• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1356-1364
• /
• 2016

This paper proposes a novel aesthetic photo recomposition method using a deep convolutional neural network (DCNN). Previous recomposition approaches define the aesthetic score of photo composition based on the distribution of salient objects, and enhance the photo composition by maximizing the score. These methods suffer from heavy computational overheads, and often fail to enhance the composition because their optimization depends on the performance of existing salient object detection algorithms. Unlike previous approaches, we address the photo recomposition problem by utilizing DCNN, which shows remarkable performance in object detection and recognition. DCNN is used to iteratively predict cropping directions for a given photo, thus generating an aesthetically enhanced photo in terms of composition. Experimental results and user study show that the proposed framework can automatically crop the photo to follow specific composition guidelines, such as the rule of thirds.

• Journal of Korean Academy of Nursing
• /
• v.42 no.6
• /
• pp.819-832
• /
• 2012

Purpose: This study was conducted to identify risk factors that influence the probability and severity of elder abuse in community-dwelling older adults. Methods: This study was a cross-sectional descriptive study. Self-report questionnaires were used to collect data from community-dwelling Koreans, 65 and older (N=416). Logistic regression, negative binomial regression and zero-inflated negative binomial regression model for abuse count data were utilized to determine risk factors for elder abuse. Results: The rate of older adults who experienced any one category of abuse was 32.5%. By zero-inflated negative binomial regression analysis, the experience of verbal-psychological abuse was associated with marital status and family support, while the experience of physical abuse was associated with self-esteem, perceived economic stress and family support. Family support was found to be a salient risk factor of probability of abuse in both verbal-psychological and physical abuse. Self-esteem was found to be a salient risk factor of probability and severity of abuse in physical abuse alone. Conclusion: The findings suggest that tailored prevention and intervention considering both types of elder abuse and target populations might be beneficial for preventative efficiency of elder abuse.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.2
• /
• pp.48-55
• /
• 2008

In this paper we propose a novel method for image retrieval system using image segmentation and salient points. The proposed method consists of four steps. In the first step, images are segmented into several regions by JSEG algorithm. In the second step, for the segmented regions, dominant colors and the corresponding color histogram are constructed. By using dominant colors and color histogram, we identify candidate regions where objects may exist. In the third step, real object regions are detected from candidate regions by SIFT matching. In the final step, we measure the similarity between the query image and DB image by using the color correlogram technique. Color correlogram is computed in the query image and object region of DB image. By experimental results, it has been shown that the proposed method detects multi-object very well and it provides better retrieval performance compared with object-based retrieval systems.

• Journal of the Korean Society of Costume
• /
• v.40
• /
• pp.95-107
• /
• 1998

The purpose of this research paper is to offer basic data for cloth design which is intended to apply appropriate shape and catacity to cloth. Followings are the analyzed result of investigation which was conducted to figure out the character of middle aged from 35 to 59 years old-women body especially in lower half of their body. 177 women took part in this investigation. 1. As a result of analyzed characters for middle aged women body shape, taking a side view of body, there are great variance in thickness coefficient which indicates the size of body. 2. According to a comparison result of early middle aged women body shape with late middle aged women body shape, the value in height items get shorter otherwise the value in thickness items get longer getting older. It means late middle aged women are relatively fat. 3. For the analysis of women body especially in lower half, 8 factors were used. They are as followings. Factor 1. Side thickness of lower half. Factor 2. Width of lower half. Factor 3. Height of lower half Factor 4. Droop of underbelly Factor 5. Salient rate of buttocks. Factor 6. Length of buttocks. Factor 7. Salient rate of underbelly. Factor 8. Droop of buttocks 4. Lower half shapes of middle aged women were divided into three groups and the character of each group are as followings. 〈Group 1〉65.0% of women who took part in this investigation have this type of body shape. They have long value in height items and thickness items. 〈Group 2〉16.4% of women who take part in this investigation were belonged to this group. The value in height items were not so different from group 1 but the thickness value are shorter than group 1. Women of group 2 have slime body shape. 〈Group 3〉18.6% of women were belonged to group 3. They show the shortest value in height items otherwise the longest value in thickness items. Therefore they are the smallest and the fattest group in this investigation.

