• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.17 no.4
• /
• pp.26-35
• /
• 2003

For the recognizing system to be classified the same or different images in the nature the rotation, scale and transition invariant features is to be necessary. There are many investigations to get the feature for the recognition system and the log-polar transform which is to be get the invariant feature for the scale and rotation is used. In this paper, we suggested the character recognition methods which are used the centroid method and the log-polar transform with the interpolation to get invariant features for the character recognition system and obtained the results of the above 50% differential ratio for the character features. And we obtained the about 90% recognition ratio from the suggested character recognition system using the BPEJTC which is used the invariant feature from the Mellin transform method for the reference image. and can be recognized the scaled and rotated input character. Therefore, we suggested the image character recognition system using the Mellin transform method and the BPEJTC is possible to recognize with the invariant feature for rotation scale and transition.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.651-658
• /
• 2021

Because bolts with anti-loosening coatings are used mainly for joining safety-related components in automobiles, accurate automatic screening of these coatings is essential to detect defects efficiently. The performance of the convolutional neural network (CNN) used in a previous study [Identification of bolt coating defects using CNN and Grad-CAM] increased with increasing number of data for the analysis of image patterns and characteristics. On the other hand, obtaining the necessary amount of data for coated bolts is difficult, making training time-consuming. In this paper, resorting to the same VGG16 model as in a previous study, transfer learning was applied to decrease the training time and achieve the same or better accuracy with fewer data. The classifier was trained, considering the number of training data for this study and its similarity with ImageNet data. In conjunction with the fully connected layer, the highest accuracy was achieved (95%). To enhance the performance further, the last convolution layer and the classifier were fine-tuned, which resulted in a 2% increase in accuracy (97%). This shows that the learning time can be reduced by transfer learning and fine-tuning while maintaining a high screening accuracy.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.2
• /
• pp.88-99
• /
• 2022

The river network is one of the essential topographical characteristics in river management. The river network which as previously constructed by the ground surveying method has recently begun to be efficiently constructed using the remote sensing datasets. Since it is difficult to remove these obstacles such as bridges in the urban rivers, it is rare to construct the urban river networks with the various obstacles. In this study, the Sentinel-2 satellite imagery was used to develop the automatic method for detecting the urban river networks without the obstacles and with the preserved boundaries as follows. First, the normalized difference water index image was generated using the multispectral bands of the given Sentinel-2 satellite imagery, and the binary image that could classify the water body and other regions was generated. Next, the morphological operations were employed for detecting the complete river networks with the obstacles removed and the boundaries preserved. As a result of applying the proposed methodology to Han River in Seoul, the complete river networks with the obstacles removed and the boundaries preserved were well constructed.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.3
• /
• pp.16-28
• /
• 2016

Advancing geo-spatial web technologies and their applications require compatible and interoperable heterogeneous browsers and platforms. Reduction of common or supporting components for web-based system development is also necessary. If properly understood and applied, OGC-based standards can be utilized as effective solutions for these problems. Thus, OGC standards are central to the design and development of web-based geo-spatial systems, and are particularly applicable to web services, which contain data processing modules. However, the application for OGC WPS 2.0 is at an early stage as compared with other OGC standards; thus, this study describes a test implementation of a web-based geo-spatial processing system with OGC WPS 2.0 focused on asynchronous processing functionality. While a binary thresholding algorithm was tested in this system, further experiments with other processing modules can be performed on requests for many types of processing from multiple users. The client system of the implemented product was based on open sources such as jQuery and OpenLayers, and server-side running on Spring framework also used various types of open sources such as ZOO project, and GeoServer. The results of geo-spatial image processing by this system implies further applicability and extensibility of OGC WPS 2.0 on user interfaces for practical applications.

