• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1996.06b
• /
• pp.18-21
• /
• 1996

In the field of Virtual Reality, many studies have been reported. Especially, there are many studies on generating virtual creatures on computer systems. In this paper we propose an algorithm to automatically generate 3D fish models from 2D images which are printed in illustrated books, pictures or handwritings. At first, 2D fish images are captured by means of image scanner. Next, the fish image is separated from background and segmented to several parts such as body, anal fin, dorsal fin, ectoral fin and ventral fin using the proposed method“Active Balloon model”. After that, users choose front view model and top view model among six samples, respectively. 3D model is automatically generated from separated body, fins and the above two view models. The number of patches is decreased without any influence on the accuracy of the generated 3D model to reduce the time cost when texture mapping is applied. Finally, we can get any kinds of 3D fish models.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.3
• /
• pp.135-138
• /
• 2014

This paper devices a facial expression recognition method robust to overfitting using 2D-DCT and EHMM algorithm. In particular, this paper achieves enhanced recognition performance by setting up a large window size for 2D-DCT feature extraction and extracting the observation vectors of EHMM. The experimental results on the CK facial expression database and the JAFFE facial expression database showed that the facial expression recognition accuracy was improved according as window size is large. Also, the proposed method revealed the recognition accuracy of 87.79% and showed enhanced recognition performance ranging from 46.01% to 50.05% in comparison to previous approaches based on histogram feature, when CK database is employed for training and JAFFE database is used to test the recognition accuracy.

• Journal of International Society for Simulation Surgery
• /
• v.1 no.1
• /
• pp.23-26
• /
• 2014

The aim of this report is to evaluate accuracy using3D surgical simulationand digitally printedwafer in orthognathic surgery. 22-year-old female was diagnosed with mandibular prognathism and apertognathia based on 3D diagnosis using CT. Digital dentition images were taken by laser scanning from dental cast, and each STL images were integrated into one virtual skull using simulation software. Digitalized intermediate wafer was manufactured using CAD/CAM software and 3D printer, and used to move maxillary segment in real patient. Constructed virtual skull from 1 month postoperative CT scan was superimposedinto simulated virtual model to reveal accuracy. Almost maxillo-mandibular landmarks were placed in simulated position within 1 mm differences except right coronoid process. Thus 3D diagnosis, surgical simulation, and digitalized wafer could be useful method to orthognathic surgery in terms of accuracy.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.11
• /
• pp.25-31
• /
• 2016

Parasitic capacitance and resistance of FinFET transistors are the important components that determine the frequency performance of the circuit. Therefore, the researchers in our group developed more accurate parasitic capacitance and resistance for FinFETs than BSIM-CMG. To verify the RF performance, proposed model was applied to design an LNA that has $S_{21}$ more than 10dB and center frequency more than 60GHz using HSPICE. To verify the accuracy of the proposed model, mixed-mode capability of 3D TCAD simulator Sentaurus was used. $S_{21}$ of LNA was chosen as a reference to estimate the error. $S_{21}$ of proposed model showed 87.5% accuracy compared to that of Sentaurus in 10GHz~100GHz frequency range. The $S_{21}$ accuracy of BSIM-CMG model was 56.5%, so by using the proposed model, the accuracy of the circuit simulator improved by 31%. This results validates the accuracy of the proposed model in RF domain and show that the accuracies of the parasitic capacitance and resistance are critical in accurately predicting the LNA performance.

• Journal of Biomedical Engineering Research
• /
• v.43 no.5
• /
• pp.341-352
• /
• 2022

Medical image segmentation is the most important task in radiation therapy. Especially, when segmenting medical images, the liver is one of the most difficult organs to segment because it has various shapes and is close to other organs. Therefore, automatic segmentation of the liver in computed tomography (CT) images is a difficult task. Since tumors also have low contrast in surrounding tissues, and the shape, location, size, and number of tumors vary from patient to patient, accurate tumor segmentation takes a long time. In this study, we propose a method algorithm for automatically segmenting the liver and tumor for this purpose. As an advantage of setting the boundaries of the tumor, the liver and tumor were automatically segmented from the CT image using the 2D CoordConv DeepLab V3+ model using the CoordConv layer. For tumors, only cropped liver images were used to improve accuracy. Additionally, to increase the segmentation accuracy, augmentation, preprocess, loss function, and hyperparameter were used to find optimal values. We compared the CoordConv DeepLab v3+ model using the CoordConv layer and the DeepLab V3+ model without the CoordConv layer to determine whether they affected the segmentation accuracy. The data sets used included 131 hepatic tumor segmentation (LiTS) challenge data sets (100 train sets, 16 validation sets, and 15 test sets). Additional learned data were tested using 15 clinical data from Seoul St. Mary's Hospital. The evaluation was compared with the study results learned with a two-dimensional deep learning-based model. Dice values without the CoordConv layer achieved 0.965 ± 0.01 for liver segmentation and 0.925 ± 0.04 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.927 ± 0.02 for liver division and 0.903 ± 0.05 for tumor division. The dice values using the CoordConv layer achieved 0.989 ± 0.02 for liver segmentation and 0.937 ± 0.07 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.944 ± 0.02 for liver division and 0.916 ± 0.18 for tumor division. The use of CoordConv layers improves the segmentation accuracy. The highest of the most recently published values were 0.960 and 0.749 for liver and tumor division, respectively. However, better performance was achieved with 0.989 and 0.937 results for liver and tumor, which would have been used with the algorithm proposed in this study. The algorithm proposed in this study can play a useful role in treatment planning by improving contouring accuracy and reducing time when segmentation evaluation of liver and tumor is performed. And accurate identification of liver anatomy in medical imaging applications, such as surgical planning, as well as radiotherapy, which can leverage the findings of this study, can help clinical evaluation of the risks and benefits of liver intervention.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1458-1463
• /
• 2004

