• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.3
• /
• pp.166-178
• /
• 2023

This study aims to introduce and assess CNN Deep Learning methods to analyze visual landscape images on social media with embedded user perceptions and experiences. This study analyzed visual landscape images by focusing on a healing place. For the study, seven adjectives related to healing were selected through text mining and consideration of previous studies. Subsequently, 50 evaluators were recruited to build a Deep Learning image. Evaluators were asked to collect three images most suitable for 'healing', 'healing landscape', and 'healing place' on portal sites. The collected images were refined and a data augmentation process was applied to build a CNN model. After that, 15,097 images of 'healing' and 'healing landscape' on portal sites were collected and classified to analyze the visual landscape of a healing place. As a result of the study, 'quiet' was the highest in the category except 'other' and 'indoor' with 2,093 (22%), followed by 'open', 'joyful', 'comfortable', 'clean', 'natural', and 'beautiful'. It was found through research that CNN Deep Learning is an analysis method that can derive results from visual landscape image analysis. It also suggested that it is one way to supplement the existing visual landscape analysis method, and suggests in-depth and diverse visual landscape analysis in the future by establishing a landscape image learning dataset.

• Journal of Fashion Business
• /
• v.15 no.1
• /
• pp.80-91
• /
• 2011

The purpose of this study is to evaluate the differences of visual effects and visual images by variations in shoulder angle and shoulder width of power shoulder jacket. The stimuli are 5 samples: One control group, 2 variations of the angle of shoulder line and 2 variations of the width of shoulder line. The data has been obtained from 87 fashion design majors. The data has been analyzed by Factor Analysis, Anova, Scheffe's Test and the Correlation Analysis. The results of the study are as follows: The visual images by the angle and the width of shoulder line of power shoulder jacket are composed of 4 factors : attention, stiffness and softness, masculinity, and trendiness. Among these factors, attention factor is estimated by the most important factor. The visual effects by the angle and the width of shoulder line of power shoulder jacket are composed of 3 factors : whole silhouette, neck and arm figure, upper body figure. In these factors, the whole silhouette is estimated by the most important factor. The power shoulder jacket with extreme changes in shoulder angle has double images: it looks trendy and classy but also gives an awkward image. In case of changes in shoulder width, the visual evaluation shows big differences with the degree of expansion. The visual evaluation with variation in angle has stronger image and effect than that in width. The power shoulder jacket trend itself is also evaluated that variation in angle reflects the trend better than that in width.

• Journal of the Korean Society of Physical Medicine
• /
• v.10 no.4
• /
• pp.59-68
• /
• 2015

PURPOSE: The purpose of this study was to determine the comparison of visual and auditory biofeedback during sit-to-stand training in patients with stroke. METHODS: Thirty-five subjects with chronic stroke were divided into three groups: a visual feedback group (12 subjects), an auditory feedback group (12 subjects) and a control group (11 subjects). All Groups received neurodevelopmental treatment, and sit-to-stand training for 30minutes three times a week for four weeks. During the sit to stand training, the experimental groups received visual feedback and auditory feedback, whereas the control group performed sit-to-stand training without feedback. Five times sit-to-stand test (FTSST), motion analysis and postural sway during sit-to-stand were used to evaluate sit to stand performance ability. In addition, Berg balance scale (BBS) was performed for evaluation of balance function in participants. RESULTS: All groups showed significant increase on FTSST and BBS between pre- and post-intervention. The BBS scores in visual feedback group was significant increase than control group. The motion analysis and postural sway, more improvement was observed in the visual and auditory feedback groups compared with the control group. The only visual feedback group was a better performance of midline excursion during sit-to-stand than control group. CONCLUSION: These findings suggest that sit-to-stand training using a biofeedback may help to improve sit to stand performance and balance ability of stroke patients.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.25 no.2
• /
• pp.104.1-104.1
• /
• 1997

