• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.4
• /
• pp.179-184
• /
• 2021

Along with the development of the fourth industry, the public sector has increasingly paid more attention to search using drones and real-time monitoring, for various goals. The drones are used and researched to complete a variety of searching and monitoring missions, including search for missing persons, security, coastal patrol and monitoring, speed enforcement, highway and urban traffic monitoring, fire and wildfire monitoring, monitoring of illegal fishing in reservoirs and protest rally monitoring. Police stations, fire departments and military authorities, however, concentrate on the hardware part, so there are little research on efficient communication systems for the real-time monitoring of data collected from high-performance resolution and infrared thermal imagining cameras, and analysis programs suitable for special missions. In order to increase the efficiency of drones with the searching mission, this paper, therefore, attempts to propose an image analysis technique to increase the precision of search by producing image data suitable for searching missions, based on images obtained from drones and provide the foundation for improving relevant policies and establishing proper platforms, based on actual field cases and experiments.

• The KIPS Transactions:PartA
• /
• v.10A no.4
• /
• pp.397-404
• /
• 2003

Dedicated-purpose embedded Java system usually takes such model that all class files are converted into a single ROM Image by the ROMizer in the host computer, and then the Java virtual machine in the embedded system executes the image. Defining the ROM Image is a very important issue for embedded system with limited memory resource and low-performance processor since the format directly influences on the memory usage and effectiveness of accessing entries in classes. In this paper we have analyzed the ROMizer and especially the format of the ROM image implemented in the simpleRTJ embedded Jana virtual machine. The analysis says that memory space can be saved up to 50% compared to the original class file and access speed exceeds up to six times with the use of the ROMizer. The result of this study will be applied to develop a more efficient ROMizer for a ROM-based embedded Java system.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.20 no.2
• /
• pp.205-213
• /
• 2018

Development and validation of crop models often require measurements of biomass for the crop of interest. Considerable efforts would be needed to obtain a reasonable amount of biomass data because the destructive sampling of a given crop is usually used. The Kinect sensor, which has a combination of image and depth sensors, can be used for estimating crop biomass without using destructive sampling approach. This approach could provide more data sets for model development and validation. The objective of this study was to examine the applicability of the Kinect sensor for estimation of chinese cabbage fresh weight. The fresh weight of five chinese cabbage was measured and compared with estimates using the Kinect sensor. The estimates were obtained by scanning individual chinese cabbage to create point cloud, removing noise, and building a three dimensional model with a set of free software. It was found that the 3D model created using the Kinect sensor explained about 98.7% of variation in fresh weight of chinese cabbage. Furthermore, the correlation coefficient between estimates and measurements were highly significant, which suggested that the Kinect sensor would be applicable to estimation of fresh weight for chinese cabbage. Our results demonstrated that a depth sensor allows for a non-destructive sampling approach, which enables to collect observation data for crop fresh weight over time. This would help development and validation of a crop model using a large number of reliable data sets, which merits further studies on application of various depth sensors to crop dry weight measurements.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.6
• /
• pp.358-370
• /
• 2007

Software simulations have been widely used for the design and application development of a wireless sensor network that is an infrastructure of ubiquitous computing. In this study, we develop a sensor network simulator that can verify the behavior of sensor network applications, estimate execution time and power consumption, and simulate a large-scale sensor network. To implement the simulator, we use an instruction-level parallel discrete-event simulation method. Instruction-level simulation uses executable images loaded into a real sensor board as workload, such that it results in the high degree of details. Parallel simulation makes simulation of a large-scale sensor network possible by distributing workload into multiple computers. The simulator can predict the amount of power consumption based on operating time of modules in a sensor node and counting the number of executed instructions by kind. Also it can simulate ubiquitous applications with various scenarios and debug programs. Instruction traces used as workload for simulations are executable images produced by the cross-compiler for ATmega128L microcontroller.

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.9
• /
• pp.514-526
• /
• 2004

Microarray is a new technique for gene expression experiment, which has gained biologist's attention for recent years. This technology enables us to obtain hundreds and thousands of expression of gene or genotype at once using microarray Since it requires manual work to analyze patterns of gene expression, we want to develop an effective and automated tools to analyze microarray image. However it is difficult to analyze DNA chip images automatically due to several problems such as the variation of spot position, the irregularity of spot shape and size, and sample contamination. Especially, one of the most difficult problems in microarray analysis is the block and spot addressing, which is performed by manual or semi automated work in all the commercial tools. In this paper we propose a new algorithm to address the position of spot and block using a new concept of regular structure grid searching. In our algorithm, first we construct maximal I-regular sequences from the set of input points. Secondly we calculate the rotational angle and unit distance. Finally, we construct I-regularity graph by allowing pseudo points and then we compute the spot/block address using this graph. Experiment results showed that our algorithm is highly robust and reliable. Supplement information is available on http://jade.cs.pusan.ac.kr/~autogrid.

