• Journal of Internet Computing and Services
• /
• v.11 no.3
• /
• pp.15-24
• /
• 2010

In this paper, we propose an image classification which combines semantic relations of tags with contents of images to improve the satisfaction of image retrieval on application domains as huge image sharing sites. To make good use of image retrieval or classification algorithms on huge image sharing sites as Flickr, they are applicable to real tagged Web images. To classify the Web images by 'bag of visual word' based image content, our algorithm includes training the category model by utilizing the preliminary retrieved images with semantically related tags as training data and classifying the test images based on PLSA. In the experimental results on the Flickr Web images, the proposed method produced the better precision and recall rates than those from the existing method using tag information.

• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1313-1318
• /
• 2017

Aggregating local features in a single vector is a fundamental problem in an image search. In this process, the image search process can be speeded up if binary features which are extracted almost two order of magnitude faster than gradient-based features are utilized. However, in order to utilize the binary features in an image search, it is necessary to study the techniques for clustering binary features to generate binary visual words. This investigation is necessary because traditional clustering techniques for gradient-based features are not compatible with binary features. To this end, this paper studies the techniques for clustering binary features for the purpose of generating binary visual words. Through experiments, we analyze the trade-off between the accuracy and computational efficiency of an image search using binary features, and we then compare the proposed techniques. This research is expected to be applied to mobile applications, real-time applications, and web scale applications that require a fast image search.

• The Journal of the Korea Contents Association
• /
• v.11 no.1
• /
• pp.113-122
• /
• 2011

Visual images are very close to our living and we make decisions and choose behavioral options with the visual images on mass media. In current-affair documentary programs, interviews have potential effects that can change public opinions on important issues. Therefore, it's a consequence that the study examined how different expressions of visual images in documentary. Using preceding research methods, this study focus on form, color, movement and depth of visual images. This study analyzed quantitatively all interview shots with 15 current-affair documentary programs from major TV stations such as KBS, MBC and SBS. The findings of the study are 1) half of interview shots used the visual image expressions to hide interviewees' face according to the shield law, 2) choosing close-up shots in company with bust shots, 3) using natural lights and hand-held camera techniques for interviews, and 4) showing wide angles without depths of visual image.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.34 no.6
• /
• pp.23-30
• /
• 2018

Gordon Cullen, who tried to understand urban landscapes in terms of visual attention, introduced a concept called 'Space and Infinity' in his book 'Townscape'. According to him, urban images like infinity spreading across the sky are more effectively created when we happen to see an open space while walking along a ground-level street than when we look at the sky. This study aims to quantitatively examine if urban observers pay more attention to spaces like pilotis on the bottom of a building. Thus, this study collected observers on actual urban landscape images and partially-edited images and conducted an experiment by adopting Eye-movement Tracking to find out if they actually pay more visual attention to a space like pilotis. This study selected a total of 50 people as research subjects and divided them into two groups. Image 1 was shown to one group, and Image 2 with the pilotis space edited was shown to the other group. As an experiment to find objective evidences on Gordon Cullen's 'Space and Infinity', this study analyzed difference between Image 1 and Image 2, and it was found that the domain of pilotis showed a value five times higher than the average visual attention since it attracted much visual attention although it was very small in area. That is, it has objectively clarified that people get most fascinated with a place with infinite images in the background like a pilotis space out of all the urban landscapes as Gordon Cullen's theory. In addition, the differences in visual concentration of pilotis space by sex, by subject was examined, and there was no significant difference in visual concentration of pilotis space by gender. As a result of examining the difference of visual concentration by classifying the subjects into architectural related major, the major group showed higher frequency of viewing than the non - major group.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.23 no.1
• /
• pp.78-89
• /
• 1999

Clothes enhance visual images through the interaction between space and background of the wearer. The influence of background is important as that of the clothes when the observer understands the images. We look at fashion pictures used as important as that various backgrounds are presented depending on the image of the clothes. The clothing the model wears in the pictures takes on shape and space which supports the clothes. The background interact to from the whole image. The background has an important influence on the delivery of image for the clothes. However when the clothes are presented in the background there are some cases that all or parts of clothes can be shown. We must consider the composition ratio of the clothes and background which influences the whole image of the clothing. These interactions and influences on the whole image in regards to clothing background and the ratio will be the focus of this study. clothing was Modern Mannish Casual, Feminine, Ground was decided artificial setting 1 natural setting 1, indoor setting 1, artificial setting 2, natural setting 2, indoor setting 2, Percentage of Clothing was 80% , 140%, 200%,. Thus visual stimulus were 72 pictures that were combined Clothing Ground and Percentage of Clothing, the main survey of questionary consisted of their evaluation of the Picture image combined Clothing and Ground by 30 semantic differential bi-polar scales and the subjects were 50 students majoring in clothing and textile. The data analyzed by factor analysis MCA, MDS, The major finding were as follows : 1) As a result of factor analysis, 5 factors -Attractiveness Hardness and softness Cuteness Attention Cool and Warm factor were found out as constructing factors the Picture image combined Clothing and Ground 2) According to multidimensional positioning map were presented in a stimulus position the perceptive image differed in degree of similarity as a ground construction of stimulus in spite of same clothing image. It will aid in choosing the most beneficial background for any clothing brand. It will enhance the picture images to their full potential in any advertising medium.

