• The Journal of the Korea Contents Association
• /
• v.8 no.2
• /
• pp.140-149
• /
• 2008

With the advent of local autonomy, local governments are seeking balanced regional development through the decentralization of the central government's authority. In line with this trend, each province has begun to recognize the significance of local identity as a means to promote regional development, and this recognition contributed to developing various brands using local resources. However, a number of these brands are similar to one another because they were developed without thoroughly analyzing and strategically differentiating local identities from one another. Thus, this study aims to propose local characteristics and consumer consciousness that need to be considered in local speciality brand development through practical marine product brand development cases representing Yeosu's local characteristics. This study intends to contribute to setting an effective direction of marine product branding by applying local color to brand development strategies and brand identity elements and by suggesting post-management and promotion plans of local brand positioning.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.6
• /
• pp.1153-1158
• /
• 2006

The classification of the background and cell areas is very important research area because of the ambiguous boundary. In this paper, the region of cell is extracted from an image of uterine cervical cytodiagnosis using the region growing method that increases the region of interest based on similarity between pixels. Segmented image from background and cell areas is binarized using a threshold value. And then 8-directional tracking algorithm for contour lines is applied to extract the cell area. First, the extracted nucleus is transformed to RGB color that is the original image. Second, the K-means clustering algorithm is employed to classify RGB pixels to the R, G, and B channels, respectively. Third, the Hue information of nucleus is extracted from the HSI models that is the transformation of the clustering values in R, G, and B channels. The backpropagation algorithm is employed to classify and identify the normal or abnormal nucleus.

• Journal of Fashion Business
• /
• v.12 no.3
• /
• pp.99-115
• /
• 2008

International exchange gets active in nations with the increase of Internet use and heading toward digital age. Thus the communication conveying image of nations effectively plays an important role in an international society. Sports events are regarded as important international exchange events and good opportunities for public relations of one's own country and taken as tools of planting good images in other nations. This study surveyed the concept and history of uniform through the documents and previous studies in order to find the aesthetic characteristics of sportswear uniform applying the image of national ensign and investigates the origin and start time in Korea of selected 6 sports items. As a result of finding the expression way of ensign image and drawing the aesthetic characteristics by analyzing the use and variation of ensign colors, the use of colors other than ensign and reflection of ensign form in collected 60 sports uniforms, this study could draw the symbolical beauty, beauty of variation and beauty of brevity. First, symbolical beauty is the aesthetic characteristics expressing uniforms by using the pattern ensign symbolizes and ensign colors themselves or enlarging a part of ensign. Second, beauty of variation is the aesthetic characteristics creating geometrical new patterns in uniform through the distortion and exaggeration of ensign shape, or transforming the colors themselves of ensign. Third, beauty of brevity is the aesthetic characteristics using other colors only as decorative factor while applying the main colors of ensign to the most part of uniform, or unifying the uniforms with only one color of ensign. As a result of survey, the proportion of the symbolical beauty was highest in summer season and beauty of brevity and beauty of variation followed and the proportion of beauty of variation was highest and the symbolical beauty and beauty of brevity followed after that in winter season. This study found the way of expressing image of one's own country in sports uniform through this article, expecting the exact recognition on sports uniform and the diversity of sports uniform design in which the images of the nation are expressed more variously.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.530-533
• /
• 2009

This paper proposes a method of recognizing that a person doesn't put on a safety cap using image processing method in DSP(Digital Signal Processor). It processes inputted images by image input devices that equipped in a industrial settings. If the method recognizes a person that doesn't put on a safety cap, a system transfers relevant recognition result to a supervisor and takes proper measures. If an accident happens and someone doesn't put on a safety cap, additional casualities could be. Proposed method can nip additional casualties in the bud. To recognize that a person don't put on a safety cap, images are processed by object abstraction, removal of noise, decision of a thing or a person, abstraction of a head part in a image, recognizing whether a man puts on a safety cap using HSV color space or not, and so on. Image input and image process are processed by DSP. And C language-based codes are optimized by an eignefunction(Intrinsics) for speed improvement of algorithms.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.12
• /
• pp.75-83
• /
• 2018

