• Journal of Korea Multimedia Society
• /
• v.7 no.11
• /
• pp.1597-1609
• /
• 2004

A lot of lipreading system has been proposed to compensate the rate of speech recognition dropped in a noisy environment. Previous lipreading systems work on some specific conditions such as artificial lighting and predefined background color. In this paper, we propose a real-time lipreading system which allows the motion of a speaker and relaxes the restriction on the condition for color and lighting. The proposed system extracts face and lip region from input video sequence captured with a common PC camera and essential visual information in real-time. It recognizes utterance words by using the visual information in real-time. It uses the hue histogram model to extract face and lip region. It uses mean shift algorithm to track the face of a moving speaker. It uses PCA(Principal Component Analysis) to extract the visual information for learning and testing. Also, it uses HMM(Hidden Markov Model) as a recognition algorithm. The experimental results show that our system could get the recognition rate of 90% in case of speaker dependent lipreading and increase the rate of speech recognition up to 40～85% according to the noise level when it is combined with audio speech recognition.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.4
• /
• pp.203-210
• /
• 2017

In this paper, we propose an effective neural network model for image caption generation and model transfer. This model is a kind of multi-modal recurrent neural network models. It consists of five distinct layers: a convolution neural network layer for extracting visual information from images, an embedding layer for converting each word into a low dimensional feature, a recurrent neural network layer for learning caption sentence structure, and a multi-modal layer for combining visual and language information. In this model, the recurrent neural network layer is constructed by LSTM units, which are well known to be effective for learning and transferring sequence patterns. Moreover, this model has a unique structure in which the output of the convolution neural network layer is linked not only to the input of the initial state of the recurrent neural network layer but also to the input of the multimodal layer, in order to make use of visual information extracted from the image at each recurrent step for generating the corresponding textual caption. Through various comparative experiments using open data sets such as Flickr8k, Flickr30k, and MSCOCO, we demonstrated the proposed multimodal recurrent neural network model has high performance in terms of caption accuracy and model transfer effect.

• Journal of Digital Convergence
• /
• v.15 no.9
• /
• pp.453-461
• /
• 2017

The video image in the movie has become more spectacular than ever, and the expression area and the subject have been infinitely expanded, but it can not be said that the range of imagination has expanded. Instead, the 60s and 70s, which were the epochs of popular culture, The film that implements the artististic visual style and expression style of the artist. Stanley Kubrick's "Clockwork Orange", which has been pursuing technological perfection and experimental style, was created using traditional video grammar and gained a great repercussion with outstanding material and high artistic expression technique at that time. These techniques have led audiences to rational observation through irony, rather than emotional sympathy for the situation, for extreme violence and sensational films. This is because the purpose of the director was not to be in technological perfection but to reveal the contradictions of the real society and to reflect on the meaning of the existence of society itself. These creative traditional visual grammar and expression methods are a good visual style that enables the intentionally transmitted message to be transmitted more intensely and effectively, and the artistic depth can be created at the same time by unconsciously perceiving the meaning present on the back to the audience.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.141-150
• /
• 2012

This paper suggests a critical path search algorithm that can easily draw PERT/GANTT chart which manages and plans a project schedule. In order to evaluate a critical path that determines the project schedule, Critical Path Method (CPM) is generally utilized. However, CPM undergoes 5 stages to calculate the critical path for a network diagram that is previously designed according to correlative relationship and execution period of project execution activities. And it may not correctly evaluate $T_E$ (The Earliest Time), since it does not suggest the way how to determine the sequence of the nodes activities that calculate the $T_E$. Also, the sequence of the network diagram activities obtained from CPM cannot be visually represented, and hence Lucko suggested an algorithm which undergoes 9 stages. On the other hand, the suggested algorithm, first of all, decides the sequence in advance, by reallocating the nodes into levels after Breadth-First Search of the network diagram that is previously designed. Next, it randomly chooses nodes of each level and immediately determines the critical path only after calculation of $T_E$. Finally, it enables the representation of the execution sequence of the project activity to be seen precisely visual by means of a small movement of $T_E$ of the nodes that are not belonging to the critical path, on basis of the $T_E$ of the nodes which belong to the critical path. The suggested algorithm has been proved its applicability to 10 real project data. It is able to get the critical path from all the projects, and precisely and visually represented the execution sequence of the activities. Also, this has advantages of, firstly, reducing 5 stages of CPM into 1, simplifying Lucko's 9 stages into 2 stages that are used to clearly express the execution sequence of the activities, and directly converting the representation into PERT/GANTT chart.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.61 no.3
• /
• pp.140-148
• /
• 2012

Aeronautical lights, which are internationally standardized sequence of colors and placements, are aeronautic safety devices that provide visual information to pilots by continuously adjusting their light intensity to appropriate level. In this paper, we consider the development testing for in pavement LED aeronautical light system such as taxiway centerline, stop line and temporary stop line. The test results of LED sourced lights have shown a drastic improvement in power consumption levels and cost efficiency compared to their halogen sourced counterparts The LED light used only 42.7% as much power as their halogen sourced counterparts. Taking installation costs into account, LED will cost only 58% of its halogen counterparts. These results suggest that developing the LED sourced aeronautical light would result in globally competitive products thar guarantees satisfaction to their consumers, and that both cost effective and energy efficient.

