• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.24 no.4
• /
• pp.484-491
• /
• 2014

Objectives: An image processing program for asbestos fibers analyzing the gradient components and partial linearity was developed in order to accurately segment fibers. The objectives were to increase the accuracy of counting through the formulation of the size and shape of fibers and to guarantee robust fiber detection in noisy backgrounds. Methods: We utilized samples mixed with sand and sepiolite, which has a similar structure to asbestos. Sample concentrations of 0.01%, 0.05%, 0.1%, 0.5%, 1%, 2%, and 3%(w/w) were prepared. The sand used was homogenized after being sieved to less than $180{\mu}m$. Airborne samples were collected on MCE filters by utilizing a personal pump with 2 L/min flow rate for 30 minutes. We used the NIOSH 7400 method for pre-treating and counting the fibers on the filters. The results of the NIOSH 7400 method were compared with those of the image processing program. Results: The performance of the developed algorithm, when compared with the target images acquired by PCM, showed that the detection rate was on average 88.67%. The main causes of non-detection were missing fibers with a low degree of contrast and overlapping of faint and thin fibers. Also, some duplicate countings occurred for fibers with breaks in the middle due to overlapping particles. Conclusions: An image detection algorithm that could increase the accuracy of fiber counting was developed by considering the direction of the edge to extract images of fibers. It showed comparable results to PCM analysis and could be used to count fibers through real-time tracking by modeling a branch point to graph. This algorithm can be utilized to measure the concentrations of asbestos in real-time if a suitable optical design is developed.

• Journal of KIISE
• /
• v.44 no.9
• /
• pp.992-1004
• /
• 2017

To assess image quality accurately, an image quality assessment (IQA) metric is required to reflect the human visual system (HVS) properly. In other words, the structure, color, and contrast ratio of the image should be evaluated in consideration of various factors. In addition, as mobile embedded devices such as smartphone become popular, a fast computing speed is important. In this paper, the proposed IQA metric combines color similarity, gradient similarity, and phase similarity synergistically to satisfy the HVS and is designed by using optimized pooling and quantization for fast computation. The proposed IQA metric is compared against existing 13 methods using 4 kinds of evaluation methods. The experimental results show that the proposed IQA metric ranks the first on 3 evaluation methods and the first on the remaining method, next to VSI which is the most remarkable IQA metric. Its computing speed is on average about 20% faster than VSI's. In addition, we find that the proposed IQA metric has a bigger amount of correlation with the HVS than existing IQA metrics.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.9
• /
• pp.2199-2205
• /
• 2013

In modern society the image processing has been applied to various digital devices such as smartphone, digital camera, and digital TV. In the field of image processing the edge detection is one of the important parts in the image processing procedure. The image edge means point that the pixel value is changed between background and object rapidly, and includes the important information such as magnitude, location, and orientation. The performance of the existing edge detection method is insufficient for the image degraded by AWGN(additive white Gaussian noise) because it detects edges by using small weighted masks. Therefore, in this paper, to detect edge in AWGN environment effectively, we proposed an algorithm that detects edge as calculated gradient of sorting vector which is transformed by estimated mask from new pixel according to each region.

• The Journal of the Korea Contents Association
• /
• v.14 no.12
• /
• pp.555-564
• /
• 2014

The boundary noise in image syntheses using DIBR consists of noisy pixels that are separated from foreground objects into background region. It is generated mainly by edge misalignment between the reference image and depth map or blurred edge in the reference image. Since hole areas are generally filled with neighboring pixels, boundary noise adjacent to the hole is the main cause of quality degradation in synthesized images. To solve this problem, a new boundary noise removal algorithm using a preprocessing of the depth map is proposed in this paper. The most common way to eliminate boundary noise caused by boundary misalignment is to modify depth map so that the boundary of the depth map can be matched to that of the reference image. Most conventional methods, however, show poor performances of boundary detection especially in blurred edge, because they are based on a simple boundary search algorithm which exploits signal gradient. In the proposed method, a two-step hierarchical approach for boundary detection is adopted which enables effective boundary detection between the transition and background regions. Experimental results show that the proposed method outperforms conventional ones subjectively and objectively.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.4
• /
• pp.239-245
• /
• 2010

Previous painterly rendering techniques normally use image gradients for stroke generation. Although image gradients are useful for expressing object shapes, it is difficult to express the flow or movements of objects of objects. In real painting, the use of brush strokes corresponding to the actual movement of objects allows viewers to recognize objects’ motion better and express the liveliness of the objects much more. In this paper, we propose a novel painterly stroke generation algorithm to express dynamic objects based on their motion information. We first extract motion information (magnitude, direction) of a scene from a set of image sequences from the same view. Then the motion directions are used for determining stroke orientations in the regions with significant motions. Where little motion is observed, image gradients are used for determining stroke orientations. Our algorithm is useful for realistically and dynamically representing moving objects.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.95-103
• /
• 2017