Recently, autonomous vehicles have been actively studied. Pedestrian detection and recognition technology is important in autonomous vehicles. Pedestrian detection using CNN(Convolutional Neural Netwrok), which is mainly used recently, generally shows good performance, but there is a performance degradation depending on the environment of the image. In this paper, we propose a pedestrian detection system applying long-term memory structure of hippocampal neural network based on CNN network with LGP-FL (Local Gradient Pattern-Feature Layer) added. First, change the input image to a size of $227{\times}227$. Then, the feature is extracted through a total of 5 layers of convolution layer. In the process, LGP-FL adds the LGP feature pattern and stores the high-frequency pattern in the long-term memory. In the detection process, it is possible to detect the pedestrian more accurately by detecting using the LGP feature pattern information robust to brightness and color change. A comparison of the existing methods and the proposed method confirmed the increase of detection rate of about 1~4%.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.67-76
• /
• 2019

In this paper, we propose an efficient object classification method based on semantic segmentation for multi-labeled image data. In addition to various pixel unit information and processing techniques such as color information, contour, contrast, and saturation included in image data, a detailed region in which each object is located is extracted as a meaningful unit and the experiment is conducted to reflect the result in the inference. We use a neural network that has been proven to perform well in image classification to understand which object is located where image data containing various class objects are located. Based on these researches, we aim to provide artificial intelligence services that can classify real-time detailed areas of complex images containing various objects in the future.

• English & American cultural studies
• /
• v.14 no.1
• /
• pp.141-167
• /
• 2014

The macro structural perspective of how race was formed nationally, politically, and socially has greatly contributed in revealing the ills of racialism until now, likewise, the dichotomous form of Asian-American literature corresponding to such perspective has made great contribution in awakening people's awareness of race. While acknowledging the contribution of such macro perspectives, we must take note that today's racialism is becoming materialized in different aspects. The tendency of present racial formation is that the recognition of race is spread out lightly but widely in everyday lives and is revealed through the perception of our body. While publicly stating that society is color-blind and inequality significantly resolved, racialism emerges in the personal and everyday aspects. Not erased but diluted and spread out more widely, and the more diluted, harder to erase, racialism has penetrated into the perception of our lives. Racialism works not as a conspicuous discrimination but as a common sense that is 'naturally' absorbed into our perception and perspective. Chang Rae Lee's Aloft shows the process of such racial formation in our age of hybridization. This study tries to clarify why present racial formation must be analyzed in the macro perceptual perspective and show how the racial perception in the narrative of the white dominant narrator, Jerry, becomes the field where he lives and how it is spread through his perception. Through the theories of Judith Butler and Linda M. Alcoff, this study analyzes how people are got to self-identification with the racialization through reiteration and what the relationship is between racial formation and the subject's performativity in Aloft. The study concludes that revealing such current processes of racial formation perceptively is not thinking it 'natural' and inevitable but the process of bringing about a change in it.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.23 no.1
• /
• pp.129-142
• /
• 2021

This study aims to identify the perception of New-Hanbok one-piece dresses that female consumers have purchased and to analyze the design preference based on design types and brands. Analysis was conducted on New-Hanbok brand websites, and additional research was carried out through a survey of 402 women in their 20s and older. The survey consisted of 36 questions, which were divided into categories including pattern, color, material, and recognition of the one-piece dress. The research results are as follows. First, the preferred design form of the New-Hanbok one-piece dress was long length, medium fit, princess line, round git, rectangular git, regular width git, V neckline, regular width dongjeong, front closing with a wide overlap of the chest are a, narrow goreum, a skirt part with moderate crease spacing and number of pleats, A-line skirt silhouette, long and narrow sleeves, diagonal shoulder line, and a cuff at the end of each sleeve. Second, the preferred colors of the New-Hanbok one-piece dress were bright, neutral, or light and were predominately monochromatic Third, the preferred fabric conveyed a contemporary atmosphere through its print pattern. The most favored fabric material was cotton. Through this study, more systematic design development research should be carried out focusing on the current situation and identifying problems, thereby improving traditional culture.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.699-705
• /
• 2022

Purpose: Sequence control is widely used by being applied to manufacturing, distribution, construction, and automation in the medical industry. With the development of the fourth industry, artificial intelligence convergence technology in the control field is becoming an important factor in the industry. In particular, it is required to evaluate the safety and innovation of facilities where microprocessors and artificial intelligence are fused to existing systems and develop reliable equipment, so it is intended to develop equipment for educational purposes and drive the development of the field. Method: The self-developed all-in-one artificial intelligence controller module is a device that combines artificial intelligence capabilities with existing sequence and PLC control circuits. As the performance evaluation items of this equipment, the recognition ability of motion, voice, text, color, etc. and the stability and reliability of the circuit were evaluated. Conclusion: After designing the sequence and PLC circuit, the performance evaluation items of the integrated integrated artificial intelligence controller module were all satisfied, and there was no problem in the safety and reliability of the circuit.