• ETRI Journal
• /
• v.38 no.1
• /
• pp.174-184
• /
• 2016

Information identification with image data by means of low-level visual features has evolved as a challenging research domain. Conventional text-based mapping of image data has been gradually replaced by content-based techniques of image identification. Feature extraction from image content plays a crucial role in facilitating content-based detection processes. In this paper, the authors have proposed four different techniques for multiview feature extraction from images. The efficiency of extracted feature vectors for content-based image classification and retrieval is evaluated by means of fusion-based and data standardization-based techniques. It is observed that the latter surpasses the former. The proposed methods outclass state-of-the-art techniques for content-based image identification and show an average increase in precision of 17.71% and 22.78% for classification and retrieval, respectively. Three public datasets - Wang; Oliva and Torralba (OT-Scene); and Corel - are used for verification purposes. The research findings are statistically validated by conducting a paired t-test.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.1
• /
• pp.961-970
• /
• 2021

This study aims to examine the impact of service recovery in building customer loyalty through the mediating role of customer satisfaction and corporate image. This study also aims to examine the reciprocal relationship between customer satisfaction and corporate image in building customer loyalty. This study uses data from 126 consumers who have received recovery for a service failure in five logistics companies which operates in Southeast Sulawesi in Indonesia, namely; JNEs; J&T Express; Pandu Logistics; MEC; and TiKi. Data was collected using a questionnaire which was then distributed to all respondents via google form. The distribution of respondents at each logistics company provider was as follows: 19 respondents were customers of JNEs; 17 respondents were customers of J&T Express; 32 respondents were customers of Pandu Logistics; 21 respondents were customers of MEC; and 37 respondents were customers of TiKi's. The structural model developed in this study was tested using Partial Least Squared (PLS) method. The research found that service recovery has a direct effect on customer satisfaction and corporate image as positive and significant. Customer satisfaction and corporate image have a reciprocal relationship which then roles in building customer loyalty. Service recovery has an indirect effect on customer loyalty through the mediating role of customer satisfaction and corporate image.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.3
• /
• pp.17-25
• /
• 1999

This paper proposes a new bit-serial multiplier/divider architecture to reduce the hardware complexity significantly and to maintain the same number of cycles compared with existing architectures. Since the proposed bit-serial multiplier/divider architecture does not extend the number of bits in registers and an adde $r_tractor to calculate a partial product or a partial remainder, the hardware overhead can be greatly reduced. In addition, the proposed architecture can perform an additio $n_traction and a shift operation in parallel and the number of cycles for $\textit{N}$-bit multiplication and division for the proposed circuits is $\textit{N}$ and $\textit{N}$ + 2, repectively. Thus, the number of cycles for multiplication and division is the same compared with existing architectures. The SliM Image Processor employs the proposed multiplier/divider architecture and proves the performance of the proposed architecture.cture.

• The Research Journal of the Costume Culture
• /
• v.16 no.3
• /
• pp.409-424
• /
• 2008

This study intends to analyze T-shirt designs, particularly in connection with pop art. 444 pieces of T-shirts which conveyed the pop art spirits of well-known designers were selected for five years from 2001 to 2005, through fashion magazines(Collection: Dong-ah TV, Collezioni: Italy). The findings are as follows. As for formative characteristics of pop art in T-shirts, previous studies were analyzed to set classifications criteria such as popularization of images, eroticism, lettering and graffiti, assemblage. The design factor of the image popularization includes everyday images, cartoon, celebrities, and caricature. Everyday images ranked first followed by cartoon, caricature and celebrities. The design factor of eroticism ranges from the see-through look, partial exposure of human body, symbolization of underwear, and to printing of sexy images. The see-through look was ranked first, followed by partial exposure of human body, symbolization of underwear, and printing of sexy images. The design factor of lettering and graffiti encompasses letters, numbers, symbols and logos. Adoption of letters, numbers or symbols was ranked first, followed by brand logos and graffiti. The design factor of Assemblage is closely related to a three-dimensional effect. Varied expressions are possible: combination of two different textiles and fusion of textile and non-textile. Combination of two different textiles are higher than fusion of textile and non-textile.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.4
• /
• pp.201-205
• /
• 2020

The structural texture is defined as a form which a texel is regularly repeated in the texture. Structural texture analysis/recognition has various industrial applications, such as automatic inspection of textiles, automatic testing of metal surfaces, and automatic analysis of micro images. In this paper, we propose a Convolution Neural Network (CNN) based system for structural texture analysis. The proposed method learns texles, which are components of textures to be classified. Then, this trained CNN recognizes a structural texture using a partial image obtained from input texture. The experiment shows the superiority of the proposed system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.918-920
• /
• 2011

In this paper, a simple edge pattern classification method is proposed for detecting straight line segments in an image corrupted by impulse noise. Corrupted images have complicated edge patterns. To detect straight line from an complicated edge pattern, it is needed to simplify the entire edge. The proposed algorithm separates the entire edge into 4 directional partial edge patterns. Each line segment is separated from the partial edge image where several line segments are overlapped, and then the straight line is detected. The results of the experiments emphasize that the proposed algorithm is simple but accurate.

