• KIISE Transactions on Computing Practices
• /
• v.22 no.3
• /
• pp.157-162
• /
• 2016

The limitation of a human's visual perception is considered to be 60 frames per second, This study investigated the effects of fast update rates (above 60 fps) in terms of interaction accuracy. Initial experiments showed that the interaction accuracy increased at rates faster than 60 fps. We assumed that either or both of the following two situations would cause such an effect: the user could recognize rendering rates faster than 60 fps, or the input processing rates were significant for the high accuracy. To evaluate the significance of these events, we conducted a second and third experiment. Although the display refresh rate was also fixed at 60 fps (by disabling the vertical sync), the rendered image actually differed for 60 fps and 150 fps. This research shows that faster update rate is necessary to achieve high interaction accuracy, and its limit is far over the usually considered 60 fps.

• Journal of KIISE
• /
• v.44 no.6
• /
• pp.581-586
• /
• 2017

For automatic web scraping, unnecessary components such as menus and advertisements need to be removed from web pages and main contents should be extracted automatically. A content block tends to be located in the middle of a web page. In particular, Korean web documents rarely include metadata and have a complex design; a suitable method of content extraction is therefore needed. Existing content extraction algorithms use the textual and structural features of content blocks because processing visual features requires heavy computation for rendering and image processing. In this paper, we propose a new content extraction method using the tag positions in HTML as a quasi-visual feature. In addition, we develop a tag rank position, a type of tag position not affected by text length, and show that gradient boosting with the tag rank position is a very accurate content extraction method. The result of this paper shows that the content extraction method can be used to collect high-quality text data automatically from various web pages.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.12
• /
• pp.1003-1007
• /
• 2009

Client-side attacks including drive-by download target vulnerabilities in client applications that interact with a malicious server or process malicious data. A typical client-side attack is web-based one related to a malicious web page exploiting specific browser vulnerability that can execute mal ware on the client system (PC) or give complete control of it to the malicious server. To defend those attacks, this paper has constructed high interaction client honeypot system using Capture-HPC that adopts execution-based detection in virtual machine. We have detected and classified malicious web pages using the system. We have also analyzed the system's performance in terms of the number of virtual machine images and the number of browsers executed simultaneously in each virtual machine. Experimental results show that the system with one virtual machine image obtains better performance with less reverting overhead. The system also shows good performance when the number of browsers executed simultaneously in a virtual machine is 50.

• Journal of KIISE
• /
• v.45 no.2
• /
• pp.157-164
• /
• 2018

Due to the revolutionary advances in deep learning, performance of pattern recognition has increased significantly in many applications like speech recognition and image recognition, and some systems outperform human-level intelligence in specific domains. Unlike pattern recognition, in this paper, we focus on generating Korean sentences based on a few Korean sentences. We apply variational recurrent auto-encoder (VRAE) and modify the model considering some characteristics of Korean sentences. To reduce the number of words in the model, we apply a word spacing model. Also, there are many Korean sentences which have the same meaning but different word order, even without subjects or objects; therefore we change the unidirectional encoder of VRAE into a bidirectional encoder. In addition, we apply an interpolation method on the encoded vectors from the given sentences, so that we can generate new sentences which are similar to the given sentences. In experiments, we confirm that our proposed method generates better sentences which are semantically more similar to the given sentences.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.11
• /
• pp.1096-1100
• /
• 2010

In this paper, we propose an automatic segmentation of the meniscus based on active shape model using interpolated shape information in MR images. First, the statistical shape model of meniscus is constructed to reflect the shape variation in the training set. Second, the generation technique of interpolated shape information by using the weight according to shape similarity is proposed to robustly segment the meniscus with large variation. Finally, the automatic meniscus segmentation is performed through the active shape model fitting. For the evaluation of our method, we performed the visual inspection, accuracy measure and processing time. For accuracy evaluation, the average distance difference between automatic segmentation and semi-automatic segmentation are calculated and visualized by color-coded mapping. Experimental results show that the average distance difference was $0.54{\pm}0.16mm$ in medial meniscus and $0.73{\pm}0.39mm$ in lateral meniscus. The total processing time was 4.87 seconds on average.