• Journal of Broadcast Engineering
• /
• v.10 no.4 s.29
• /
• pp.474-487
• /
• 2005

T-DMB (Terrestrial-Digital Multimedia Broadcasting) adopted MPEG-4 BIFS (Binary Format for Scene) Core2D scene description profile and graphics profile as the standard of video associated data service. By using BIFS, we can support to overlay objects, i.e. text, stationary image, circle, polygon, etc., on the main display of receiving end according to the properties designated in broadcasting side and to make clickable buttons and website links on desired objects. Therefore, a variety of interactive data services can be served by BIFS. In this paper, we implement real-time video associated data service system far T-DMB. Our developing system places emphasis on real-time data service by user operation and on inter-working and stability with our previously developed video encoder. Our system consists of BIFS Real-time System, Automatic Stream Control System and Receiving Monitoring System. Basic functions of our system are designed to reflect T-DMB programs and characteristics of program production environment as a top priority. Our developed system was used in BIFS trial service via KBS T-DMB, it is supposed to be used in T-DMB main service after improvement process such as intensifying system stability.

• The Journal of Industrial Distribution & Business
• /
• v.9 no.12
• /
• pp.63-72
• /
• 2018

Purpose - In this study, it is classified the service quality dimension of mobile shopping app using Kano model. In addition, it is evaluated quality factors suitable for strategic management from the viewpoint of service provider through mobile application through binary dimension analysis. Research design, data, and methodology - In this study, seven quality dimensions such as information quality, reliability, immediacy, convenience, design, security and customer service were derived through related studies to make binary shopping quality app quality measurement. 37 sub-variables were set by each quality dimensions. Each questionnaire was composed of positive and negative items like Kano's proposed method, and the satisfaction coefficient suggested by Timko(1993) was examined to understand the influence of each factors on customer satisfaction. Results - As a result of research, shopping app users perceived unity quality factor in most items of service quality dimension such as information quality, reliability, immediacy, convenience and customer service. In addition, the satisfaction coefficient showed a good impression, quick response of the result, fast delivery, and the unsatisfactory coefficient showed more interest in personal information such as payment method safety, and transaction security. As a result of research, shopping app users perceived unity quality factor in most items of service quality dimension such as information quality, reliability, immediacy, convenience and customer service. And, in information quality, the information overload was classified as an apathetic quality component, while the related information provision belonged to an attractive quality component. In reliability quality, customized service provision was classified as an attractive quality component. In instant connectivity, the quality of the connection during transport was classified as an attractive quality component. In convenience quality, access to product information was classified as a one-way quality component. All components of designs quality were classified as attractive quality components, and in security quality, all of their components were all classified as one quality component. Lastly, in customer service, they components were all classified as a single quality component. In addition, the satisfaction coefficient showed a good impression, quick response of the result, fast delivery, and the unsatisfactory coefficient showed more interest in personal information such as payment method safety, and transaction security. Conclusion - In the online service environment, which is difficult to differentiate in terms of upward upgrading only by technological implementation and function, the results of this study can be suggested as a differentiating factor for major channels with customers rather than improve the brand image.

• Journal of Biomedical Engineering Research
• /
• v.25 no.5
• /
• pp.323-328
• /
• 2004

The development of group-specific tissue probability maps (TPM) provides a priori knowledge for better result of cerebral tissue classification with regard to the inter-ethnic differences of inter-subject variability. We present sequential procedures of group-specific TPM and evaluate the age effects in the structural differences of TPM. We investigated 100 healthy volunteers with high resolution MRI scalming. The subjects were classified into young (60, 25.92+4.58) and old groups (40, 58.83${\pm}$8.10) according to the age. To avoid any bias from random selected single subject and improve registration robustness, average atlas as target for TPM was constructed from skull-stripped whole data using linear and nonlinear registration of AIR. Each subject was segmented into binary images of gray matter, white matter, and cerebrospinal fluid using fuzzy clustering and normalized into the space of average atlas. The probability images were the means of these binary images, and contained values in the range of zero to one. A TPM of a given tissue is a spatial probability distribution representing a certain subject population. In the spatial distribution of tissue probability according to the threshold of probability, the old group exhibited enlarged ventricles and overall GM atrophy as age-specific changes, compared to the young group. Our results are generally consistent with the few published studies on age differences in the brain morphology. The more similar the morphology of the subject is to the average of the population represented by the TPM, the better the entire classification procedure should work. Therefore, we suggest that group-specific TPM should be used as a priori information for the cerebral tissue classification.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.221-241
• /
• 2018