Horizon correction is a crucial stage for image composition enhancement. In this paper, we propose a deep learning based method for estimating the slanted angle of a photograph and correcting it. To estimate and correct the horizon direction, existing methods use hand-crafted low-level features such as lines, planes, and gradient distributions. However, these methods may not work well on the images that contain no lines or planes. To tackle this limitation and robustly estimate the slanted angle, we propose a convolutional neural network (CNN) based method to estimate the slanted angle by learning more generic features using a huge dataset. In addition, we utilize multiple adaptive spatial pooling layers to extract multi-scale image features for better performance. In the experimental results, we show our CNN-based approach robustly and accurately estimates the slanted angle of an image regardless of the image content, even if the image contains no lines or planes at all.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.13 no.2
• /
• pp.37-70
• /
• 1985

The purpose of this study is to present objective basic data for environmental design by the quantitative analysis of visual quality emboded in physical environment. For this, as for the front garden of high schools, the spatial image was measured by the S.D. Scale Method, Factor Analysis was proceeded by the principal component analysis and the visual preference was investigated by the Paired Comparision Method. The scale values of plain and unpleasant road surface and external appearance of buildings, which are related to emotions of simpleness fell from straightness and stability, were found to be high. But, except for the road surface of Kyunggi High School, scale values of variables explaining the variation of the quality of materials, level of floor and rythm were generally low. For all green spaces, scale values of variables explaining the degree of pleasantness was found to be generally high. And, those explaining tidiness and characteristics of green spaces were not in the same tendency. But, the green spaces of Youngdong High school can be considered to the space with plenty of visual absorption uniqueness were high. As for the correlation between variables, variables for green spaces(12 and 26) and those for overall view of front garden( 1 and 4) revealed high positive correlation. Also, "order - disorder" and "convenient- incovenient" included in road surface variable can be regarded to have the same meaning since the correlation coefficient between them is very high, 0.7045. Image variables including road surface, external appearance of buildings, green spaces and overall view of front garden showed 91.21~61.08% of total variance. Thus, the remains can be considered to be the error valiance or specific variance. In Fctor I, II and III, main components explaining the road surface image of front gardens are order, hardness, texture, color, gradient and rythm. As for the external appearance of b wilding, variables of color, hardness, stability, peculiality and shape revealed high values of factor load. For all variables, communality was drastically high and ellen values and common variance were found to be very high in Factor I. As for the front gardens, variables explaining volume and peculiarity were found to be the main components of Factor I. In Factor II and III, variables of factor load were tidiness, pleasantness.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.12B
• /
• pp.2359-2368
• /
• 1999

In this paper we propose a 2D FLIR image-based 3D target recognition system which performs group-to-ground vehicle recognition using the target contour and its degree of reliability extracted from FLIR image. First we extract target from background in FLIR image. Then we define contour points of the extracted target which have high edge gradient magnitude and brightness value as reliable contour point and make reliable contour by grouping all reliable contour points. After that we extract corresponding reliable contours from model contour image and perform comparison between scene and model features which are calculated by DST(discrete sine transform) of reliable contours. Experiment shows that the proposed algorithm work well and even in case of imperfect target extraction it showed better performance then conventional 2D contour-based matching algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.10
• /
• pp.2163-2170
• /
• 2009

We present an automated, energy minimized-based method for Lung parenchyma segmenting Chest Computed Tomography(CT) datasets. Deformable model is used for energy minimized segmentation. Quantitative knowledge including expected volume, shape of Chest CT provides more feature constrain to diagnosis or surgery operation planning. Segmentation subdivides an lung image into its consistent regions or objects. Depends on energy-minimizing, the level detail image of subdivision is carried. Segmentation should stop when the objects or region of interest in an application have been detected. The deformable model that has attracted the most attention to date is popularly known as snakes. Snakes or deformable contour models represent a special case of the general multidimensional deformable model theory. This is used extensively in computer vision and image processing applications, particularly to locate object boundaries, in the mean time a new type of external force for deformable models, called gradient vector flow(GVF) was introduced by Xu. Our proposed algorithm of deformable model is new external energy of GVF for exact segmentation. In this paper, Clinical material for experiments shows better results of proposal algorithm in Lung parenchyma segmentation on Chest CT.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.4
• /
• pp.273-280
• /
• 2013

This paper presents novel OCS-LBP (Oriented Center Symmetric Local Binary Patterns) based on orientation of pixel gradient and image retrieval system based on BoF (Bag-of-Feature) and random forest classifier. Feature vectors extracted from training data are clustered into code book and each feature is transformed new BoF feature using code book. BoF features are applied to random forest for training and random forest having N classes is constructed by combining several decision trees. For testing, the same OCS-LBP feature is extracted from a query image and BoF is applied to trained random forest classifier. In contrast to conventional retrieval system, query image selects similar K-nearest neighbor (K-NN) classes after random forest is performed. Then, Top K similar images are retrieved from database images that are only labeled K-NN classes. Compared with other retrieval algorithms, the proposed method shows both fast processing time and improved retrieval performance.