• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.149-158
• /
• 2024

Photo booths have traditionally provided a fun and easy way to capture and print photos to cherish memories. These booths allow individuals to capture their desired poses and props, sharing memories with friends and family. To enable diverse expressions, generative AI-powered photo booths have emerged. However, existing AI photo booths face challenges such as difficulty in taking group photos, inability to accurately reflect user's poses, and the challenge of applying different concepts to individual subjects. To tackle these issues, we present CINEMAPIC, a photo booth system that allows users to freely choose poses, positions, and concepts for their photos. The system workflow includes three main steps: pre-processing, generation, and post-processing to apply individualized concepts. To produce high-quality group photos, the system generates a transparent image for each character and enhances the backdrop-composited image through a small number of denoising steps. The workflow is accelerated by applying an optimized diffusion model and GPU parallelization. The system was implemented as a prototype, and its effectiveness was validated through a user study and a large-scale pilot operation involving approximately 400 users. The results showed a significant preference for the proposed system over existing methods, confirming its potential for real-world photo booth applications. The proposed CINEMAPIC photo booth is expected to lead the way in a more creative and differentiated market, with potential for widespread application in various fields.

• Journal of Advanced Navigation Technology
• /
• v.28 no.5
• /
• pp.745-753
• /
• 2024

In this paper, we propose a system that extracts customer data from self-photos taken through a photo booth and automatically generates an operation report consisting of analysis results for each data and marketing strategy suggestions. The customer data to be extracted was selected based on attributes that could be used to analyze event operation results or to plan next year's event and establish promotional strategies. We utilize ChatGPT4o in image analysis, customer data analysis, and next marketing strategy proposal. As a result of analyzing self-photos taken at a local festival through the proposed system, customer data such as the number of people photographed, gender, age, relationship, and hairstyle were analyzed with high accuracy. In addition, the proposed system was shown to automatically generate operational reports based on customer data and marketing strategies extracted and analyzed by ChatGPT4o.

• Applied Chemistry for Engineering
• /
• v.27 no.4
• /
• pp.433-438
• /
• 2016

The current study evaluated the air quality of the smoking booth equipped with the air purification system consisting of photocatalysts and air filters by measuring the concentrations of hazardous substances of tobacco smoke such as CO, HCHO, $CH_3CHO$, PM10 and PM2.5. To enhance the removal efficiency of hazardous substances, an infrared ray was exposed to improve the reactivity of OH radical generated from the photocatalyst toward environmental tobacco smoke (ETS) gas phase hazardous materials. It was found that the smoking booth with the air purification system improved the removal efficiency of hazardous substances containing formaldehyde by 85.2% compared to that of the smoking booth without any purification systems. In addition, the removal efficiency of the fine dust after treatment was enhanced up to 89.4%.

• Journal of Energy Engineering
• /
• v.14 no.2 s.42
• /
• pp.133-139
• /
• 2005

An activated carbon-photo catalysis hybrid system is proposed for the treatment of VOC produced from paint booth. and its VOC removal performance is experimentally evaluated. Activated carbon tower is designed on the basis of the adsorption characteristics of toluene. Photocatalytic system is designed as the series of $TiO_2/SiO\_2$ fluidized bed reactor and $TiO_2$-coated filters. The present activated carbon-photo catalysis hybrid system shows the VOC removal efficiency within $75\~100\%$ under different VOC species and concentrations.

• Journal of Environmental Science International
• /
• v.25 no.8
• /
• pp.1177-1189
• /
• 2016

In order to prepare the information needed to construct a reduction system for volatile organic compounds (VOCs) exhausted from ship-block paint-booths in a giant shipyard, VOCs in paint-shop airs were analyzed and compared to the components in paint thinners. Aromatic hydrocarbons containing eight and nine carbon atoms are known to be major VOC compounds found in shipyard paint-shops. The total hydrocarbon (THC(C7)) concentrations calibrated using toluene gas, were measured in block paint-shops with two photo-ionization detector (PID) meters, and the resulting THC(C7) data were converted to THC(C1) concentrations according to the Standard Methods for the Measurements of Air Pollution in South Korea. THC(C1) concentrations near the spray site ranged from 10 to 2,000 ppm, but they were less than 400 ppm near the walls of the paint-booth. The measurements of THC concentrations, based on the height of the monitoring sites, were related to the height of the target to which the spray paints were applied. The maximum concentrations occurred at almost the same height as the spray targets. When painted blocks had been dried-by warming with no spraying, the THC concentrations were 80~100 ppm.