• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.375-382
• /
• 2002

Handwritten character recognition is classified into on-line handwritten character recognition and off-line handwritten character recognition. On-line handwritten character recognition has made a remarkable outcome compared to off-line hacdwritten character recognition. This method can acquire the dynamic written information such as the writing order and the position of a stroke by means of pen-based electronic input device such as a tablet board. On the contrary, Any dynamic information can not be acquired in off-line handwritten character recognition since there are extreme overlapping between consonants and vowels, and heavily noisy images between strokes, which change the recognition performance with the result of the preprocessing. This paper proposes a method that effectively extracts the stroke including dynamic information of characters for off-line Korean handwritten character recognition. First of all, this method makes improvement and binarization of input handwritten character image as preprocessing procedure using watershed algorithm. The next procedure is extraction of skeleton by using the transformed Lu and Wang's thinning: algorithm, and segment pixel array is extracted by abstracting the feature point of the characters. Then, the vectorization is executed with a maximum permission error method. In the case that a few strokes are bound in a segment, a segment pixel array is divided with two or more segment vectors. In order to reconstruct the extracted segment vector with a complete stroke, the directional component of the vector is mortified by using right-hand writing coordinate system. With combination of segment vectors which are adjacent and can be combined, the reconstruction of complete stroke is made out which is suitable for character recognition. As experimentation, it is verified that the proposed method is suitable for handwritten Korean character recognition.

• Science of Emotion and Sensibility
• /
• v.8 no.4
• /
• pp.423-433
• /
• 2005

The computer hardware development has provided many chances of emergence between art and technology. In many cases today's interactive artworks cannot be completed without audience's participation. The interactive production process with technical supplementation can be celled feedback. Mr. Nam Jun Paik showed 'Participant TV' that interacts with audience's response in real time. It means artwork changes with the constantly changing value from the data set from human visual perception. Dan Graham showed another feedback related work, which delays 5second playback in mirror that implies consequence of time. Today's media art has to sublimate coincidence, time ant audience into philosophical artwork through consonance that comes with video and sound as we can see from Bill Viola. Stelarc produced artworks. That use input data that is weak signals from brain, muscles. Through a terminal display with player, body expanded meaning of media. Jeffrey Shaw's 'Legible City' provided a fabrication of the reality with the interaction of bicycle's pedal speed and steering direction that is controlled by 4river. RE:MARK used microphone as input device as Edmond Couchot's 'Je same a la vent' and Nam Jun Paik's 'Participant TV' did. There is no communication without feedback between human being. The reality makes audience involved into artworks. That is the reason why feedback has to be natural. Through the feedback process, the originality of the idea is altered by audience. The feedback is not just part of flesh of artwork rather skeleton of it. Technological showoff cannot be art itself The perfection of technological application plan helps feedback that interacts with audience naturally in order that audience hoes not feel the feedback as artificial plan. Interactive media art has to be evolved into new media form with new integration feedback technology.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.279-286
• /
• 2021

Recently, We are carrying out a policy of physical distancing of at least 1m from each other to prevent the spreading of COVID-19 disease in public places. In this paper, we propose a method for measuring distances between people in real time and an automation system that recognizes objects that are within 1 meter of each other from stereo images acquired by drones or CCTVs according to the estimated distance. A problem with existing methods used to estimate distances between multiple objects is that they do not obtain three-dimensional information of objects using only one CCTV. his is because three-dimensional information is necessary to measure distances between people when they are right next to each other or overlap in two dimensional image. Furthermore, they use only the Bounding Box information to obtain the exact coordinates of human existence. Therefore, in this paper, to obtain the exact two-dimensional coordinate value in which a person exists, we extract a person's key point to detect the location, convert it to a three-dimensional coordinate value using Stereo Vision and Camera Calibration, and estimate the Euclidean distance between people. As a result of performing an experiment for estimating the accuracy of 3D coordinates and the distance between objects (persons), the average error within 0.098m was shown in the estimation of the distance between multiple people within 1m.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2022

In this paper, we propose a vector-based augmentation technique that can generate data required for crack detection and a ConvNet(Convolutional Neural Network) technique that can learn it. Detecting cracks quickly and accurately is an important technology to prevent building collapse and fall accidents in advance. In order to solve this problem with artificial intelligence, it is essential to obtain a large amount of data, but it is difficult to obtain a large amount of crack data because the situation for obtaining an actual crack image is mostly dangerous. This problem of database construction can be alleviated with elastic distortion, which increases the amount of data by applying deformation to a specific artificial part. In this paper, the improved crack pattern results are modeled using ConvNet. Rather than elastic distortion, our method can obtain results similar to the actual crack pattern. By designing the crack data augmentation based on a vector, rather than the pixel unit used in general data augmentation, excellent results can be obtained in terms of the amount of crack change. As a result, in this paper, even though a small number of crack data were used as input, a crack database can be efficiently constructed by generating various crack directions and patterns.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.189-198
• /
• 2024

Research combining deep learning-based models and physical simulations is making important advances in the medical field. This extracts the necessary information from medical image data and enables fast and accurate prediction of deformation of the skeleton and soft tissue based on physical laws. This study proposes a system that integrates Neural Radiance Fields (NeRF), Position-Based Dynamics (PBD), and Parallel Resampling to generate 3D volume data, and deform and visualize them in real-time. NeRF uses 2D images and camera coordinates to produce high-resolution 3D volume data, while PBD enables real-time deformation and interaction through physics-based simulation. Parallel Resampling improves rendering efficiency by dividing the volume into tetrahedral meshes and utilizing GPU parallel processing. This system renders the deformed volume data using ray casting, leveraging GPU parallel processing for fast real-time visualization. Experimental results show that this system can generate and deform 3D data without expensive equipment, demonstrating potential applications in engineering, education, and medicine.

