• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.1
• /
• pp.366-381
• /
• 2020

Steganography has been successfully employed in various applications, e.g., copyright control of materials, smart identity cards, video error correction during transmission, etc. Deep learning-based steganography models can hide information adaptively through network learning, and they draw much more attention. However, the capacity, security, and robustness of the existing deep learning-based steganography models are still not fully satisfactory. In this paper, three models for different cases, i.e., a basic model, a secure model, a secure and robust model, have been proposed for different cases. In the basic model, the functions of high-capacity secret information hiding and extraction have been realized through an encoding network and a decoding network respectively. The high-capacity steganography is implemented by hiding a secret image into a carrier image having the same resolution with the help of concat operations, InceptionBlock and convolutional layers. Moreover, the secret image is hidden into the channel B of carrier image only to resolve the problem of color distortion. In the secure model, to enhance the security of the basic model, a steganalysis network has been added into the basic model to form an adversarial network. In the secure and robust model, an attack network has been inserted into the secure model to improve its robustness further. The experimental results have demonstrated that the proposed secure model and the secure and robust model have an overall better performance than some existing high-capacity deep learning-based steganography models. The secure model performs best in invisibility and security. The secure and robust model is the most robust against some attacks.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.107-114
• /
• 2017

Iris diagnosis is an alternative medicine to diagnose the disease of the patient by using different of the iris pattern, color and other characteristics. This paper proposed a disease prediction algorithm that using the iris regions that analyze iris change to using differential image of iris image. this method utilize as patient's health examination according to iris change. Because most of previous studies only find a sign pattern in a iris image, it's not enough to be used for a iris diagnosis system. We're developed an iris diagnosis system based on a iris images processing approach, It's presents the extraction algorithms of 8 major iris signs and correction manually for improving the accuracy of analysis. As a result, PNSR of applied edge detection image is about 132, and pattern matching area recognition presented practical use possibility by automatic diagnostic that presume situation of human body by iris about 91%.

• The Journal of Korean Academy of Prosthodontics
• /
• v.56 no.2
• /
• pp.166-172
• /
• 2018

In case of the treatment of maxillary anterior teeth, it should be taken into account the proper morphology, arrangement and color satisfying patient's esthetic demands. For this purpose, facial composition, dentofacial composition, dental composition and dentogingival composition should be considered making diagnosis and treatment plan in an esthetic point of view. In adjustable temporary crown state, careful evaluation and correction of the esthetic and functional aspect were performed, and the definite restoration was reproduced using double scan.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.2
• /
• pp.235-240
• /
• 2015

Active Safety system is requested on the market of the medium and heavy duty commercial vehicle over 4.5ton beside the market of passenger car with advancement of the digital equipment proportionally. Unlike the passenger car, the mounting position of camera in case of the medium and heavy duty commercial vehicle is relatively high, it is disadvantaged conditions for lane recognition in contradiction to passenger car. In this work, we show the method of lane recognition through the Sobel edge, based on the spatial domain processing, Hough transform and color conversion correction. Also we suggest the low error method of front vehicles recognition in order to reduce the detection error through Haar-like, Adaboost, SVM and Template matching, etc., which are the object recognition methods by frontal camera vision. It is verified that the reliability over 98% on lane recognition is obtained through the vehicle test.

• Journal of Digital Convergence
• /
• v.15 no.3
• /
• pp.307-312
• /
• 2017

The purpose of this paper is to develop a new type of RGB lighting pipeline that can save time in animation production. After identifying the problems of the current method, the researchers studied 8 steps through new methods and comparative analysis. A method of implementing a graphic image lighting effect by the RGB lighting pipeline according to the current method is to create a render layer for each light set and a set of digital light separated by texture, Three types of written information can be stored in one layer and graphic image, and the accuracy and precision of color correction can be improved. Through this study, we propose the new and improved RGB lighting pipeline according to the characteristics of the work and the industries.

• Journal of the Korea Computer Industry Society
• /
• v.8 no.2
• /
• pp.103-106
• /
• 2007

In order to construct a Video Database, shot change detection should be made first. But, because these processes are not automated perfectly, we need a lot of time and efforts now. And, there are many shot change detection algorithms, which can't always insure the perfect result because of the editing effects such as cut, wipe, and dissolves used in film production. Therefore, in order to receive the exact shot change, It needs the verification and correction by manual processing at any cost. Spatiotemporal slice is a simple image condensing method for the content changes of video. The editing effects are expressed on the Spatiotemporal slice in the visually noticed form of vertical line, diagonal line, curved line and gradual color changes, etc. Accordingly the parts doubted as a shot change can be easily detected by the change of the Spatiotemporal slice without replaying the video. The system proposed in this study makes it possible to delete the false detected key frames, and create the undetected key frames on the Spatiotemporal slice.