• Journal of Fashion Business
• /
• v.15 no.2
• /
• pp.12-22
• /
• 2011

The purpose of this study is to evaluate the differences of visual image on variations in the shoulder strap and length of the one piece swimsuit. Nine samples were examined: 3 variations of the shoulder strap and 3 variations of the swimsuit length. Data have been obtained from 90 fashion design majors and analyzed using Factor Analysis, Anova, Scheffe's Test and the MCA method. The results of the study are as follows: 1) The visual image, according to changes in the shoulder strap and length of the one piece swimsuit, was composed of attraction factor and boldness factor. Attraction was the most important factor in the one piece swimsuit. 2) The visual images according to changes in the shoulder strap of the one piece swimsuits are ranked in the order of one shoulder strap, strapless and two shoulder straps. They are shown to be wanted to dress - sophisticated image and untidy - unique image. 3) As the swimsuit gets shorter, it has more wanted to dress - sophisticated image and untidy - unique image. 4) The number of shoulder straps and swimsuit length do interact with each other in attraction factor and boldness factor. In attraction factor, one shoulder strap and high cut of the one piece swimsuit has the most wanted to dress - sophisticated image. However two shoulder straps and low cut of the one piece swimsuit has the most not wanted to dress - countrified image. In boldness factor, one shoulder strap and high cut of the one piece swimsuit has the most untidy - unique image. However two shoulder straps and regular cut of the one piece swimsuit has the most tidy - ordinary image.

• Journal of Digital Contents Society
• /
• v.7 no.3
• /
• pp.153-160
• /
• 2006

It is not too much to say that invention of image divided the 19th and 20th century. Rapidly developed, produced and played images have a stronger effect on human beings and society. Today, images have an influence on forming interpersonal relationships by means of consciousness and ideas of new dimension, creating new image relationship different from verbal relationship between people. Especially moving image(image) is unlike other images, an image has unique psychological characteristics of its on. An image stimulates all the five human senses as well as sight, is easer to access and perceive than other media, and unable to control image development passively in general but get absorbed unconsciously very quickly. On 21th century As we are exposed to image whether consciously or unconsciously everyday, consideration on current times driving human beings and social relationship in an abnormal way is needed. Furthermore, new view of image study suggest to new relation of image that is a key factor to recover humanity and functions of society.

• The Journal of Korea Robotics Society
• /
• v.2 no.2
• /
• pp.129-136
• /
• 2007

This paper introduces a position-based robust visual servoing method which is developed for operation of a human-like robot with two arms. The proposed visual servoing method utilizes SIFT algorithm for object detection and CAMSHIFT algorithm for object tracking. While the conventional CAMSHIFT has been used mainly for object tracking in a 2D image plane, we extend its usage for object tracking in 3D space, by combining the results of CAMSHIFT for two image plane of a stereo camera. This approach shows a robust and dependable result. Once the robot's task is defined based on the extracted 3D information, the robot is commanded to carry out the task. We conduct several position-based visual servoing tasks and compare performances under different conditions. The results show that the proposed visual tracking algorithm is simple but very effective for position-based visual servoing.

• Journal of Welding and Joining
• /
• v.18 no.3
• /
• pp.60-67
• /
• 2000

In this study, we constructed a preview-sensing visual sensor system for weld seam tracking in GMA welding. The visual sensor consists of a CCD camera, a diode laser system with a cylindrical lens and a band-pass-filter to overcome the degrading of image due to spatters and/or arc light. To obtain weld joint position and edge points accurately from the captured image, we compared Hough transform method with central difference method. As a result, we present Hough transform method can more accurately extract the points and it can be applied to real time weld seam tracking. Image processing is carried out to extract straight lines that express laser stripe. After extracting the lines, weld joint position and edge points is determined by intersecting points of the lines. Although a spatter trace is in the image, it is possible to recognize the position of weld joint. Weld seam tracking was precisely implemented with adopting Hough transform method, and it is possible to track the weld seam in the case of offset angle is in the region of $\pm15^{\circ}$.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.8
• /
• pp.1843-1859
• /
• 2013

The continuous increase of the spatial resolution of remote sensing images brings great challenge to image analysis and processing. Traditional prior knowledge-based region detection and target recognition algorithms for processing high resolution remote sensing images generally employ a global searching solution, which results in prohibitive computational complexity. In this paper, a more efficient region of interest (ROI) detection algorithm based on visual attention and threshold segmentation (VA-TS) is proposed, wherein a visual attention mechanism is used to eliminate image segmentation and feature detection to the entire image. The input image is subsampled to decrease the amount of data and the discrete moment transform (DMT) feature is extracted to provide a finer description of the edges. The feature maps are combined with weights according to the amount of the "strong points" and the "salient points". A threshold segmentation strategy is employed to obtain more accurate region of interest shape information with the very low computational complexity. Experimental statistics have shown that the proposed algorithm is computational efficient and provide more visually accurate detection results. The calculation time is only about 0.7% of the traditional Itti's model.