Deep learning is getting attention recently. The deep learning technique which had been applied in competitions of the International Conference on Image Recognition Technology(ILSVR) and AlphaGo is Convolution Neural Network(CNN). CNN is characterized in that the input image is divided into small sections to recognize the partial features and combine them to recognize as a whole. Deep learning technologies are expected to bring a lot of changes in our lives, but until now, its applications have been limited to image recognition and natural language processing. The use of deep learning techniques for business problems is still an early research stage. If their performance is proved, they can be applied to traditional business problems such as future marketing response prediction, fraud transaction detection, bankruptcy prediction, and so on. So, it is a very meaningful experiment to diagnose the possibility of solving business problems using deep learning technologies based on the case of online shopping companies which have big data, are relatively easy to identify customer behavior and has high utilization values. Especially, in online shopping companies, the competition environment is rapidly changing and becoming more intense. Therefore, analysis of customer behavior for maximizing profit is becoming more and more important for online shopping companies. In this study, we propose 'CNN model of Heterogeneous Information Integration' using CNN as a way to improve the predictive power of customer behavior in online shopping enterprises. In order to propose a model that optimizes the performance, which is a model that learns from the convolution neural network of the multi-layer perceptron structure by combining structured and unstructured information, this model uses 'heterogeneous information integration', 'unstructured information vector conversion', 'multi-layer perceptron design', and evaluate the performance of each architecture, and confirm the proposed model based on the results. In addition, the target variables for predicting customer behavior are defined as six binary classification problems: re-purchaser, churn, frequent shopper, frequent refund shopper, high amount shopper, high discount shopper. In order to verify the usefulness of the proposed model, we conducted experiments using actual data of domestic specific online shopping company. This experiment uses actual transactions, customers, and VOC data of specific online shopping company in Korea. Data extraction criteria are defined for 47,947 customers who registered at least one VOC in January 2011 (1 month). The customer profiles of these customers, as well as a total of 19 months of trading data from September 2010 to March 2012, and VOCs posted for a month are used. The experiment of this study is divided into two stages. In the first step, we evaluate three architectures that affect the performance of the proposed model and select optimal parameters. We evaluate the performance with the proposed model. Experimental results show that the proposed model, which combines both structured and unstructured information, is superior compared to NBC(Naïve Bayes classification), SVM(Support vector machine), and ANN(Artificial neural network). Therefore, it is significant that the use of unstructured information contributes to predict customer behavior, and that CNN can be applied to solve business problems as well as image recognition and natural language processing problems. It can be confirmed through experiments that CNN is more effective in understanding and interpreting the meaning of context in text VOC data. And it is significant that the empirical research based on the actual data of the e-commerce company can extract very meaningful information from the VOC data written in the text format directly by the customer in the prediction of the customer behavior. Finally, through various experiments, it is possible to say that the proposed model provides useful information for the future research related to the parameter selection and its performance.

• 전자공학회논문지 IE
• /
• v.43 no.4
• /
• pp.65-75
• /
• 2006

This thesis deals with a wavelet-based method of denoising of infrared images contaminated with impulse noise and Gaussian noise, he method of thresholding the wavelet coefficients using derivatives and median absolute deviations of the wavelet coefficients of the detail subbands was proposed to effectively denoise infrared images with noises. Particularly, in order to eliminate the impulse noise the method of generating binary masks indicating locations of the impulse noise was selected. By this method, the threshold values dividing edges and noises were obtained more effectively proving the validity of the denoising method compared with the conventional wavelet shrinkage method.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.11
• /
• pp.2845-2854
• /
• 1998

Median filter can be implemented in the binary domain based on threshold decomposition, stacking property, and linear separability. In this paper, we develop one-dimensional and two-dimensional parallel algorithms for the median filter on a reconfigurable mesh with buses(RMESH) which is suitable for VLSI implementation. And we evaluate their performance by comparing the time complexities of RMESH algorithms with those of algorithms on mesh-connected computer. When the length of M-valued 1-D signal is N and w is the window width, the RMESH algorithm is done in O(Mw) time and mesh algorithm is done in $O(Mw^2)$ time. Beside, when the size of M-valued 2-D image is $N{\times}N$ and the window size is $w{\times}w$, our algorithm on $N{\times}N$ RMESH can be computed in O(Mw) time which is a significant improvement over the $O(Mw^2)$ complexity on $N{\times}N$ mesh.