• Journal of Korea Society of Industrial Information Systems
• /
• v.8 no.2
• /
• pp.14-20
• /
• 2003

This paper presents a text extraction method of camera based document image. It is more difficult to recognize camera based document image in comparison with scanner based image because of segmentation problem due to variable lighting condition and versatile fonts. Both document binarization and character extraction are important processes to recognize camera based document image. After converting color image into grey level image, gray level normalization is used to extract character region independent of lighting condition and background image. Local adaptive binarization method is then used to extract character from the background after the removal of noise. In this character extraction step, the information of the horizontal and vertical projection and the connected components is used to extract character line, word region and character region. To evaluate the proposed method, we have experimented with documents mixed Hangul, English, symbols and digits of the ETRI database. An encouraging binarization and character extraction results have been obtained.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.4
• /
• pp.721-729
• /
• 2012

In this paper, human sensibility is measured on multi-modal environment and a sensitivity lighting system is implemented according to driven emotional indexes. We use LED lighting because it supports ecological circumstance, high efficiency, and long lifetime. In particular, the LED lighting provides various color schemes even in single lighting bulb. To cognize the human sensibility, we use the image information and the arousal state information, which are composed of multi-modal basis and calculates emotional indexes. In experiments, as the LED lighting color vision varies according to users' emotional index, we show that it provides human friendly lighting system compared to the existing systems.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.363-366
• /
• 2005

In this paper, for detecting human faces under variations of lighting condition and facial expression, distance ranking feature and detection algorithm based on the feature are proposed. Distance ranking is the intensity ranking of a distance transformed image. Based on statistically consistent edge information, distance ranking is robust to lighting condition change. The proposed detection algorithm is a matching algorithm based on FFT and a solution of discretization problem in the sliding window methods. In experiments, face detection results in the situation of varying lighting condition, complex background, facial expression change and partial occlusion of face are shown

• Science of Emotion and Sensibility
• /
• v.14 no.2
• /
• pp.301-310
• /
• 2011

Today, the city greatly increase the interest in the night, increasing the importance of building and landscape lighting is a trend. Landscape lighting and a combination of factors, especially the media has been expanding in the domestic media facade. The facade of the building for the implementation of the screen to install the LED, or are projecting the image through the projector. The facade of this study present a paradigm shift in traditional media based on interactive and works by combining the artistry of the item type, art, colors, patterns, and interactions were drawn into 5 main topics. This section of the 83 kinds of domestic. Other media facade sample was classified. Categorized by 5 types of lighting techniques, lighting system, manner of expression, changing the way lighting design elements were based. Thus, the current trend changes, depending on the technical value and artistic value of the applied media facade lighting design should be applied to identify the elements and the combination of media facades and IT skills beyond simply directing programmed to communicate interactively with various designs Must be for you.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.372-376
• /
• 2008

Nowadays, active teachers expend much time and effort in preparing for classes. Especially, the basic formative calsses in art education have much effect when they are done with a lot of material(plaster casts, etc.) and lighting effect, but not in real. Proposed web-based learning instrument makes possible basic formative classes with simple operation by loading several materials and lighting operator on the web. In this paper, we propose web-based learning instrument to improve basic formative classes. Students will easily be able to express shadow and shade by lights with this web-based learning instrument in basic formative classes.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.6
• /
• pp.185-199
• /
• 1994

This study has been performed to present a new automatic tool wear measurement by digital image processing. The purpose of this paper is to develop an automatic tool wear measuring system based on the image processing which can be applied to the quasi-real time measurement of the characteristics of insert tip in turning. Tool wear monitoring is one of the key-problems, for the development of control systems of modern unmanned factory which are not completely solved now. In oredr words at present complete qualitative and quantitative information on tool wear morphology is required, at least on the following aspects : flank wear, its dimensions and distribution on the maximum and mean values on VB pqrqmeter in the various zones of the wearland. crater wear, its main dimensions and values of KT parameters. This research has been performed to this technique made possible by designing a proper lighting system to the worn tool with following features : The flank wear is measured by observing the active cutting part from a proper direction and by lighting the wearland by a diffuser optic system. The crater wear is visualized by lighting the tool by a He-Ne gas laser system developed in this study. By means of this system it is research to evaluate classical parameters of tool wear and to have complete information about tool wear morphology.