• Journal of Digital Contents Society
• /
• v.19 no.7
• /
• pp.1333-1339
• /
• 2018

Recently, as disasters caused by weather such as heavy rains have increased, interests in forecasting weather and disasters using radars have been increasing, and related studies have also been actively performed. As the Ministry of Environment(ME) has established and operated a radar network on a national scale, utilization of radars has been emphasized. However, persons in charge and researchers, who want to use the data from radars need to understand characteristics of the radar data and are also experiencing a lot of trials and errors when converting and calibrating the radar data from Universal Format(UF) files. Hence, this study developed a Radar Display and Analysis Program(RaDAP) based on Graphic User Interface(GUI) using the Java Programming Language in order for UF-type radar data to be generated in an ASCII-formatted image file and text file. The developed program can derive desired radar rainfall data and minimize the time required to perform its analysis. Therefore, it is expected that this program will contribute to enhancing the utilization of radar data in various fields.

• The Journal of Korean Association of Computer Education
• /
• v.6 no.3
• /
• pp.173-183
• /
• 2003

E-learning education methodology using the web has been as much activated with the introduction of the internet to our society. As for the web-based education, there is no exception in case of mathematics. However, when it comes to representing math equations by using HTML image tags, a type of web marked-up language, it can be hard to represent math equations that have structural features, and to do the search, resulting in the difficulty in reusing math related applications. Therefore, based on MathML and using ActiveX control technology, a math equation generating website was designed and implemented in this study. Since this system employed ActiveX control technology, it is possible to generate math equations without the limit of time and place on the web, and to manage the program with the most up-to-dale version. And in this system, it is also possible to save the math equations generated in this system to be referred to for their reuse in the future.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.1
• /
• pp.140-153
• /
• 2019

Cloase-range image information from drones and ground-based camera has been frequently used in the field of disaster mitigation with 3D modeling and mapping. In addition, the utilization of virtual reality(VR) is being increased by implementing realistic 3D models with the VR technology simulating disaster circumstances in large scale. In this paper, we created a VR training program by extracting realistic 3D models from close-range images from unmanned aircraft and digital camera on hand and observed several issues occurring during the implementation and the effectiveness in the case of a VR application in training for disaster mitigation. First of all, we built up a scenario of disaster and created 3D models after image processing with the close-range imagery. The 3D models were imported into Unity, a software for creation of augmented/virtual reality, as a background for android-based mobile phones and VR environment was created with C#-based script language. The generated virtual reality includes a scenario in which the trainer moves to a safe place along the evacuation route in the event of a disaster, and it was considered that the successful training can be obtained with virtual reality. In addition, the training through the virtual reality has advantages relative to actual evacuation training in terms of cost, space and time efficiencies.

• Korean Journal of Organic Agriculture
• /
• v.15 no.1
• /
• pp.59-69
• /
• 2007

This experiment was conducted to study the spring productivity and feeding value of hairy vetch varieties. We also measured DM yield and feeding value by analyze CP and CF that authors made possible to calculate TDN and RFV. The results can be summarized as follows; Dry matter yield were increased earlier autumn seeding date and later cut in spring. Differences of dry matter yield in earlier cut in spring was high in order of Ostsaat, Welta, Vv4712, Penn-02, Common and Minnie. Crude protein(CP) yield was increased when earlier autumn seeding date and later cut in spring. Total digestible nutrient(TDN) yield of hairy vetch varieties was decreased when later autumn seeding date, and was increased when later cut in spring. TDN yield was highest in Ostsaat and Welta varieties had highest dry matter yield. Acid detergent fiber(ADF) content was decreased when later autumn seeding date and was increased when later cut in spring. Neutral detergent fiber(NDF) content was decreased when later autumn seeding date. Average values for relative feed value(RFV) were 157% and 132% in both cut. It shows that a high feed value in all of hairy vetch varieties. Above all, the results presented that the optimal seeding date for cultivating hairy vetch in the central region of Korea is between the 10th to the 20th of September. Because Ostsaat and Welta had significantly high dry matter yield we expected Ostsaat and Welta have a higher wintering ability.