 no.2
• /
• pp.80-84
• /
• 2018

$[^{13}N]$Ammonia or $[^{13}N]NH_3$ is one of the most widely used PET tracer for the measurement of MBF. To produce $[^{13}N]NH_3$, devarda's alloy which contains aluminum, copper and zinc is used for the purpose of reduction from $^{13}N$-nitrate/nitrite to $[^{13}N]NH_3$. Since aluminum has neurotoxicity and renal toxicity, the amount of it should be carefully limited for the administration to the human body. Although USP and EP provide a way to identify the aluminum ion concentration, there are some difficulties to perform. Therefore, we tried to develop the modified method for verifying aluminum concentration of test solution. We compared color between test and standard solutions using chrome azurol S in pH 4.6 acetate buffer. We also tested color change of test and standard solutions according to pH, amounts and the order of reagent and time difference These results demonstrated that the color change of the solution can reflect quantitatively measure aluminum ion concentration. We hope the method is to be used effectively and practically in many sites where $[^{13}N]NH_3$ is produced.

• The Korean Journal of Pain
• /
• v.35 no.3
• /
• pp.250-260
• /
• 2022

Background: Cranial nerve ganglia, which are prone to viral infections and tumors, are located deep in the head, so their detailed anatomy is difficult to understand using conventional cadaver dissection. For locating the small ganglia in medical images, their sectional anatomy should be learned by medical students and doctors. The purpose of this study is to elucidate cranial ganglia anatomy using sectioned images and three-dimensional (3D) models of a cadaver. Methods: One thousand two hundred and forty-six sectioned images of a male cadaver were examined to identify the cranial nerve ganglia. Using the real color sectioned images, real color volume model having a voxel size of 0.4 × 0.4 × 0.4 mm was produced. Results: The sectioned images and 3D models can be downloaded for free from a webpage, anatomy.dongguk.ac.kr/ganglia. On the images and model, all the cranial nerve ganglia and their whole course were identified. In case of the facial nerve, the geniculate, pterygopalatine, and submandibular ganglia were clearly identified. In case of the glossopharyngeal nerve, the superior, inferior, and otic ganglia were found. Thanks to the high resolution and real color of the sectioned images and volume models, detailed observation of the ganglia was possible. Since the volume models can be cut both in orthogonal planes and oblique planes, advanced sectional anatomy of the ganglia can be explained concretely. Conclusions: The sectioned images and 3D models will be helpful resources for understanding cranial nerve ganglia anatomy, for performing related surgical procedures.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.32 no.6
• /
• pp.818-824
• /
• 2003

This study was carried out to select Meju of a good quality through general composition analysis, organoleptic evaluation, and to conduct isolation, identification, and growth characteristics of main strain related to fermentation from selected Meju. Moisture and crude protein of Meju were 7.2∼28.8% and 32.7∼42.3%, respectively. The amino nitrogen contents of Kyongbuk and Chonbuk Mejus were 770.8 mg% and 239.9 mg%, respectively. And also, free amino acid and glutamic acid contents of Doenjangs made from Chonbuk and Kyongbuk Mejus were 4,169.6 mg% and 499.4 mg%, respectively. The result of sensory evaluation of Mejus collected from several regions showed Kyongbuk was the most suitable Meju in items of color, flavor, appearance and overall (p<0.05). The typical properties of B. lichenifomis NH20 strain isolated from Kyongbuk Meju showed gram positive, aerobic rod cell and motility. As major component among its cellular fatty acid composition, $C_{15:0}$ anteiso fatty acid, $C_{15:1}$ iso fatty acid, $C_{17:0}$ anteiso fatty acid, and $C_{17:0}$ iso fatty acid were 30.7, 28.9, 13.3 and 11.2%, respectively. It showed the same identification coefficient (0.653) compared to the standard strain. Therefore, it was identified to be B. licheniformis NH20 according to Bergey's Manual of Systematic Bacteriology and its fatty acid profiles. The optimum pH, temperature, salt content, and culture time of B. licheniformis NH20 were 7.0, 32$^{\circ}C$, 2%, and 9 hours, respectively.ctively.

• Korean Journal of Ichthyology
• /
• v.29 no.2
• /
• pp.139-145
• /
• 2017

The spontaneous color mutant, albino individuals of genus Misgurnus, are rarely discovered in Korea and there are difficult to identify morphological species due to lack melanin pigmentation. In this study, we developed a genetic identification method for the species of albino Misgurnus individuals based on phylogenetic analysis by using recombination activating gene 1 (rag1) and cytochrome b (cytb) region of mitochondrial DNA. As a result of molecular phylogenetic analysis, three clades were identified as Misgurnus mizolepis, M. anguillicaudatus and M. mohoity. The homology of the cytb sequences of M. mohoity was best match to that of M. mohoity sequences in GenBank database. As a result of species identification of 25 albino Misgurnus individuals based on the phylogenetic tree, the red-eye type was identified as 16 M. anguillicaudatus and one M. mizolepis. The remaining three individuals were identified as one M. mizolepis ♀${\times}$M. anguillicaudatus ♂, and two M. mohoity ♀${\times}$M. anguillicaudatus ♂, respectively. In addition, the five black-eye type individuals were identified as one M. anguillicaudatus, three M. mizolepis and one M. mohoity. Therefore, this genetic identification method will be an useful techniques for species or hybrid identification in genus Misgurnus.