• Korean Journal of Cognitive Science
• /
• v.15 no.1
• /
• pp.43-67
• /
• 2004

Using qualitative research methodology, this study has investigated the semantic features of 39 nouns, which are classified into the categories of grains, fruits and vegetables. A survey has been conducted with a substantial number of undergraduate students, who were asked to describe any semantic features they associated with the lexical items within the three categories. The analysis of the survey data shows that the concepts of examples of fruits are defined predominantly by intrinsic semantic features, while those of grains and vegetables are defined noticeably by extrinsic semantic features rather than intrinsic ones. Intrinsic semantic features are any properties inherent in an object itself and extrinsic semantic features are defined as any properties constructed by association with other objects or personal experiences in a certain situation. However, this study does not maintain that either intrinsic or extrinsic semantic features solely define the concepts of the examples of the three categories. Instead, it concludes that both kinds of semantic features are involved in the representation of the concepts of those vocabularies, with intrinsic features salient in the category of fruits and extrinsic features salient in the categories of gains and vegetables.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.12
• /
• pp.547-552
• /
• 2014

As social multimedia sites are getting popular such as Flickr and Facebook, the amount of image information has been increasing very fast. So there have been many studies for accurate social image retrieval. Some of them were web image classification using semantic relations of image tags and BoVW(Bag of Visual Words). In this paper, we propose a method to detect salient region in images using GBVS(Graph Based Visual Saliency) model which can eliminate less important region like a background. First, We construct BoVW based on SIFT algorithm from the database of the preliminary retrieved images with semantically related tags. Second, detect salient region in test images using GBVS model. The result of image classification showed higher accuracy than the previous research. Therefore we expect that our method can classify a variety of images more accurately.

• The Journal of the Korea Contents Association
• /
• v.11 no.6
• /
• pp.18-25
• /
• 2011

Salient object attracts more and more attention from researchers due to its important role in many fields of multimedia processing like tracking, segmentation, adaptive compression, and content-base image retrieval. Usually, a saliency map is binarized into black and white map, which is considered as the binary mask of the salient object in the image. Still, the threshold is heuristically chosen or parametrically controlled. This paper suggests using the global optimal threshold to perform saliency map thresholding. This work also considers the usage of multi-level optimal thresholds and the local adaptive thresholds in the experiments. These experimental results show that using global optimal threshold method is better than parametric controlled or local adaptive threshold method.

• Journal of Korea Multimedia Society
• /
• v.14 no.3
• /
• pp.378-391
• /
• 2011

In this paper, we suggest a novel method of selecting visual information based on bottom-up visual attention of human. We propose a new model that improve accuracy of detecting attention region by using depth information in addition to low-level spatial features such as color, lightness, orientation, form and temporal feature such as motion. Motion is important cue when we derive temporal saliency. But noise obtained during the input and computation process deteriorates accuracy of temporal saliency Our system exploited the result of psychological studies in order to remove the noise from motion information. Although typical systems get problems in determining the saliency if several salient regions are partially occluded and/or have almost equal saliency, our system is able to separate the regions with high accuracy. Spatiotemporally separated prominent regions in the first stage are prioritized using depth value one by one in the second stage. Experiment result shows that our system can describe the salient regions with higher accuracy than the previous approaches do.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.5
• /
• pp.62-68
• /
• 2010

This study is to identify target locations with low false alarms on thermal infrared images obtained from natural environment. The proposed method is different from the previous researches because it uses morphology filters for Gabor response images instead of an intensity image in initial detection stage. This method does not need precise extracting a target silhouette to distinguish true targets or clutters. It comprises three distinct stages. First, morphological operations and adaptive thresholding are applied to the summation image of four Gabor responses of an input image to find out salient regions. The locations of extracted regions can be classified into targets or clutters. Second, local texture features are computed from salient regions of an input image. Finally, the local texture features are compared with the training data to distinguish between true targets and clutters. The multi-layer perceptron having three layers is used as a classifier. The performance of the proposed method is proved by using natural infrared images. Therefore it can be applied to real automatic target detection systems.

• Journal of Internet Computing and Services
• /
• v.12 no.5
• /
• pp.87-100
• /
• 2011

In this paper, we address a video summarization task as generating both visually salient and semantically important video segments. In order to find salient data points, one can use the OC-SVM (One-class Support Vector Machine), which is well known for novelty detection problems. It is, however, hard to incorporate into the OC-SVM process the importance measure of data points, which is crucial for video summarization. In order to integrate the importance of each point in the OC-SVM process, we propose a fuzzy version of OC-SVM. The Importance-based Fuzzy OC-SVM weights data points according to the importance measure of the video segments and then estimates the support of a distribution of the weighted feature vectors. The estimated support vectors form the descriptive segments that best delineate the underlying video content in terms of the importance and salience of video segments. We demonstrate the performance of our algorithm on several synthesized data sets and different types of videos in order to show the efficacy of the proposed algorithm. Experimental results showed that our approach outperformed the well known traditional method.