• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.2
• /
• pp.318-328
• /
• 2014

In this paper, as a way of performance improvement of business card recognition in the mobile environment, we suggested a hybrid OCR agent which combines data using a parallel processing sequence between various algorithms and different kinds of business card recognition engines which have learning data. We also suggested an Image Processing Method on mobile cameras which adapts to the changes of the lighting, exposing axis and the backgrounds of the cards which occur depending on the photographic conditions. In case a hybrid OCR agent is composed by the method suggested above, the average recognition rate of Korean business cards has improved from 90.69% to 95.5% compared to the cases where a single engine is used. By using the Image Processing Method, the image capacity has decreased to the average of 50%, and the recognition has improved from 83% to 92.48% showing 9.4% improvement.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.3
• /
• pp.427-433
• /
• 2001

This paper proposes a web-based 3 dimensional face modeling system that makes a realistic facial model efficiently without any 30 scanner or camera that uses in the traditional methods. Without expensive image-input equipments, we can easily create 3B models only using front and side images. The system is available to make 3D facial models as we connect to the facial modeling server on the WWW which is independent from specific platforms and softwares. This system will be implemented using Java 3D API, which includes the functions and conveniences of developed graphic libraries. It is a Client/server architecture which consists of user connection module and 3D facial model creating module. Clients connect with the facial modeling server, input two facial photographic images, detects the feature points, and then create a 3D facial model modifying generic facial model with the points according to the procedures using only the web browser.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.14 no.3
• /
• pp.3-19
• /
• 1987

The purpose of this study was to investigate desirable width / height ratio of enclosed space and to offer basic information for the design of enclosed spaces. The data of this study were gathered from the experiment through simulation. Photographic sampling of 7 campus sites located in Kwanak campus of Seoul National University and slides of perspective drawings of enclosed spaces with various D/H ratio (12, 1, 2, 4, 6, 9, 12)were used for simulation. A response format was made using the method of paired comparison and students from various departments were randomly selected for evaluation. In the method of analysis of data Thurstone's equation of Comparative Judgement was used for calculating preference score. A1so non-linear regression analysis was used for finding out relations between preference and D/H ratio. The other method of data analysis were correlation, Chi - test. And the results were summarized as follows. 1. In sketch simulation the ratio of D/H 4 got the highest preference store. This result suggests that desirable D/H ratio of enclosed space is D/H 4. And at the lower range of D/H ratio, as ratio increases, the preference score increases. At the higher range of D/H ratio, however, as ratio increases, the preference score starts to decrease from the cardinal point of D/H 4. 2. In campus photograph simulation preference is influenced by slope, elevation change of floor, trees, lawn area, familiarity, space arrangement, and exterior shape of building besides D/H ratio. 3. The preference virtue was not significantly affected by order effect. This result suggests that order effect can be ignored in the study of visual preference. 4. There are so many factors related to preference that it is difficult to explore those factors without scientific information based on scientific method. We must carry out study for scientific approach of planning and design based on precise, complete simulation technique.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.6
• /
• pp.874-880
• /
• 2018

3D modeling is extensively used in the field of architecture, machinery and contents production such as movies. Modeling is a time-consuming task. In order to compensate for these drawbacks, attempts have recently been made to reduce the production period by applying 3D scanning technology. 3D scanning for small objects can be done directly with laser or optics, but large buildings and sculptures require expensive equipment, which makes it difficult to acquire data directly. In this study, 3D modeling data for a large object is acquired using photometry with using drones to acquire the image data. The maintenance method for uniform spacing between the sculpture and the drone, the measurement method for the flight line were presented. In addition, we presented a production environment that can utilize the obtained 3D point cloud data for animation and a rendered animation result to find ways to make it in various environments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.11
• /
• pp.919-927
• /
• 2013

In this paper, we present a perception-based tone mapping technique using histogram modification for displaying high dynamic range image. HDR (high dynamic range) tone mapping algorithms are used to display HDR image on LDR (low dynamic rnage) devices. Although perception-based tone mapping methods provides better performance, it dose not always produce good results for a wide variety of images. The proposed method reduces dynamic range by using the perception-based tone mapping function and histogram modification. A derivative of perception-based tone mapping function is used as constraint function of histogram and additional compensation process is performed. This method not only improves contrast by adopting different constraints on each pixel value, but also preserves more visual details. In order to prevent over enhancement, histogram modification technique is applied. Furthermore, it can control the rate of image contrast using control parameters. Subjective and objective evaluations show that proposed algorithm is better than existing algorithms.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.305-315
• /
• 2020

The purpose of this study is to compare algorithms of single photo resection, which determines the exterior orientation parameters used in fields such as photogrammetry, computer vision, robotics, etc. To this end, the algorithms were compared by generating experimental data by simulating terrain based on a camera used in aerial and close-range photogrammetry. Through experiments on aerial photographic camera that was taken almost vertically, it was possible to determine the exterior orientation parameters using three ground control points, but the Procrustes algorithm was sensitive to the configuration of the ground control points. Even in experiments with a close-range amateur camera where the attitude angles of the camera change significantly, the algorithm was sensitive to the configuration of the ground control points, and the other algorithms required at least six ground control points. Through experiments with two types of cameras, it was found that cosine lawbased spatial resection shows performance similar to that of a traditional photogrammetry algorithm because the number of iterations is short and no explicit initial values are required.