• Archives of Plastic Surgery
• /
• v.39 no.3
• /
• pp.190-197
• /
• 2012

Background : This article presents long-term outcomes after correcting secondary bilateral cleft lip nasal deformities using a refined reverse-U incision and V-Y plasty or in combination with a composite graft in order to elongate the short columella. Methods : A total of forty-six patients underwent surgery between September 1996 and December 2008. The age of the patients ranged from 3 to 19 years of age. A bilateral reverse-U incision and V-Y plasty were used in 24 patients. A composite graft from the helical root was combined with a bilateral reverse-U incision in the 22 patients who possessed a severely shortened columella. The follow-up period ranged between 2 and 10 years. Results : A total of 32 patients out of 46 were evaluated postoperatively. The average columella length was significantly improved from an average of 3.7 mm preoperatively to 8.5 mm postoperatively. The average ratio of the columella height to the alar base width was 0.18 preoperatively and 0.29 postoperatively. The postoperative basal and lateral views revealed a better shape of the nostrils and columella. The elongated columella, combined with a composite graft, presented good maintenance of the corrected position with no growth disturbance. A composite graft showed color mismatching in several patients. Twenty-six patients demonstrated no alar-columella web deformity and satisfactory symmetry of the nostrils. Four patients experienced a drooping and overhanging of the corrected alar-columella web. Conclusions : A bilateral reverse-U incision with V-Y plasty or in combination with a composite graft was effective in correcting secondary bilateral cleft lip nasal deformity.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.43-48
• /
• 1998

Prior to launch, simulated radiances of the Ocean Scanning Multispectral Imager (OSMI) will be very useful to guess the real imagery of OSMI and to check the data processing system for OSMI. The data processing system for OSMI which is one sensor of Korea Mult i - Purpose Satellite (KOMPSAT) scheduled for launch in 1999 is being developed based on the SeaWiFS Data Analysis System (SeaDAS). Such a simulation should include the spectral bands, orbital and scanning characteristics of the OSMI and KOMPSAT spacecraft. The simulation is also very helpful for finding and preparing for problem areas before launch. This paper describes a method to create simulated radiances of the OSMI over the oceans. Our method for constructing a simulated OSMI imagery is to propagate a KOMPSAT orbit over a field of Coastal Zone Color Scanner (CZCS) pigment values and to use the values and atmospheric components to calculate total radiances. A modified Brouwer - Lyddane model with drag was used for the realistic orbit prediction, the CZCS pigment data were used to compute water - leaving radiances, and a variety of radiative transfer models were used to calculate atmospheric contributions to total radiances detected by OSMI. Imagery of the simulated OSMI total radiances for 6 nominal bands was obtained. As expected, water - leaving radiances were only a small fraction of total radiances and sun glint contaminations were observed near the solar declination. Therefore, atmospheric correction is very important in the calculation of pigment concentration from total radiances. Because the imagery near the sun's glitter pattern is virtually useless and must be discarded, more advanced mission planning will be required.

• Journal of Broadcast Engineering
• /
• v.22 no.3
• /
• pp.339-349
• /
• 2017

In this paper, we propose a technique for smoothly replacing a signboard image in a video clip with another signboard image and an application for performing it. In order to replace the signboard area in the image, it must be tracked and the shape of the signboard changed. Also, when an obstruction occurs due to a front object, the obscured area is extracted so that only the signboard area can be replaced, and color correction is performed for natural synthesis. The proposed application receives the information required by the algorithm from the user and explains the required functions, thereby disclosing the entire process in which the algorithm is actually implemented and tested. This can be used for a variety of media, and can be used as a means to remove the indirect advertisement that is often seen, and it can also be used as a new advertisement model in which another advertisement image is inserted into the image to be advertised.

• Journal of Broadcast Engineering
• /
• v.22 no.3
• /
• pp.327-338
• /
• 2017

Exposure fusion is a typical image fusion technique to generate a high dynamic range image by combining two or more different exposure images. In this paper, we propose block-based exposure adjustment considering unique characteristics of human visual system and improved saturation measure to get weight map. Proposed exposure adjustment artificially corrects intensity values of each input images considering human visual system, efficiently preserving details in the result image of exposure fusion. The improved saturation measure is used to make a weight map that effectively reflects the saturation region in the input images. We show the superiority of the proposed algorithm through subjective image quality, MEF-SSIM, and execution time comparison with the conventional exposure fusion algorithm.