Tracking is one of the most important pre-required task for many application such as human-computer interaction through gesture and face recognition, motion analysis, visual servoing, augment reality, industrial assembly and robot obstacle avoidance. Recently, 3D information of object is required in realtime for many aforementioned applications. 3D tracking is difficult problem to solve because during the image formation process of the camera, explicit 3D information about objects in the scene is lost. Recently, many vision system use stereo camera especially for 3D tracking. The 3D feature based tracking(3DFBT) which is on of the 3D tracking system using stereo vision have many advantage compare to other tracking methods. If we assumed the correspondence problem which is one of the subproblem of 3DFBT is solved, the accuracy of tracking depends on the accuracy of camera calibration. However, The existing calibration method based on accurate camera model so that modelling error and weakness to lens distortion are embedded. Therefore, this thesis proposes 3D feature based tracking method using SVM which is used to solve reconstruction problem.

• Design & Manufacturing
• /
• v.15 no.3
• /
• pp.1-6
• /
• 2021

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.

• Journal of Technologic Dentistry
• /
• v.40 no.4
• /
• pp.231-237
• /
• 2018

Purpose: The development of the dental technology industry has digitized the dental process. Definition of Digitalization of Dental Implantation Digitalization is the process of model making and prosthodontic processing using 3D CAD and CAM. Currently, it is becoming popular due to the spread of various devices. However, precision evaluation at this stage is an important factor in precision-based dental procedures. Therefore, in this study, we want to analyze the precision of the processed body made with digital dental machine. Methods: The accuracy of digital dental pore devices was evaluated. Specimens were fabricated with 5 types of 3D printers. The external shape was measured with the prepared specimen. The surface roughness was measured. Results: As a result, precision was excellent in order of EP2 specimen, EP1 specimen, and EA2 specimen. The precision of EP3 specimen and EA1 specimen is not excellent. And the precision of the specimen processed with polymer 3D printer is excellent. The accuracy of LCPS type polymer 3D printers is considered to be excellent. Conclusion : 1. Observation of the shape The 3D printer for LCPS system and the 3D printer for SLM $40{\mu}m$ system were found to be precisely processed. 2. Surface roughness results The LCPS system polymer 3D printer has been shown to have a precise surface.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.729-748
• /
• 2021

Vocal detection is one of the fundamental steps in musical information retrieval. Typically, the detection process consists of feature extraction and classification steps. Recently, neural networks are shown to outperform traditional classifiers. In this paper, we report our study on how to improve detection accuracy further by carefully choosing the parameters of the deep network model. Through experiments, we conclude that a feature-classifier model is still better than an end-to-end model. The recommended model uses a spectrogram as the input plane and the classifier is an 18-layer convolutional neural network (CNN). With this arrangement, when compared with existing literature, the proposed model improves the accuracy from 91.8% to 94.1% in Jamendo dataset. As the dataset has an accuracy of more than 90%, the improvement of 2.3% is difficult and valuable. If even higher accuracy is required, the ensemble learning may be used. The recommend setting is a majority vote with seven proposed models. Doing so, the accuracy increases by about 1.1% in Jamendo dataset.

• KIEAE Journal
• /
• v.16 no.1
• /
• pp.89-94
• /
• 2016

This study is part of three-dimensional(3D) heat transfer analysis program developmental process. The program is being developed without it's own built in 3D-modeller. So 3D-model must be created from another 3D-modeller such as generic CAD programs and imported to the developed program. After that, according to the 3D-geometric data form imported model, 3D-mesh created for numerical calculation. But the 3D-model created from another 3D-modeller is likely to have errors in it's geometric data such as mismatch of position between vertexes or surfaces. these errors make it difficult to create 3D-mesh for calculation. These errors are must be detected and cured in the pre-process before creating 3D-mesh. So, in this study four kinds of filters and functions are developed and tested. Firstly, 'vertex error filter' is developed for detecting and curing for position data errors between vertexes. Secondly, 'normal vector error filter' is developed for errors of surface's normal vector in 3D-model. Thirdly, 'intersection filter' is developed for extracting and creating intersection surface between adjacent objects. fourthly, 'polygon-line filter' is developed for indicating outlines of object in 3D-model. the developed filters and functions were tested on several shapes of 3D-models. and confirmed applicability. these developed filters and functions will be applied to the developed program and tested and modified continuously for less errors and more accuracy.