• Journal of KIISE:Information Networking
• /
• v.30 no.1
• /
• pp.17-23
• /
• 2003

In this Paper. we Propose a digital watermarking scheme for digital images based on a perceptual model, the frequency masking, texture making, and luminance masking Properties of the human visual system(HVS), which have been developed in the context of image compression. We embed two types of watermark, one is pseudo random(PN) sequences, the other is a logo image. To embed the watermarks, original images are decomposed into $8\times8$ blocks, and the discrete cosine transform(DCT) is carried out for each block. Watermarks are casted in the low frequency components of DCT coefficients. The perceptual model adjusts adaptively scaling factors embedding watermarks according to the local image properties. Experimental results show that the proposed scheme presents better results than that of non-perceptual watermarking methods for image qualify without loss of robustness.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.2C
• /
• pp.113-123
• /
• 2007

In Ubiquitous communication environment, various conversions of images are essential, and most digital images are compressed by standard methods such as the Joint Photographic Expert Group (JPEG) and Motion Picture Expert Group (MPEG) which are based on the discrete cosine transform (DCT). In this paper, various image resizing algorithms in the DCT domain are analyzed, and a new image resizing algorithm, which shows superior performance compared with the conventional methods, is proposed. For arbitrary-ratio image resizing in the DCT domain, several blocks of $8{\times}8$ DCT coefficients are converted into one block using the conversion formula in the proposed algorithm, and the size of the inverse discrete cosine transform (IDCT) is decided optimally. The performance is analyzed by comparing the peak signal to noise ratio (PSNR) between original images and converted images. The performance of the proposed algorithm is better than that of the conventional algorithm, since the correlation of pixels in images is utilized more efficiently.

• Cross-Cultural Studies
• /
• v.29
• /
• pp.25-53
• /
• 2012

The attitude of observer in the painting of history is to exclude a prejudice and a subjective view of an artist and to introduce a photograph, which is a record of objectivity, in the process of painting. Its ultimate intent is to redescribe the fact of an event's image intactly without any prejudice and to represent the event as a proven evidence that it was. The representation of history based on fact had already been conceived in imagination of renowned artists such as Francisco Goya or $Th{\acute{e}}odore$ $G{\acute{e}}ricault$ even before cameras were invented. What they portrayed was their own truth of reality which is gained through their observation, not a history that have corresponded to political ideologies, for all reliance on a limited tool of representation, painting. Furthermore, history was necessary for 19th century impressionism artists to be represented under proven fact in a neutral perspective excluding all subjective prejudice, not based on the representation with imagination. Edouard Manet in particular reconstited an instant moment on the basis of real proof of photograph without personal prejudice or opinion as if today's photojournalism. The catastrophic series by Andy Warhol and the photographic painting by Gerhard Richter show another role of painting in the realm of art, each of them implying information distortion and abuse by current media and intentional deformation toward history as Manet's painting of history. Today, the representation of an historical event that we experience in the era of the Internet and social networks having a great deal of information already came to be the exclusive property of the cutting edge mass media. Nevertheless, the attitude of observer which is realistic and contemplative in the realm of art is the crucial point in terms of artists' act as ever.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.3 no.2
• /
• pp.67-72
• /
• 2022

Ecological research relies on the interpretation of large amounts of visual data obtained from extensive wildlife surveys, but such large-scale image interpretation is costly and time-consuming. Using an artificial intelligence (AI) machine learning model, especially convolution neural networks (CNN), it is possible to streamline these manual tasks on image information and to protect wildlife and record and predict behavior. Ecological research using deep-learning-based object recognition technology includes various research purposes such as identifying, detecting, and identifying species of wild animals, and identification of the location of poachers in real-time. These advances in the application of AI technology can enable efficient management of endangered wildlife, animal detection in various environments, and real-time analysis of image information collected by unmanned aerial vehicles. Furthermore, the need for school education and social use on biodiversity and environmental issues using AI is raised. School education and citizen science related to ecological activities using AI technology can enhance environmental awareness, and strengthen more knowledge and problem-solving skills in science and research processes. Under these prospects, in this paper, we compare the results of our early 2013 study, which automatically identified African cichlid fish species using photographic data of them, with the results of reanalysis by CNN deep learning method. By using PyTorch and PyTorch Lightning frameworks, we achieve an accuracy of 82.54% and an F1-score of 0.77 with minimal programming and data preprocessing effort. This is a significant improvement over the previous our machine learning methods, which required heavy feature engineering costs and had 78% accuracy.