• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2009.11a
• /
• pp.54-57
• /
• 2009

This study was aimed to investigate the effects of visual texture on color emotion and to establish prediction models for color emotion by both physical color properties and visual texture characteristics. A variety of fabrics were printed by digital printer according to hue and tone combinations. Subjective sensation was evaluated in terms of visual texture for fabrics printed in gray whereas color emotion for those in chromatically printed. As results, fabric clusters by visual texture showed significant differences in color emotion factors and the differences were clearer for grayish tone fabrics. Prediction models for color emotion factors by both physical color properties and visual texture clusters were proposed as for all fabrics and grayish ones, respectively.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.34 no.9
• /
• pp.1567-1580
• /
• 2010

This study investigates the effects of visual texture on color emotion and establishes prediction models for color emotion by both physical color properties and visual texture characteristics. A variety of fabrics including silk, cotton, and flax were colored by digital textile printing according to chromatic hue and tone combinations that are evaluated in terms of color emotion. Subjective visual texture ratings are also obtained for gray-colored same fabrics to those used in color emotion tests. As a result, fabric clusters by visual texture factors showed significant differences in color emotion factors that are primarily affected by physical color properties. Finally prediction models for color emotion factors by both physical color properties and visual texture clusters were established, which has a potential to be used to explain color emotion according to the visual texture characteristics of fabrics.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2011.11a
• /
• pp.56-58
• /
• 2011

• Journal of the Ergonomics Society of Korea
• /
• v.30 no.1
• /
• pp.221-227
• /
• 2011

Objective: The aim of this study is to investigate the quantitative effects of various emotions and retention periods on the color vividness of visual memory. Background: Although numerous studies have focused on the effects of emotions on memory such as visual detail and vividness of emotional events compared to neutral events, the relationship between emotion and visual memory is ambiguous yet. Furthermore, there were few studies on the effect of emotion on vividness of visual memory. Method: A total of 68 subjects were participated in serial experiments proceed on online and the experiments had two phases: recognition phase and reproduction phase. The 15 photographs were used as visual stimuli and all experiments were conducted over the internet(experiment website) and the results were collected on the web database. Results: The retention period, sleep-arousal emotion and subjective saturation of visual stimuli had a significant effect on the color vividness of visual memory. Conclusion: The results suggested that the color of visual stimulus might be more vividly remembered when it is arousing, the subjective saturation is higher and the retention period is longer. Application: The findings of this study may help clarify the relationship between human emotions and visual memory.

• Proceedings of the ESK Conference
• /
• 1997.10a
• /
• pp.473-476
• /
• 1997

Human visual emotion were investigated by analyzing HRV from ECG signals, which were varied by the visual stimuli. In this paper, twelve university students experienced visual emotion by pictures from IAPS. ECG and subjective rating were obtained for human emotion evaluation. For determination of HRV, ECG was extracted into HF and LF via power spectrum analysis. The results showed that HRV is good for discrimination between positive and negative emotions.

• Journal of Korea Multimedia Society
• /
• v.24 no.7
• /
• pp.880-889
• /
• 2021

In everyday life, recognizing people's emotions from their frames is essential and is a popular research domain in the area of computer vision. Visual emotion has a severe class imbalance in which most of the data are distributed in specific categories. The existing methods do not consider class imbalance and used accuracy as the performance metric, which is not suitable for evaluating the performance of the imbalanced dataset. Therefore, we proposed a method for recognizing visual emotion using balanced data augmentation to address the class imbalance. The proposed method generates a balanced dataset by adopting the random over-sampling and image transformation methods. Also, the proposed method uses the Focal loss as a loss function, which can mitigate the class imbalance by down weighting the well-classified samples. EfficientNet, which is the state-of-the-art method for image classification is used to recognize visual emotion. We compare the performance of the proposed method with that of conventional methods by using a public dataset. The experimental results show that the proposed method increases the F1 score by 40% compared with the method without data augmentation, mitigating class imbalance without loss of classification accuracy.

• Journal of the Korean Society for Library and Information Science
• /
• v.48 no.1
• /
• pp.53-73
• /
• 2014

Given that emotion-based computing environment has grown recently, it is necessary to focus on emotional access and use of multimedia resources including images. The purpose of this study aims to identify the visual cues for emotion in images. In order to achieve it, this study selected five basic emotions such as love, happiness, sadness, fear, and anger and interviewed twenty participants to demonstrate the visual cues for emotions. A total of 620 visual cues mentioned by participants were collected from the interview results and coded according to five categories and 18 sub-categories for visual cues. Findings of this study showed that facial expressions, actions / behaviors, and syntactic features were found to be significant in terms of perceiving a specific emotion of the image. An individual emotion from visual cues demonstrated distinctive characteristics. The emotion of love showed a higher relation with visual cues such as actions and behaviors, and the happy emotion is substantially related to facial expressions. In addition, the sad emotion was found to be perceived primarily through actions and behaviors and the fear emotion is perceived considerably through facial expressions. The anger emotion is highly related to syntactic features such as lines, shapes, and sizes. Findings of this study implicated that emotional indexing could be effective when content-based features were considered in combination with concept-based features.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2011.05a
• /
• pp.93-94
• /
• 2011

• Proceedings of the Korea Society of Design Studies Conference
• /
• 2002.11b
• /
• pp.86-87
• /
• 2002

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2012.05a
• /
• pp.132-133
• /
• 2012