• Journal of Environmental Science International
• /
• v.23 no.6
• /
• pp.1013-1020
• /
• 2014

Based on the survey of the parks in Tai'an by questionnaire survey, on-the-spot investigation and in-depth interview, the paper analyzes the tendencies of visitors in modern landscape lighting design forms and methods from two terms: primary attributes and the preferences of artistic lighting design. To increase the safety of the parks is a pressing need for visitors. Visitors have a pressing need for increasing the safety of the parks' lighting and artistic quality. Most visitors think the parks' lighting has blind spots and the brightness is not enough. Visitors' night activities in the park will be insecure. As to artistry aspects, people prefer strong artistic style of lamps and lanterns to the common, such as ethnic style and animal image; Tourists prefer to use white light and yellow light to illuminate trees, because these colors make people feel more warm and amiable. This research provides basic data for lighting design of parks.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2213-2216
• /
• 2003

In this paper, we propose the face identification method which is robust for lighting based on the feature points method. First of all, the proposed method extracts an edge of facial feature. Then, by the hough transform, it determines ellipse parameters of each facial feature from the extracted edge. Finally, proposed method performs the face identification by using parameters. Even if face image is taken under various lighting condition, it is easy to extract the facial feature edge. Moreover, it is possible to extract a subject even if the object has not appeared enough because this method extracts approximately the parameters by the hough transformation. Therefore, proposed method is robust for the lighting condition compared with conventional method. In order to show the effectiveness of the proposed method, computer simulations are done by using the real images.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.399-410
• /
• 2021

Aiming at the problem that complex external variables in natural scenes have a greater impact on facial expression recognition results, a facial expression recognition method based on two-stream convolutional neural network is proposed. The model introduces exponentially enhanced shared input weights before each level of convolution input, and uses soft attention mechanism modules on the space-time features of the combination of static and dynamic streams. This enables the network to autonomously find areas that are more relevant to the expression category and pay more attention to these areas. Through these means, the information of irrelevant interference areas is suppressed. In order to solve the problem of poor local robustness caused by lighting and expression changes, this paper also performs lighting preprocessing with the lighting preprocessing chain algorithm to eliminate most of the lighting effects. Experimental results on AFEW6.0 and Multi-PIE datasets show that the recognition rates of this method are 95.05% and 61.40%, respectively, which are better than other comparison methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.3 no.5
• /
• pp.423-443
• /
• 2009

We present the design and implementation of a unique sensing and actuation application -- the Illuminator: a sensor network-based intelligent light control system for entertainment and media production. Unlike most sensor network applications, which focus on sensing alone, a distinctive aspect of the Illuminator is that it closes the loop from light sensing to lighting control. We describe the Illuminator's design requirements, system architecture, algorithms, implementation and experimental results. The system uses the Illumimote, a multi-modal and high fidelity light sensor module well-suited for wireless sensor networks, to satisfy the high-performance light sensing requirements of entertainment and media production applications. The Illuminator system is a toolset to characterize the illumination profile of a deployed set of fixed position lights, generate desired lighting effects for moving targets (actors, scenic elements, etc.) based on user constraints expressed in a formal language, and to assist in the set up of lights to achieve the same illumination profile in multiple venues. After characterizing deployed lights, the Illuminator computes optimal light settings at run-time to achieve a user-specified actuation profile, using an optimization framework based on a genetic algorithm. Uniquely, it can use deployed sensors to incorporate changing ambient lighting conditions and moving targets into actuation. Experimental results demonstrate that the Illuminator handles various high-level user requirements and generates an optimal light actuation profile. These results suggest that the Illuminator system supports entertainment and media production applications.