• Journal of Internet Computing and Services
• /
• v.10 no.6
• /
• pp.219-228
• /
• 2009

The increased popularity of multimedia applications places a great demand on efficient data storage and transmission techniques. Some methods have been proposed to combine compression and encryption together to reduce the overall processing time, but they are either insecure or intensive computationally. specially, they are unsuitable to wireless communication of mobile device. We propose a novel solution called partial encryption, We introduce quadtree and zerotree wavelet image compression in this paper, it reduces computation for date transmission in mobile device, and does not reduce the compression rate. In conclusion, the proposed partial encryption schemes are fast, secure, and do not reduce the compression performance of underlying compression algorithm.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.28-31
• /
• 2003

In the present work, a main purpose is to propose a fuzzy integral-based aggregation framework to complementarily combine partial information due to lack of completeness. Based on Choquet integral (CI) viewed as monotone expectation, we take into account complementary, non-interactive, and substitutive aggregations of different sources of defective information. A CI-based system representing upper, conventional, and lower expectations is designed far handling three aggregation attitudes towards uncertain information. In particular, based on Choquet integrals for belief measure, probability measure, and plausibility measure, CI$\_$bi/-, CI$\_$pr/ and CI$\_$pl/-aggregator are constructed, respectively. To illustrate a validity of proposed aggregation framework, multiple matching systems are developed by combining three simple individual template-matching systems and tested under various image variations. Finally, compared to individual matchers as well as other traditional multiple matchers in terms of an accuracy rate, it is shown that a proposed CI-aggregator system, {CI$\_$bl/-aggregator, CI$\_$pl/-aggregator, Cl$\_$pl/-aggregator}, is likely to offer a potential framework for either enhancing completeness or for resolving conflict or for reducing uncertainty of partial information.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.36 no.5
• /
• pp.353-362
• /
• 2016

Thermal barrier coating (TBC) is an essential element consisting of a super-alloy base and ceramic coating designed to achieve long operational time under a high temperature and pressure environment. However, the top coat of TBC can be delaminated at certain temperatures with long operation time. As the delamination of TBC is directly related to the blade damage, the coupling status of the TBC should be assured for reliable operation. Conventional studies of nondestructive evaluation have been made for detecting generation of thermally grown oxide (TGO) or qualitatively evaluating delamination in TBC. In this study, the ultrasonic C-scan method was developed to obtain the damage map inside TBC by estimating the delamination in a quantitative way. All specimens were isothermally degraded at $1,100^{\circ}C$ with different time, having different partial delamination area. To detect partial delamination in TBC, the C-scan was performed by a single transducer using pulse-echo method with normal incidence. Partial delamination coefficients of 1 mm to 6 mm were derived by the proportion of the surface reflection signal and flaw signal which were theoretical signals using Rogers-Van Buren and Kim's equations. Using the partial delamination coefficients, the partial delamination maps were obtained. Regardless of the partial delamination coefficient, partial delamination area was increased when degradation time was increased in TBC. In addition, a decrease in partial delamination area in each TBC specimen was observed when the partial delamination coefficient was increased. From the portion of the partial delamination maps, the criterion for delamination was derived.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.22 no.2
• /
• pp.283-290
• /
• 1992

The purpose of this study was to evaluate the spatial relationship of facial bone more accurately. For this study, the three-dimensional images of dry skull were reconstructed using computer image analysis system and three-dimensional reconstructive program involved CT. The obtained results were as follows: 1. Three-dimensional reconstructive CT results in images that have better resolution and more contrast 2. It showed good marginal images of anatomical structure on both three-dimensional CT and computer image analysis system, but the roof of orbit, the lacrimal bone and the squamous portion of temporal bone were hardly detectable. 3. The partial loss of image data were observed during the regeneration of saved image data on three-dimensional CT. 4. It saved the more time for reconstruction of three-dimensional images using computer image analysis system. But, the capacity of hardware was limited for inputting of image data and three-dimensional reconstructive process. 5. We could observe the spatial relationship between the region of interest and the surrounding structures by three-dimensional reconstructive images without invasive method.