• Korean Chemical Engineering Research
• /
• v.47 no.2
• /
• pp.179-184
• /
• 2009

Recent evolution of computer technology enhances the effectiveness of CFD(Computational Fluid Dynamics) analysis for the 3-dimensional complex transport phenomena including turbulent flows. Cheaper and easier than laser and ultra-sonic methods, the windows simulator name by CAMSI(Computer-Aided Management of Stereo Images) has been developed in order to implement the 3-dimensional image using a disparity histogram extracted from left and right stereo images. In our program using the area-based method, the matching pixel finding methods consist of SSD(Sum of Squared Distance), SAD(Sum of Absolute Distance), NCC(Normalized Correlation Coefficient) and MPC(Matching Pixel Count). On performing the program, stereo images on different window sizes for various matching pixel finding methods are compared reasonably. When the image has a small noise, SSD on small window size is more effective. Whereas there is much noise, NCC or MPC is more effective than SSD. CAMSI from the present study will be much helpful to implement the complex objects and to analyze 3-dimensional CFD around them.

• Journal of KIISE:Databases
• /
• v.35 no.5
• /
• pp.379-390
• /
• 2008

Due to the increase of the amount of image data, the demand for searching similar images is continuously increasing. Therefore, many researches about the content-based image retrieval (CBIR) are conducted to search similar images effectively. In CBIR, it uses image contents such as color, shape, and texture for more effective retrieval. However, when we apply CBIR to satellite images which are complex and pose the difficulty in using color information, we can have trouble to get a good retrieval result. Since it is difficult to use color information of satellite images, we need image segmentation to use shape information by separating the shape of an object in a satellite image. However, because satellite images are complex, image segmentation is hard and poor image segmentation results in poor retrieval results. In this paper, we propose a new approach to search similar images without image segmentation for satellite images. To do a similarity search without image segmentation, we define a similarity of an image by considering SIFT keypoint descriptors which doesn't require image segmentation. Experimental results show that the proposed approach more effectively searches similar satellite images which are complex and pose the difficulty in using color information.

• Journal of Korean Society of Rural Planning
• /
• v.23 no.4
• /
• pp.27-38
• /
• 2017

Humans are provided with a wide range of public benefits from ecosystems and agricultural ecosystems. But the establishment of the horticulture complex is a space that hampers the public ecosystem. Therefore, we have evaluated the creating landscape function of the horticulture complex and found improvement. A total of 20 landscape slides were used for the study. Korea-paddy field, Korea-vinyl greenhouse, Korea-glass greenhouse, Japan-vinyl greenhouse and Netherlands-glass greenhouse were selected as 4 slides. The evaluation used the AHP method and 10 adjectives Likert which compares 20 landscape slides. Four Korea-paddy fields were rated highly positive images. All 10 adjectives can be selected as representative images of production scenes. In most adjectives, four scenes of KVG1, KVG2, KVG3 and KVG4, which are the Korea-greenhouse scenes, were evaluated as negative images. Netherlands and Korea-glass greenhouse scenes and Japan-vinyl greenhouse scenes were generally positive images. In conclusion, it is confirmed that glass greenhouse scenery is higher than vinyl greenhouse scenery. And Japan and Netherlands scenery are higher and better than Korea. Therefore, JVG1 in Japan and NGG3 in the Netherlands were proposed to be set as landscape improvement targets.

• Journal of Multimedia Information System
• /
• v.7 no.1
• /
• pp.1-10
• /
• 2020

The image analysis is an important and predominant task for classifying the different parts of the image. The analysis of complex image analysis like histopathological define a crucial factor in oncology due to its ability to help pathologists for interpretation of images and therefore various feature extraction techniques have been evolved from time to time for such analysis. Although deep reinforcement learning is a new and emerging technique but very less effort has been made to compare the deep learning and deep reinforcement learning for image analysis. The paper highlights how both techniques differ in feature extraction from complex images and discusses the potential pros and cons. The use of Convolution Neural Network (CNN) in image segmentation, detection and diagnosis of tumour, feature extraction is important but there are several challenges that need to be overcome before Deep Learning can be applied to digital pathology. The one being is the availability of sufficient training examples for medical image datasets, feature extraction from whole area of the image, ground truth localized annotations, adversarial effects of input representations and extremely large size of the digital pathological slides (in gigabytes).Even though formulating Histopathological Image Analysis (HIA) as Multi Instance Learning (MIL) problem is a remarkable step where histopathological image is divided into high resolution patches to make predictions for the patch and then combining them for overall slide predictions but it suffers from loss of contextual and spatial information. In such cases the deep reinforcement learning techniques can be used to learn feature from the limited data without losing contextual and spatial information.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.14 no.2
• /
• pp.83-96
• /
• 2011

