• Magazine of the Korean Society of Agricultural Engineers
• /
• v.36 no.3
• /
• pp.90-99
• /
• 1994

To investigate the undrained shear strength characteristics of marine soils with high water content, high compressibility and weak bearing capacity, a series of undrained triaxial tests with pore pressure measurements on undisturbed and disturbed Banwol marine clay in normally consolidated and overconsolidated states is carried out. The results and main conclusions of this study are summarized as follows : 1 . When the consolidation pressure is increased, the maximum deviator stress of disturbed and undistubed clay in normally consolidated state is increased. Pore pressure parameters and internal friction angle of undisturbed clay are greater than those of disturbed clay. 2. The relationship between pore pressure and axial strain of undisturbed clay in normally consolidated state can be expressed as a hyperbolic function like stress-strain relation proposed by Kondner. 3. In the pore pressure-axial strain relation of disturbed clay in normally consolidated state, failure ratio R'f is greatly deviated in the range of 0.7~0.9 proposed by Christian and Desai. 4. For overconsolided clay, when overconsolidation ratio (OCR) is increased, normalized maximum deviator stress is increased and maximum pore pressure is decreased gradually. 5. Cohesion of overconsolidated clay is greater than that of nomally consolidated clay and internal friction angle slightly is decreased. 6. Pore pressure parameter at failure (Af) of overconsolidated clay is varied with OCR, Af becomes negative values with increment in OCR

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.11
• /
• pp.345-350
• /
• 2020

Based on the analysis of physical and learning characteristics and requirements of the silver generation, a video English dictionary was developed and evaluated as English learning contents. The video English dictionary was developed using OCR as an input method and video as an output method, and 17 silver generations were evaluated for academic achievement, learning satisfaction, and ease of use. As a result of the analysis, both the text English dictionary and the video English dictionary showed high learning satisfaction, but the video English dictionary showed higher results than the text English dictionary in an academic achievement and ease of use.

• International journal of advanced smart convergence
• /
• v.8 no.3
• /
• pp.95-101
• /
• 2019

Recently, there have been many issues related to text recognition using Tesseract. One of these issues is that the text recognition accuracy is significantly lower for smaller fonts. Tesseract extracts text by creating an outline with direction in the image. By searching the Tesseract database, template matching with characters with similar feature points is used to select the character with the lowest error. Because of the poor text extraction, the recognition accuracy is lowerd. In this paper, we compared text recognition accuracy after applying various super-resolution methods to smaller text images and experimented with how the recognition accuracy varies for various image size. In order to recognize small Korean text images, we have used super-resolution algorithms based on deep learning models such as SRCNN, ESRCNN, DSRCNN, and DCSCN. The dataset for training and testing consisted of Korean-based scanned images. The images was resized from 0.5 times to 0.8 times with 12pt font size. The experiment was performed on x0.5 resized images, and the experimental result showed that DCSCN super-resolution is the most efficient method to reduce precision error rate by 7.8%, and reduce the recall error rate by 8.4%. The experimental results have demonstrated that the accuracy of text recognition for smaller Korean fonts can be improved by adding super-resolution methods to the OCR preprocessing module.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.6-10
• /
• 2021

Recognition of characters printed or marked on the PCB components from images captured using cameras is an important task in PCB components inspection systems. Previous optical character recognition (OCR) of PCB components typically consists of two stages: character segmentation and classification of each segmented character. However, character segmentation often fails due to corrupted characters, low image contrast, etc. Thus, OCR without character segmentation is desirable and increasingly used via deep neural networks. Typical implementation based on deep neural nets without character segmentation includes convolutional neural network followed by recurrent neural network (RNN). However, one disadvantage of this approach is slow execution due to RNN layers. LPRNet is a segmentation-free character recognition network with excellent accuracy proved in license plate recognition. LPRNet uses a wide convolution instead of RNN, thus enabling fast inference. In this paper, LPRNet was adapted for recognizing characters printed on PCB components with fast execution and high accuracy. Initial training with synthetic images followed by fine-tuning on real text images yielded accurate recognition. This net can be further optimized on Intel CPU using OpenVINO tool kit. The optimized version of the network can be run in real-time faster than even GPU.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.73-79
• /
• 2021

In the wave of the 4th industrial revolution, smart factory is required in many factories. However, small and mid-sized companies (SMEs) still have aging machines and are having difficulties in the data collection stage, which is the basis of smart factories. This study proposes a low cost monitoring method by using an open source based technology that extracts data from the image of the facility control panel without the need for modification of existing facilities. The proposed method was tested and evaluated for forging facilities in automobile parts manufacturing plants through prototyping. As a result of the evaluation, it was confirmed that low-cost facility monitoring is possible, and it will help SMEs build smart factories.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.133-137
• /
• 2023

