• Journal of IKEEE
• /
• v.18 no.2
• /
• pp.291-297
• /
• 2014

Since hand gesture recognition was realized thanks to improved image processing algorithms, sign language translation has been a critical issue for the hearing-impaired. In this paper, we extract human hand figures from a real time image stream and detect gestures in order to figure out which kind of hand language it means. We used depth-color calibrated image from the Kinect to extract human hands and made a decision tree in order to recognize the hand gesture. The decision tree contains information such as number of fingers, contours, and the hand's position inside a uniform sized image. We succeeded in recognizing 'Hangul', the Korean alphabet, with a recognizing rate of 98.16%. The average execution time per letter of the system was about 76.5msec, a reasonable speed considering hand language translation is based on almost still images. We expect that this research will help communication between the hearing-impaired and other people who don't know hand language.

• Journal of the Korea Computer Graphics Society
• /
• v.6 no.4
• /
• pp.9-14
• /
• 2000

Non-Photorealistic rendering techniques, such as toon rendering, can enhance the quality of hand-drawn cell-animation images greatly with less effort. For this reason, to on rendering is one of the popular techniques used in the cell-animation image production field. The existing toon rendering techniques, however, have not been effective enough for the real-time image processing that the techniques have not been adequate for some processes that needs immediate responses such as virtual-realities, or video games. This paper will suggest the real-time toon rendering to overcome the limits through real-time outline detection and phong shading. In addition, a effective result-image is created as adding a shadow and a execution time remains by real-time through fast shadow generation algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.5B
• /
• pp.526-531
• /
• 2009

In this paper, we propose new novel technique (ILCT: Instruction-Level Correlation Technique) which can detect tempered instructions by software attacks or hardware attacks before their execution. In conventional works, due to both high complex computation of cipher process and low processing speed of cipher modules, existing secure processor architecture applying cipher technique can cause serious performance degradation. While, the secure processor architecture applying ILCT with FEC does not incur excessive performance decrease by complexity of computation and speed of tampering detection modules. According to experimental results, total memory overhead including parity are increased in average of 26.62%. Also, secure programs incur CPI degradation in average of $1.20%{\sim}1.97%$.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.166-169
• /
• 2017

Currently, studies using Deep Learning are actively carried out showing good results in many fields. A template matching method is mainly used to recognize parts mounted on PCB(Printed Circuit Board). However, template matching should have multiple templates depending on the shape, orientation and brightness. And it takes long time to perform matching because it searches for the entire image. And there is also a disadvantage that the recognition rate is considerably low. In this paper, we use the Faster-RCNN method for recognizing PCB components as machine learning for classifying several objects in one image. This method performs better than the template matching method, execution time and recognition.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.4
• /
• pp.267-272
• /
• 2013

As an important operation with many applications such as data cleaning and duplicate detection, the similarity join is a challenging issue, which finds all pairs of records whose similarities are above a given threshold in a dataset. We propose a new algorithm that uses the prefix filtering principle as strong constraints on generation of candidate pairs for fast similarity joins. The candidate pair is generated only when the current prefix token of a probing record shares one prefix token of an indexing record within the constrained prefix tokens by the principle. This generation method needs not to compute an upper bound of the overlap between two records, which results in reduction of execution time. Experimental results show that our algorithm significantly outperforms the previous prefix filtering-based algorithms on real datasets.

• Journal of Korea Multimedia Society
• /
• v.21 no.11
• /
• pp.1342-1352
• /
• 2018

Voice Command systems are important means of ensuring accessibility to digital devices for use in situations where both hands are not free or for people with disabilities. Interests in services using speech recognition technology have been increasing. In this study, we developed a mobile writing application using voice recognition and voice command technology which helps people create and edit documents easily. This application is characterized by the minimization of the touch on the screen and the writing of memo by voice. We have systematically designed a mode to distinguish voice writing and voice command so that the writing and execution system can be used simultaneously in one voice interface. It provides a shortcut function that can control the cursor by voice, which makes document editing as convenient as possible. This allows people to conveniently access writing applications by voice under both physical and environmental constraints.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.346-349
• /
• 2014

Currently, the growing cyber threat continues, the damage caused by the evolution of malicious code incidents become more bigger. Such advanced attacks as APT using 'zero-day vulnerability' bring easy way to steal sensitive data or personal information. However it has a lot of limitation that the traditional ways of defense like 'access control' with blocking of application ports or signature base detection mechanism. This study is suggesting a way of controlling application activities focusing on keeping integrity of applications, authorization to running programs and changes of files of operating system by hardening of legitimate resources and programs based on 'white-listing' technology which analysis applications' behavior and its usage.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.220-228
• /
• 2022

Image always carry useful information, detecting a text from scene images is imperative. The proposed work's purpose is to recognize scene text image, example boarding image kept on highways. Scene text detection on highways boarding's plays a vital role in road safety measures. At initial stage applying preprocessing techniques to the image is to sharpen and improve the features exist in the image. Likely, morphological operator were applied on images to remove the close gaps exists between objects. Here we proposed a two phase algorithm for extracting and recognizing text from scene images. In phase I text from scenery image is extracted by applying various image preprocessing techniques like blurring, erosion, tophat followed by applying thresholding, morphological gradient and by fixing kernel sizes, then canny edge detector is applied to detect the text contained in the scene images. In phase II text from scenery image recognized using MSER (Maximally Stable Extremal Region) and OCR; Proposed work aimed to detect the text contained in the scenery images from popular dataset repositories SVT, ICDAR 2003, MSRA-TD 500; these images were captured at various illumination and angles. Proposed algorithm produces higher accuracy in minimal execution time compared with state-of-the-art methodologies.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.2
• /
• pp.153-166
• /
• 2020

DDI(Display Driver IC) are used to drive numerous pixels that make up display. For stable driving of DDI, it is necessary to attach a protective film to shield electromagnetic waves. When the protective film is attached, defects often occur if the film is inclined or the center point is not aligned. In order to minimize such defects, an algorithm for correcting the center point and the inclined angle using camera image information is required. This technology detects the corner coordinates of the protective film by image processing in order to correct the positional defects where the protective film is attached. Corner point coordinates are detected using an algorithm, and center point position finds and correction values are calculated using the detected coordinates. LUT (Lookup Table) is used to quickly find out whether the angle is inclined or not. These algorithms were described by Verilog HDL. The method using the existing software requires a memory to store the entire image after processing one image. Since the method proposed in this paper is a method of scanning by adding a line buffer in one scan, it is possible to scan even if only a part of the image is saved after processing one image. Compared to those written in software language, the execution time is shortened, the speed is very fast, and the error is relatively small.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.389-391
• /
• 2023

In the era of Big Data, humanity is facing a huge overflow of information. To overcome such an obstacle, many new cutting-edge technologies are being introduced. The movie recommendation system is also one such technology. To date, many theoretical and practical kinds of research have been conducted. Our research also focuses on the movie recommendation system by implementing methods from Social Network Analysis(SNA) and Parallel Programming. We applied the Girvan-Newman algorithm to detect communities of users, and a future package to perform the parallelization. This approach not only tries to improve the accuracy of the system but also accelerates the execution time. To do our experiment, we used the MovieLense Dataset.