• The korean journal of orthodontics
• /
• v.27 no.2
• /
• pp.209-219
• /
• 1997

This investigation was designed to analyze the degree of dental compensation according to horizontal components of craniofacial skeleton and to investigate correlation between dental compensation and craniofacial pattern in skeletal class III malocclusion. The material selected for this study consisted of standard lateral cephalogram of 59 subjects in normal occlusion group, 91 subjects in mild skeletal class III malocclusion group and 58 subjects in severe skeletal class III malocclusion group. The mild skeletal class III malocclusion group was divided into two groups, one was class III malocclusion without anterior crossbite group and the other was class III malocclusion with anterior crossbite group. The data were analyzed by Quick-ceph image program. The results were as follows. 1. Mild skeletal class III malocclusion without anterior crossbite group showed the most labial inclination of upper incisors, followed by severe skeletal class III malocclusion group and mild skeletal class III malocclusion with anterior crossbite group, the Latter showing the least. The amount of lingual inclination of lower incisors was the largest in severe skeletal class III malocclusion group, and there was no statistically significant difference between mild skeletal claw III malocclusion without anterior crossbite group and mild skeletal class III malocclusion with anterior crossbite group. 2. There were little differences in vertical skeletal structure between mild skeletal class III malocclusion without anterior crossbite group and mild skeletal class III malocclusion with anterior cwssbite group, they showed statistically significant differences in the upper incisors measurements. 3. The measurements of lower incisors in mild skeletal class III malocclusion without anterior crossbite group and upper incisors in mild skeletal class III malocclusion with anterior crossbite group represented a high correlation with skeletal structure. Especially, ∠IMPA and ∠FMIA of lower incisor measurements, and ∠U1-FH ∠U1-SN of upper incisor measurements showed high correlation with skeletal structure in each group. 4. ∠IMPA and ∠FMIA of lower incisor measurements showed high correlation with skeletal structure in all groups. ∠U1-FH, ∠U1-SN and U1-facial plane(mm) of upper incisor measurements represented higher correlation with skeletal structure than any other upper incisor measurements.

• Nuclear Medicine and Molecular Imaging
• /
• v.41 no.1
• /
• pp.30-41
• /
• 2007

Purpose: Bone metastasis in breast cancer patients are usually assessed by conventional Tc-99m methylene diphosphonate whole-body bone scan, which has a high sensitivity but a poor specificity. However, positron emission tomography with $^{18}F-2-deoxyglucose$ (FDG-PET) can offer superior spatial resolution and improved specificity. FDG-PET/CT can offer more information to assess bone metastasis than PET alone, by giving a anatomical information of non-enhanced CT image. We attempted to evaluate the usefulness of FDG-PET/CT for detecting bone metastasis in breast cancer and to compare FDG-PET/CT results with bone scan findings. Materials and Methods: The study group comprised 157 women patients (range: $28{\sim}78$ years old, $mean{\pm}SD=49.5{\pm}8.5$) with biopsy-proven breast cancer who underwent bone scan and FDG-PET/CT within 1 week interval. The final diagnosis of bone metastasis was established by histopathological findings, radiological correlation, or clinical follow-up. Bone scan was acquired over 4 hours after administration of 740 MBq Tc-99m MDP. Bone scan image was interpreted as normal, low, intermediate or high probability for osseous metastasis. FDG PET/CT was performed after 6 hours fasting. 370 MBq F-18 FDG was administered intravenously 1 hour before imaging. PET data was obtained by 3D mode and CT data, used as transmission correction database, was acquired during shallow respiration. PET images were evaluated by visual interpretation, and quantification of FDG accumulation in bone lesion was performed by maximal SUV(SUVmax) and relative SUV(SUVrel). Results: Six patients(4.4%) showed metastatic bone lesions. Four(66.6%) of 6 patients with osseous metastasis was detected by bone scan and all 6 patients(100%) were detected by PET/CT. A total of 135 bone lesions found on either FDG-PET or bone scan were consist of 108 osseous metastatic lesion and 27 benign bone lesions. Osseous metastatic lesion had higher SUVmax and SUVrel compared to benign bone lesion($4.79{\pm}3.32$ vs $1.45{\pm}0.44$, p=0.000, $3.08{\pm}2.85$ vs $0.30{\pm}0.43$, p=0.000). Among 108 osseous metastatic lesions, 76 lesions showed as abnormal uptake on bone scan, and 76 lesions also showed as increased FDG uptake on PET/CT scan. There was good agreement between FDG uptake and abnormal bone scan finding (Kendall tau-b : 0.689, p=0.000). Lesion showed increased bone tracer uptake had higher SUVmax and SUVrel compared to lesion showed no abnormal bone scan finding ($6.03{\pm}3.12$ vs $1.09{\pm}1.49$, p=0.000, $4.76{\pm}3.31$ vs $1.29{\pm}0.92$, p=0.000). The order of frequency of osseous metastatic site was vertebra, pelvis, rib, skull, sternum, scapula, femur, clavicle, and humerus. Metastatic lesion on skull had highest SUVmax and metastatic lesion on rib had highest SUVrel. Osteosclerotic metastatic lesion had lowest SUVmax and SUVrel. Conclusion: These results suggest that FDG-PET/CT is more sensitive to detect breast cancer patients with osseous metastasis. CT scan must be reviewed cautiously skeleton with bone window, because osteosclerotic metastatic lesion did not showed abnormal FDG accumulation frequently.