In this paper, we developed a 'comprehensive pet management application' that combines pet AI diagnosis, animal hospital search, smart household accounts, and community functions. The application can solve the inconvenience of users who have to use multiple functions as separate applications, and can easily use pet AI diagnosis services through photos, provides animal hospital information using crawling, finds nearby animal hospitals, and supports smart households that can scan receipts using OCR text extraction techniques. By using this application, information necessary for raising pets such as health and consumption details of pets can be managed in one system.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.42 no.4
• /
• pp.373-379
• /
• 2009

This study investigated oxygen consumption rate (OCR), $Q_{10}$ coefficient and ammonia excretion rate of the greenling, Hexagrammos otakii Jordan et Starks with the average body weight of 250 g in a semi-recirculated respiratory measuring system. The experiment was done under three different water temperatures (10, 15, $20^{\circ}C$) and five different ambient ammonia concentrations (0, 2.5, 5, 10, 20 mg/L). As the water temperature and ambient ammonia concentration increased the OCR has significantly increased (P<0.05). Given experimental conditions, the OCR of greenling were $50.8{\sim}159.4\;mg\;O_2\;kg^{-1}\;hr^{-1}$ and the relationship of water temperature (T) and ambient ammonia concentration (C) on the OCR were following: OCR = 41.3 - 1.87T - 7.38C + $0.463T^2$ + $0.66lC^2$ + 0.642TC - $0.011T^3$ - $0.010C^2$ - $0.031TC^2$ - $0.001T^2$C ($r^2$= 0.9226). $Q_{10}$ coefficients were $1.88{\sim}3.50$ for $10^{\circ}C$ to $15^{\circ}C$, $1.03{\sim}2.73$ for $15^{\circ}C$ to $20^{\circ}C$ and $1.40{\sim}1.90$ for $10^{\circ}C$ to $20^{\circ}C$, respectively. In general, the ammonia excretion rate tended to increase with increasing of the water temperature within normal ambient ammonia concentration. However, interestingly, it was observed that ammonia was absorbed rather than excreted above the ambient ammonia concentration of $2.5\;mg\;L^{-1}$, regardless of the water temperature. Thus, the largest ammonia absorption rate (AAR) was obserbed at the level of $98.4\;mg\;TAN\;kg^{-1}\;hr^{-1}$. The relationship ambient ammonia concentration (C) on AAR was following: Y = 1.61 + $10.9X^{0.7}$ ($r^2$ = 0.889).

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.29-39
• /
• 2020

Purpose The atmosphere of respect for individual tastes that have spread throughout society has changed the consumption trend. As a result, the travel industry is also seeing customized travel as a new trend that reflects consumers' personal tastes. In particular, there is a growing interest in 'film-induced tourism', one of the areas of travel industry. We hope to satisfy the individual's motivation for traveling while watching movies with customized travel proposals, which we expect to be a catalyst for the continued development of the 'film-induced tourism industry'. Design/methodology/approach In this study, we implemented a methodology through 'OCR' of extracting and suggesting film location information that viewers want to visit. First, we extract a scene from a movie selected by a user by using 'OpenCV', a real-time image processing library. In addition, we detected the location of characters in the scene image by using 'EAST model', a deep learning-based text area detection model. The detected images are preprocessed by using 'OpenCV built-in function' to increase recognition accuracy. Finally, after converting characters in images into recognizable text using 'Tesseract', an optical character recognition engine, the 'Google Map API' returns actual location information. Significance This research is significant in that it provides personalized tourism content using fourth industrial technology, in addition to existing film tourism. This could be used in the development of film-induced tourism packages with travel agencies in the future. It also implies the possibility of being used for inflow from abroad as well as to abroad.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.53-60
• /
• 2021

The number of visually impaired and blind people is increasing, but braille translation textbooks for them are insufficient, which violates their rights to education despite their will. In order to guarantee their rights, this paper develops a learning system, HunMinJeomUm, that helps them access textbooks, documents, and photographs that are not available in braille, without the assistance of others. In our system, a smart phone app and web pages are designed to promote the accessibility of the blind, and a braille kit is produced using Arduino and braille modules. The system supports the following functions. First, users select documents or pictures that they want, and the system extracts the text using OCR. Second, the extracted text is converted into voice and braille. Third, a membership registration function is provided so that the user can view the extracted text. Experiments have confirmed that our system generates braille and audio outputs successfully, and provides high OCR recognition rates. The study has also found that even completely blind users can easily access the smart phone app.

• 전기산업
• /
• v.2 no.4
• /
• pp.58-63
• /
• 1991