The open space of apartment complex has changed diversely according to construction periods which were divided into the introduction stage (the 1980s), the development stage (the 1990s), and the maturity stage (after 1999). This study set out to analyze the periodic changes of visual characteristics and preference with the open space of apartment complexes in Cheongju City. For analysis of visual characteristics and preference, nineteen adjectives that were determined to sufficiently express the feeling of the open space of apartment complex. The results are as follows. As for adjective image assessment by using descriptive statistics, favorable images were shown in complexes of maturity stage phase that were constructed after the liberalization of apartment sale in 1999. These results may be caused both by quantitative increase and diversification of materials in planting and landscaping furniture and by nature-friendly designing. The results of factor analysis by Varimax rotation method showed that common variance was 73.9%, which indicates higher explanation. The nineteen adjectives could be divided into three factors, 'pleasantness factor,' 'negative factor,' and 'irregular factor.' Visual preference was analysed by using Least significant Difference (LSD) by analysis of variance : complexes of maturity stage phase that were constructed according to the liberalization of apartment sale in 1999 were highest in assessment. The correlation between view preference and adjective images was analyzed by multiple regression analysis, and 'feeling like walking,' 'well-arranged,' 'beautiful,' 'friendly,' and 'clean' (in order) were adjective images that most affected the preference. As for the analysis of the correlation between visual preference and physical components of view, the preference increased as the rate of pavement and greens was higher, while it decreased as size of building was larger. Therefore, backgrounds of walking and greens had strong effects on the preference.

• Journal of the Korean Regional Science Association
• /
• v.31 no.3
• /
• pp.99-112
• /
• 2015

Observation of land surface temperature in industrial areas is problematic, as it is not possible to construct a network of weather stations with sufficiently high density and continuous operation in such zones. Multiphase remote sensing data that cover a wide area and take a short time to process can enable the user to precisely and continuously measure the current and changing land surface temperatures in a certain region. Jeollanam-Do in South Korea is undergoing rapid industrialization, with the establishment of a number of industrial complexes, such as the Gwangyang Steelworks, Yeosu Industrial Complex, Yulchon Industrial complex, and Daebul Industrial Complex. To look into the properties of industrial complex's temperature, this study uses the thermal band of Landsat 7 ETM+ images acquired under thermal infrared wavelengths in order to calculate and compare the surface temperatures of the four above-named industrial complexes. From this, it is possible to obtain the basic information about industrial complex for environmental and natural resource management, which will aid industrial complex planners in developing methods of addressing environmental problems.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.20 no.4
• /
• pp.369-375
• /
• 2011

Design is important in the IT, digital appliance, and auto industries. Aesthetic and art images are being applied for better quality of the products. Most image patterns are complex and much lead-time is required to implement them to the product design process. A precise reverse engineering method generating 2.5D engraving models from 2D artistic images is proposed through the image processing, NURBS interpolation and 2.5D reconstruction methods. To generate 2.5D TechArt models from the art images, boundary points of the images are extracted by using the adaptive median filter and the novel MBF (modified boundary follower) algorithm. Accurate NURBS interpolation of the points generates TechArt CAD models. Performance of the developed system has been confirmed through the quick turnaround 2.5D engraving simulation linked with the commercial CAD/CAM system.

• Applied Microscopy
• /
• v.37 no.2
• /
• pp.143-146
• /
• 2007

The objects of the nature have three dimensional (3-D) parameters. The 3-D profiles are embedded on the photographs and microscopic images. To understand 3-D configuration, stereo pair image with thick section is frequently employed. The perception of 3-D images is possible with the aid of stereoscopic glasses, although the expert can perceive 3-D images without the glasses. Anaglyphic stereo images are constructed by various softwares from commercial and freeware. Here we would like to present an easy anaglyphs construction method with Adobe $Photoshop^{(R)}$ based on tilting paired images from high voltage electron microscope. The anaglyphic stereo images constructed revealed the same 3-D perception with conventional stereoscopy. We could zoom in/out the anaglyph image digitally to investigate the detail configuration by real time. This method is expected to contribute to understanding complex structures 3 dimensionally.

• The Journal of the Korea Contents Association
• /
• v.3 no.2
• /
• pp.19-23
• /
• 2003

Neurons in the mammalian visual cortex can be dassified into the two main categories of simple cells and complex cells based on their response properties. Here, we find the complex features corresponding to the response of complex cells by applying the unsupervised independent component analysis network to input images. This result will be helpful to elucidate the information processing mechanism of neurons in primary visual cortex.

• Database Research
• /
• v.34 no.3
• /
• pp.148-158
• /
• 2018

The optical character recognition (OCR) is a technique to extract and recognize texts from images. It is an important preprocessing step in data analysis since most actual text information is embedded in images. Many OCR engines have high recognition accuracy for images where texts are clearly separable from background, such as white background and black lettering. However, they have low recognition accuracy for images where texts are not easily separable from complex background. To improve this low accuracy problem with complex images, it is necessary to transform the input image to make texts more noticeable. In this paper, we propose a method to segment an input image into text lines to enable OCR engines to recognize each line more efficiently, and to determine the final output by comparing the recognition rates of CLAHE module and Two-step module which distinguish texts from background regions based on image processing techniques. Through thorough experiments comparing with well-known OCR engines, Tesseract and Abbyy, we show that our proposed method have the best recognition accuracy with complex background images.