The purpose of this study is to grasp the characteristics of user''''s response to perceived safety and visual preferences for outdoor green spaces by the types of campus layouts. This research was investigated by color slide ratings and questionnaire survey to the students who are majoring in Landscape architecture in three universities locating at Taegu area. Two research sites have similarities in many ways but have differences in campus land form and design type such as ''''Closed'''' and ''''Open'''' types. Major results were summarised as follows ; 1. As a result of the slide test, the high degree of visual preference was shown in the campus that is ''''Closed'''' type. However the degree of perceived safety was lower than that of in Youngnam Univ. campus. 2. According to the result of the comparative analysis between user''''s perceived safety and visual preferences in each campus, the degree of perceived safety at ''''Closed'''' type was lower than that of ''''Open'''' type, but the degree of visual satisfactioni was higher at ''''Closed'''' type. 3. The factors affecting visual preference in campus were shown as density of wood, land form, and diverse type of the spaces. On the other hand, the factors affecting perceived safety were ''''enclosed space by wood'''' at the day time, and ''''the condition of lighting'''' at night. 4. Regarding gender differences in sensation of each space variables, female users showed higher satisfactio on the scenic beauty. 5. Regression analysis showed that general satisfation was determined by the variables such as ''''arrangement'''', familiarity'''', ''''cleanness'''', and ''''closed feeling'''', in Kyungbook Univ. And in Youngnam Univ. , the variables were ''''texture'''', ''''perceived beauty'''', ''''cleanness'''', and ''''complexity'''' respectively. 6. In conclusion, campus users wanted the outdoor spaces that have various land form and somewhat ''''open-closed'''' mixture type, which has a good ''''Edge Effect'''' to satisfy both aspects in safety and visual preferneces.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.25 no.2
• /
• pp.104-116
• /
• 1997

The purpose of this study is to grasp the characteristics of user's response to perceived safety and visual preferences for outdoor green spaces by the types of campus layouts. This research was investigated by color slide ratings and questionnaire survey to the students who are majoring in Landscape architecture in three universities locating at Taegu area. Two research sites have similarities in many ways but have differences in campus land form and design type such as 'Closed' and 'Open' types. Major results were summarised as follows ; 1. As a result of the slide test, the high degree of visual preference was shown in the campus that is 'Closed' type. However the degree of perceived safety was lower than that of in Youngnam Univ. campus. 2. According to the result of the comparative analysis between user's perceived safety and visual preferences in each campus, the degree of perceived safety at 'Closed' type was lower than that of 'Open' type, but the degree of visual satisfactioni was higher at 'Closed' type. 3. The factors affecting visual preference in campus were shown as density of wood, land form, and diverse type of the spaces. On the other hand, the factors affecting perceived safety were 'enclosed space by wood' at the day time, and 'the condition of lighting' at night. 4. Regarding gender differences in sensation of each space variables, female users showed higher satisfactio on the scenic beauty. 5. Regression analysis showed that general satisfation was determined by the variables such as 'arrangement', familiarity', 'cleanness', and 'closed feeling', in Kyungbook Univ. And in Youngnam Univ. , the variables were 'texture', 'perceived beauty', 'cleanness', and 'complexity' respectively. 6. In conclusion, campus users wanted the outdoor spaces that have various land form and somewhat 'open-closed' mixture type, which has a good 'Edge Effect' to satisfy both aspects in safety and visual preferneces.

• Journal of Animal Science and Technology
• /
• v.63 no.3
• /
• pp.614-625
• /
• 2021

This study investigates how visual appearance of pork cuts affects consumer preference. Images of pork belly, Boston butt, and loin were chosen on the basis of visible fattiness and used to analyze consumers' perception of the appearance of each pork cut. Meat color and visible fat proportion of images of pork cuts were analyzed by the researchers before conducting the survey. A total of 211 pork eaters evaluated the pork cuts based on appearance (lightness of color, redness, visible fat proportion, and fat distribution), preferability, and overall acceptability. Also, muscle pieces from different pork cuts were taken and the relative area composition of muscle fibers was measured. Based on survey results, correlation between visual traits and preferences of each pork cut was analyzed. The survey results showed that preferred pork appearance varied as per each individual's favorite pork cut. Also, the respondents evaluated visual characteristics and preference for each pork cut differently possibly due to the different visual characteristics of each cut. Correlation analysis between visual traits and preference indicated that overall acceptability of pork cuts was mainly influenced by fat preference, followed by color preference. Fat and color preferences for each pork cut were affected by various visual attributes including redness, lightness of color, visible fat proportion, and fat distribution, but their effects were considerably varied among different pork cuts. Thus, Korean consumers perceived and assessed pork appearance using various quality cues but the evaluation depended on which cut was being observed.

• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.374-381
• /
• 2022

This study analyzes the visual perceptual difference of observers in the artworks created by human artists and artificial intelligence(AI) through eye-tracking. More specifically, the study analyzes the degree of visual attention through a fixation experiment on non-linguistic sources such as the formation and expression of artworks. As a result of this study, the subjects had guessed that one out of four artworks were created by AI (in actuality, 61.1% of the artworks were created by The Next Rembrandt). This demonstrates that most of the subjects hardly recognized the difference between the artwork of human artists and AI. From the comparative analysis of visual perceptual differences found through eye-tracking, more visual attention was found to be demanded for catching details of more stimulating visuals compared to less stimulating visuals. In the gender difference analysis, both of the female and male subjects were likely to stare more intently at the flowers of still-life paintings (Deep Dream & Vincent Van Gogh) while the eyes of a portrait painting (Rembrandt & The Next Rembrandt); this demonstrates no significant differences in gender. Various opinions on AI and art creation from different perspectives arose, therefore, this research is meaningful in a way that it suggests an objective examination through experiments with an artistic perspective.

• Journal of Broadcast Engineering
• /
• v.17 no.2
• /
• pp.223-236
• /
• 2012

We develop a video processing method that allows the more advanced human perception oriented video coding. The proposed method necessarily reflects all influences by the rate-distortion based optimization and the human visual perception that is affected by the visual saliency, the limited space-time resolution and the regional moving history. For reflecting the human perceptual effects, we devise an online moving pattern classifier using the Hedge algorithm. Then, we embed the existing visual saliency into the proposed moving patterns so as to establish a human visual perception model. In order to realize the proposed human visual perception model, we extend the conventional foveation filtering method. Compared to the conventional foveation filter only smoothing less stimulus video signals, the developed foveation filter can locally smooth and enhance signals according to the human visual perception without causing any artifacts. Due to signal enhancement, the developed foveation filter more efficiently transfers the bandwidth saved at smoothed signals to the enhanced signals. Performance evaluation verifies that the proposed video processing method satisfies the overall video quality, while improving the perceptual quality by 12%~44%.

• Korean Institute of Interior Design Journal
• /
• v.17 no.6
• /
• pp.71-81
• /
• 2008

The purposes of this research are to correctly understand the relationship between a visual communication structure and a semantic communication structure when integrating and changing various architectural visual information. This study will classify various diagrams, which have been actively applied to the works of Rem Koolhaas and MVRDV when designing architecture, and based on the classification, it will analyze how the expression viewpoints inherent in the diagrams are changed and applied to processing and changing architectural visual information. The transformal usage of the visual information of architectural diagrams is classified into an analysis-centered processing method and a concept-centered processing method, and the characteristics of their usage are analyzed. The former shows an observer-centered expression viewpoint which effectively delivers an architect's analyzed architectural information or intent to a customer or an observer. It also allows an easy perception of the analyzed data, and uses qualitative expression viewpoints. The method combines systematic expression viewpoints, which value a relationship with visual information, and various architectural visual information; uses the combined expression viewpoints as one diagram for delivering various information simultaneously and for changing visual information. The latter shows author-centered subjective expression viewpoints, which are different from reproduction-centered fixed expression viewpoints. This method uses arbitrary expression viewpoints that overly extort, change or manipulate visual information. It shows simultaneous expression viewpoints that integrate various architectural visual information via omniscient expression viewpoints, such as reversing or projecting the points of viewing subjects, which human beings cannot perceive.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.27 no.3
• /
• pp.58-68
• /
• 1999

Purpose of this thesis is to find out the relationship among the amount of change and the visual cognition, and the visual preference which people like and can feel. Through the investigation of relationships between the amount of change, which indicates the degree of visual variation and the visual preference, the amount of change and the visual cognition, and the visual preference and the visual cognition, basic design data will be supplied, which can satisfy users' desire as much as possible in the most economic way. In order to investigate the relationship between the visually produced the amount of change and preferences, graphic simulation, in which variables other than the visual change are controlled, has been proceeded. Graphic factors of the visual change in the cyber exterior space are determined on the point of location (base plane, vertical plane, overhead plane), shape, size and color. As for the relationship between the amount of change and the preference, only the size is effective. since preferences on the location, shape and color are individual preferences, no common trend can be found. Therefore, we cannot say that which shape or color is better, Since the location, shape and color are qualitative change and the size is the quantitative change, the size can be the measurable change quantity. The relationship between the amount of change of size and the degree of preference is found to be inverse U-shape, i.e., as the amount of change of size increases the degree of preference first increases and, after a certain level, decreases. The same result has been obtained in photo simulation.