• Smart Media Journal
• /
• v.5 no.3
• /
• pp.30-34
• /
• 2016

Nowadays, there are a lot of Korean documents, which often need to be identified in one of printed or handwritten text. Early methods for the identification use structural features, which can be simple and easy to apply to text of a specific font, but its performance depends on the font type and characteristics of the text. Recently, the bag-of-words model has been used for the identification, which can be invariant to changes in font size, distortions or modifications to the text. The method based on bag-of-words model includes three steps: word segmentation using connected component grouping, feature extraction, and finally classification using SVM(Support Vector Machine). In this paper, bag-of-words model based method is proposed using SURF(Speeded Up Robust Feature) for the identification of machine printed and handwritten text in Korean documents. The experiment shows that the proposed method outperforms methods based on structural features.

• Journal of the Korean Society for Precision Engineering
• /
• v.31 no.6
• /
• pp.491-495
• /
• 2014

We developed a compact high-precision slot-die coating machine for thin-film deposition on a flexible substrate. For smooth and precise coating, air-bearing and linear motor system were employed to minimize velocity ripple. The gap control mechanism is specially designed to have repeatability of gap between nozzle and substrate under 1 ${\mu}m$. Due to extremely precise gap control, the machine can coat thin-films down to 50 nm with $200mm{\times}100mm$ size. A thin film of Ag nano-particle ink is coated for demonstration.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.2
• /
• pp.137-143
• /
• 2022

Composite materials, being light-weight and of high mechanical strength, are increasingly used in various industries such as the aerospace, automobile, sporting-goods manufacturing, and ship-building industries. Recently, manufacturing of composite materials using 3D printers has increased. 3D-printed composite materials are made in free-form and adapted for end-use by adjusting the fiber content and orientation. However, research on the machining of 3D printed composite materials is limited. The aim of this study is to develop a machine learning method to select machining conditions for machining of 3D-printed composite materials. The composite material was composed of Onyx and carbon fibers and stacked sequentially. The experiments were performed using the following machining conditions: spindle speed, feed rate, depth of cut, and machining direction. Cutting forces of the different machining conditions were measured by milling the composite materials. PCA, a method of machine learning, was developed to select the machining conditions and will be used in subsequent experiments under various machining conditions.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.3
• /
• pp.25-30
• /
• 2019

In this paper, we have analyzed manufacturing problems of the scaffold with pores using FDM 3D printer and PLGA. We suggested the solutions using 3SC practical TRIZ. We selected the final solution used machine learning. We reduced number of experiments using most influential factor after analysis print factors. We printed the scaffold and measured pore size. We created the regression model using python tensorflow. The print condition data of measured pore size was used as training data. We predicted the pore size of printed condition using regression model. We printed the scaffold using the predicted the print condition data. We quantitatively compare the predicted scaffold pore size data and the measured scaffold pore size data. We got satisfactory result.

• Journal of KIISE:Software and Applications
• /
• v.30 no.10
• /
• pp.904-911
• /
• 2003

In this paper, we propose an effective method for the distinction between machine-printed and handwritten Korean address images. It is important to know whether an input image is handwritten or machine-printed, because methods for handwritten image are quite different from those of machine-printed image in such applications as address reading, form processing, FAX routing, and so on. Our method consists of three blocks: valid connected components grouping, feature extraction, and classification. Features related to width and position of groups of valid connected components are used for the classification based on a neural network. The experiment done with live Korean address images has demonstrated the superiority of the proposed method. The correct classification rate for 3,147 testing images was about 98.85%.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.3
• /
• pp.472-478
• /
• 2012

The inspection machine in PCB (printed circuit board) assembly line checks assembly errors by inspecting the images inside of the component inspection region. The component inspection region consists of region of component package and region of soldering. It is necessary to extract the regions automatically for auto-teaching system of the inspection machine. We propose an image segmentation method to extract the component inspection regions automatically from images of PCB. The acquired image is transformed to HSI color model, and then segmented by several regions by clustering method. We develop a modified K-means algorithm to increase the accuracy of extraction. The heuristics generating the initial clusters and merging the final clusters are newly proposed. The vertical and horizontal projection is also developed to distinguish the region of component package and region of soldering. The experimental results are presented to verify the usefulness of the proposed method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.3
• /
• pp.554-559
• /
• 2009

This paper proposes a new method of weighted template matching fur machine-printed numeral recognition. The proposed weighted template matching, which emphasizes the feature of a pattern using adaptive Hamming distance on local feature areas, improves the recognition rate while template matching processes an input image as one global feature. The experiment compares confusion matrices of the template matching, error back propagation neural network classifier, and the proposed weighted template matching respectively. The result shows that the proposed method improves fairly the recognition rate of the machine-printed numerals.

• Journal of Korea Technical Association of The Pulp and Paper Industry
• /
• v.45 no.3
• /
• pp.1-8
• /
• 2013

Hanji has been used mainly for preservation paper because of superior mechanical properties. However, it was not used in printing for inkjet and laser printer-printed letters. In this study, machine-made Hanji was prepared with five different contents of paper mulberry 20, 40, 60, 80 and 100% and managed by same pressure calendering. By increasing of paper mulberry contents, tearing index and folding endurance of machine-made Hanji increased because of increased fiber-to-fiber bonding. Printability property of machine-made Hanji improved by decreasing of paper mulberry contents. After 20 hours accelerated aging, the initial folding endurance of machine-made Hanji was reduced by approximately one-fourth degree. Between 40 and 100% contents of paper mulberry was showed similar levels about preservation property. The machine-made Hanji of paper mulberry 60% content was suitable for permanence and printability properties using preservation paper and printer-printed letters.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.2
• /
• pp.97-103
• /
• 2016

This paper deals with the cycle time minimization problem that determines the productivity in printed circuit board (PCB) with n components using the m placement machines. This is known as production cycle time determination problem (PCTDP). The polynomial time algorithm to be obtain the optimal solution has been unknown yet, therefore this hard problem classified by NP-complete. This paper gets the initial assignment result with the machine has minimum unit placement time per each component firstly. Then, the balancing process with reallocation from overhead machine to underhead machine. Finally, we perform the swap optimization and get the optimal solution of cycle time $T^*$ within O(mn) computational complexity. For experimental data, the proposed algorithm can be obtain the same result as integer programming+branch-and-bound (IP+B&B) and B&B.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.4
• /
• pp.46-50
• /
• 2019

In this paper, We used the regression model of machine learning for improve the print quantity problem when which print scaffold with 400 ㎛ pore using FDM 3d printer. We have difficult to experiment with changing all factors in the field. So we reduced print quantity by selected two factors that most impact the pore size. We printed and measured scaffold 5 times under same conditions. We created regression model using scaffold pore size and print conditions. We predicted pore size of untested print condition using the regression model. After print scaffold with 400 ㎛ pore, we printed scaffold 5 times under same conditions. We compare the predicted scaffold pore size and the measured scaffold pore size. We confirmed that error is less than 1 % and we verified the results quantitatively.