• Journal of KIISE:Software and Applications
• /
• v.34 no.5
• /
• pp.465-475
• /
• 2007

With the spread of Internet, web users express their daily life by articles, pictures and cartons to recollect personal memory or to share their experience. For the easier recollection and sharing process, this paper proposes diverse cartoon generation methods using the landmark lists which represent the behavior and emotional status of the user. From the priority and causality of each landmark, critical landmark is selected for composing the cartoon scenario, which is revised by story ontology. Using similarity between cartoon images and each landmark in the revised scenario, suitable cartoon cut for each landmark is composed. To make cartoon story more diverse, weather, nightscape, supporting character, exaggeration and animation effects are additionally applied. Through example scenarios and usability tests, the diversity of the generated cartoon is verified.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.30-35
• /
• 2018

GuessWhat?! is a game in which two machine players, composed of questioner and answerer, ask and answer yes-no-N/A questions about the object hidden for the answerer in the image, and the questioner chooses the correct object. GuessWhat?! has received much attention in the field of deep learning and artificial intelligence as a testbed for cutting-edge research on the interplay of computer vision and dialogue systems. In this study, we discuss the objective function and characteristics of the GuessWhat?! game. In addition, we propose a simple solver for GuessWhat?! using a simple rule-based algorithm. Although a human needs four or five questions on average to solve this problem, the proposed method outperforms state-of-the-art deep learning methods using only two questions, and exceeds human performance using five questions.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.94-98
• /
• 2018

We propose Wide Inception ResNet (WIR Net) an optimized neural network architecture as a real-time semantic segmentation method for autonomous driving. The neural network architecture consists of an encoder that extracts features by applying a residual connection and inception module, and a decoder that increases the resolution by using transposed convolution and a low layer feature map. We also improved the performance by applying an ELU activation function and optimized the neural network by reducing the number of layers and increasing the number of filters. The performance evaluations used an NVIDIA Geforce GTX 1080 and TX1 boards to assess the class and category IoU for cityscapes data in the driving environment. The experimental results show that the accuracy of class IoU 53.4, category IoU 81.8 and the execution speed of $640{\times}360$, $720{\times}480$ resolution image processing 17.8fps and 13.0fps on TX1 board.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.6
• /
• pp.718-731
• /
• 2003

SAN(Storage Area Network) was developed in response to the requirements of high availability of data, scalable growth, and system performance. In order to use the SAN more efficiently, most of the SAN operating software supports storage virtualization concepts that allow users to view physical storage devices of the SAN as a large volume. A logical volume manager plays a key role in storage virtualization. It realizes the storage virtualization by mapping logical addresses to physical addresses. In this paper, we design and implement an efficient and flexible mapping method for the logical volume manager. Additionally we also design and implement a free space management method for flexible mapping. Our mapping method supports a snapshot that preserves a volume image at certain time and on-line reorganization to allow users to add or remove storage devices to and from the SAN even while the system is running. To justify our mapping method, we compare it with the mapping method of the GFS (Global File System) through various experiments.

• Journal of KIISE:Software and Applications
• /
• v.26 no.12
• /
• pp.1482-1496
• /
• 1999

기존의 스테레오 정합 알고리즘은 크게 명암기반기법과 특징기반기법의 두 가지로 나눌 수 있다. 그리고, 각 기법은 그들 나름대로의 장단점을 갖는다. 본 논문은 이 두 기법을 결합하는 새로운 알고리즘을 제안한다. 본 논문에서는 물체모델링을 목적으로 하기 때문에 배경을 제거하여 정합하는 방법을 사용한다. 이를 위해, 정합요소들과 정합유사함수가 정의되고, 정합유사함수는 두 기법사이의 장단점을 하나의 인수에 의해 조절한다. 그 외에도 거리차 지도의 오류를 제거하는 coarse-to-fine기법, 폐색문제를 해결하는 다중윈도우 기법을 사용하였고, 물체의 표면형태를 알아내기 위해 morphological closing 연산자를 이용하여 물체와 배경을 분리하는 방법을 제안하였다. 이러한 기법들을 기반으로 하여 여러가지 영상에 대해 실험을 수행하였으며, 그 결과들은 본 논문이 제안하는 기법의 효율성을 보여준다. 정합의 결과로 만들어지는 거리차 지도는 3차원 모델링을 통해 가상공간상에서 보여지도록 하였다.Abstract Classical stereo matching algorithms can be classified into two major areas; intensity-based and feature-based stereo matching. Each technique has advantages and disadvantages. This paper proposes a new algorithm which merges two main matching techniques. Since the goal of our stereo algorithm is in object modeling, we use images for which background is removed. Primitives and a similarity function are defined. The matching similarity function selectively controls the advantages and disadvantages of intensity-based and feature-based matching by a parameter.As an additional matching strategy, a coarse-to-fine method is used to remove a errorneous data on the disparity map. To handle occlusions, multiple windowing method is used. For finding the surface shape of an object, we propose a method that separates an object and the background by a morphological closing operator. All processes have been implemented and tested with various image pairs. The matching results showed the effectiveness of our method. From the disparity map computed by the matching process, 3D modeling is possible. 3D modeling is manipulated by VRML(Virtual Reality Manipulation Language). The results are summarized in a virtual reality space.