• The Bulletin of The Korean Astronomical Society
• /
• v.40 no.1
• /
• pp.73.1-73.1
• /
• 2015

Isolated galaxies in low-density regions are significant in the sense that they are least affected by the hierarchical pattern of galaxy growth and interactions with perturbers at least for the last few Gyr. To form a comprehensive picture of the star formation history of isolated galaxies, we construct a catalog of isolated galaxies and their comparison sample in relatively denser environments. The galaxies are drawn from SDSS DR7 in the redshift range of 0.025 < z < 0.044. We performed visual inspection and classified their morphology following the Hubble classification scheme. We have investigated the color-magnitude diagram and found elliptical and unbarred spiral galaxies in isolated systems are relatively fainter and bluer than those in denser regions. For the spectroscopic study, we make use of the OSSY catalog (Oh et al. 2011). Our analysis on the absorption-line properties based on the comparison with stellar population models suggests that isolated elliptical galaxies are likely to be younger and metal poorer, while isolated Sc-type galaxies seem to have older luminosity-weighted ages, than their high-density counterpart. In addition, according to the BPT diagnostics, early-type galaxies among isolated galaxies are rather evenly classified into star forming, composite, Seyfert and LINER, whereas their comparisons are mainly populated in the LINER region. On the other hand, late-type galaxies do not show any prominent difference. We discuss the evolutionary histories of isolated galaxies in the context of the standard ${\Lambda}CDM$ cosmology.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.1 no.1
• /
• pp.51-54
• /
• 2009

In or automotive engineering education is introduced. Main objective of the system is teaching disassemble/assemble procedure of automatic transmission of a vehicle to students, who study automotive engineering. System includes vehicle transmission, set of tools and mechanical facilities, two video cameras, computer with developed software, HMD glasses and two LCD screens. Developed software gives instructions on assembling and disassembling processes of real vehicle transmission with the help of augmenting virtual reality objects on the video stream. Overlaying of 3D instructions on the technological workspace can be used as an interactive educational material. In disassembling process, mechanical parts which should be disassembled are augmented on video stream from video cameras. Same is done for assembling process. Animation and other visual effects are applied for better indication of the current assembling/disassembling instruction. During learning and training, student can see what parts of vehicle transmission and in which order should be assembled or disassembled. Required tools and technological operations are displayed to a student with the help of augmented reality, as well. As a result, the system guides a student step-by-step through an assembly/disassembly sequence. During educational process a student has an opportunity to return back to any previous instruction if it is necessary. Developed augmented reality system makes educational process more interesting and intuitive. Using of augmented reality system for engineering education in automotive technology makes learning process easier and financially more effective.

• Journal of Information Processing Systems
• /
• v.12 no.1
• /
• pp.46-56
• /
• 2016

Dynamic textures are videos that exhibit a stationary property with respect to time (i.e., they have patterns that repeat themselves over a large number of frames). These patterns can easily be tracked by a linear dynamic system. In this paper, a model that identifies the underlying linear dynamic system using wavelet coefficients, rather than a raw sequence, is proposed. Content based threshold filtering based on Set Partitioning in a Hierarchical Tree (SPIHT) helps to get another representation of the same frames that only have low frequency components. The main idea of this paper is to apply SPIHT based threshold filtering on different bands of wavelet transform so as to have more significant information in fewer parameters for singular value decomposition (SVD). In this case, more flexibility is given for the component selection, as SVD is independently applied to the different bands of frames of a dynamic texture. To minimize the time complexity, the proposed model is implemented on a graphics processing unit (GPU). Test results show that the proposed dynamic system, along with a discrete wavelet and SPIHT, achieve a highly compact model with better visual quality, than the available LDS, Fourier descriptor model, and higher-order SVD (HOSVD).

• The Plant Pathology Journal
• /
• v.33 no.1
• /
• pp.9-20
• /
• 2017

Incidence of leaf blast on nursery plants and pitting disease on maturing banana bunches has been recorded in banana plantations during rainy season in Eastern India during 2014 to 2015. Taxonomical identification as well as DNA sequence analysis of the internal transcribed spacer region of fungus isolated from affected tissue culture derived plantlets and fruits confirmed the pathogen to be Pyricularia angulata Hashioka "in both the cases". Koch's postulates were proved on young plantlets as well as on maturing fruits of cv. Grand Naine under simulated conditions. Evolutionary history was inferred and presented for our P. angulata strain PG9001 with GenBank accession no. KU984740. The analysis indicated that the P. angulata is phylogenitically distinct from other related species related to both Pyricularia and Magnaporthe. Detailed symptoms of blast lesions on young leaves, transition leaves, mid rib, petioles, peduncle, maturing bunches, bunch stalks and cushions were documented. Notably, the distinct small pitting spots on maturing bunches reduced the visual appeal of mature fruits. Appearance of pitting symptoms on fruits in relation with age of fruits and their distribution pattern on bunch and fingers was also documented in detail. Further, the roles of transitory leaves, weed hosts, seasonality on disease occurrence have also been documented.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1934-1935
• /
• 2011

In order for a service robot to perform several tasks, basically autonomous navigation technique such as localization, mapping, and path planning is required. The localization (estimation robot's pose) is fundamental ability for service robot to navigate autonomously. In this paper, we propose a new system for point pattern matching based visual global localization using spot lightings in ceiling. The proposed algorithm us suitable for system that demands high accuracy and fast update rate such a guide robot in the exhibition. A single camera looking upward direction (called ceiling vision system) is mounted on the head of the mobile robot and image features such as lightings are detected and tracked through the image sequence. For detecting more spot lightings, we choose wide FOV lens, and inevitably there is serious image distortion. But by applying correction calculation only for the position of spot lightings not whole image pixels, we can decrease the processing time. And then using point pattern matching and least square estimation, finally we can get the precise position and orientation of the mobile robot. Experimental results demonstrate the accuracy and update rate of the proposed algorithm in real environments.