• The KIPS Transactions:PartB
• /
• v.15B no.3
• /
• pp.205-210
• /
• 2008

A new approach is proposed for restoration of corrupted regions and segmentation in natural text images. The challenge is to fill in the corrupted regions on the basis of color feature analysis by second order symmetric stick tensor. It is show how feature analysis can benefit from analyzing features using tensor voting with chromatic and achromatic components. The proposed method is applied to text images corrupted by manifold types of various noises. Firstly, we decompose an image into chromatic and achromatic components to analyze images. Secondly, selected feature vectors are analyzed by second-order symmetric stick tensor. And tensors are redefined by voting information with neighbor voters, while restore the corrupted regions. Lastly, mode estimation and segmentation are performed by adaptive mean shift and separated clustering method respectively. This approach is automatically done, thereby allowing to easily fill-in corrupted regions containing completely different structures and surrounding backgrounds. Applications of proposed method include the restoration of damaged text images; removal of superimposed noises or streaks. We so can see that proposed approach is efficient and robust in terms of restoring and segmenting text images corrupted.

• Journal of the Society of Disaster Information
• /
• v.15 no.2
• /
• pp.186-197
• /
• 2019

Purpose: This study intends to develop a nonlinear cyclic plasticity damage model in the framework of finite element formulation, which is capable of taking large deformation effects into account, in order to accurately predict the hysteretic behavior of stainless steel structures. Method: The new cyclic constitutive equations that utilize the combined isotropic-kinematic hardening rule for plastic deformation is incorporated into the damage mechanic model in conjunction with the large strain formulation. The damage growth law is based on the experimental observations that the evolution of microvoids yields nonlinear damage accumulation with plastic deformation. The damage model parameters and the procedure for their identification are presented. Results and Conclusion: The proposed nonlinear damage model has been verified by simulating uniaxial strain-controlled monotonic and cyclic loading tests, and successfully applied to a thin-walled stainless steel pipe subjected to constant and alternating strain-controlled cyclic loadings.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.22 no.1
• /
• pp.37-44
• /
• 2004

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.31 no.12
• /
• pp.8-15
• /
• 2013

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.11 no.1
• /
• pp.13-25
• /
• 1993

• Nuclear industry
• /
• v.4 no.5 s.21
• /
• pp.62-67
• /
• 1984

TMI-2호로의 복구작업에서는 원자로의 제염에서부터 손상된 노심의 철거까지 일련의 작업이 행하여지고 있는데 이작업을 통해서 얻어진 정보에 의해서 앞으로 원자로를 한층 더 안전하게 하는데 도움이 되는 귀중한 정보가 많다.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.4
• /
• pp.315-322
• /
• 2003

We propose a channel-attentive Mel frequency cepstral coefficient (CAMFCC) extraction method to improve the recognition performance of speech that is partially corrupted in the frequency domain. This method introduces weighting terms both at the filter bank analysis step and at the output probability calculation of decoding step. The weights are obtained for each frequency channel of filter bank such that the more reliable channel is emphasized by a higher weight value. Experimental results on TIDIGITS database corrupted by various frequency-selective noises indicated that the proposed CAMFCC method utilizes the uncorrupted speech information well, improving the recognition performance by 11.2% on average in comparison to a multi-band speech recognition system.

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.47-54
• /
• 2010

Old archived film shows two major defects: line scratch and blobs. In this paper, we present a design and implementation of an automatic video restoration system for line scratches observed in archived film. We use autoregressive (AR) image model because we can make stochastic and specifically autoregressive image generation process with our PAST-PRESENT model and Sampling Pattern. We designed locality maximizing scanning pattern, which can generate nearly stationary time-like series of pixels, which is a strong requirement for a stochastic series to be autoregressive. The sampled pixel series undergoes filtering and model fitting using Durbin-Levinson algorithm before interpolation process. We designed three-stage film restoration system, which includes (1) film acquisition from VHS tapes, (2) simple line scratch detection and restoration, and (3) manual blob identification and sophisticated inpainting scheme. We implemented film acquisition and simple inpainting scheme on Texas Instruments DSP board TMS320DM642 EVM, and implemented our AR inpainting scheme on PC for sophisticated restoration. We experimented our scheme with two old Korean films: "Viva Freedom" and "Robot Tae-Kwon-V", and the experimental results show that our scheme improves Bertalmio's scheme for subjective quality (MOS), objective quality (PSNR), and especially restoration ratio (RR), which reflects how much similar to the manual inpainting results.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.2
• /
• pp.387-396
• /
• 2016

As the number of people using digital devices has increased, the digital forensic, which aims at finding clues for crimes in digital data, has been developed and become more important especially in court. Together with the development of the digital forensic, the anti-forensic which aims at thwarting the digital forensic has also been developed. As an example, with anti-forensic technology the criminal would delete an digital evidence without which the investigator would be hard to find any clue for crimes. In such a case, recovery techniques on deleted or damaged information will be very important in the field of digital forensic. Until now, even though EVTX(event log)-based recovery techniques on deleted files have been presented, but there has been no study to retrieve event log data itself, In this paper, we propose some recovery algorithms on deleted or damaged event log file and show that our recovery algorithms have high success rate through experiments.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.1
• /
• pp.59-72
• /
• 2011

The research of psychological supporting systems as safety and welfare for disaster victims damaged psychologically as well as physically by a sudden disaster to return to effectively their social life has been carried. The domestic National Emergency Management Agency(NEMA) is operating the Disaster Victim Psychology Support Center that helps with curing damaged psychology and studies the transmission system of psychology management services, the classification of victims for disaster psychology support, and emergency consultation method to systemically support disaster psychology management. However, current psychology supporting centers provide the simple information for supporting centers such as medical and social welfare organizations. The development research of IT-based management systems to obtain needed information to construct the proposed systems curing psychological damage is still primitive step. Therefore, this paper shall propose a GIS-based integrated management system for victims and managers to effectively share related information one another and to return to victims' social life as soon as possible. Also, we implement a simple prototype system based on the Web. The proposed system supports the spatial search and statistical analysis based on map as well as keyword search, because having the location information on disaster victims, damage occurrence places, welfare and medical institutions, and psychological supporting centers. In addition, this system has the advantage reducing the frequency of disaster damage by providing aids in making efficient policy systems for the managers.