• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.212-220
• /
• 2024

When a typhoon or natural disaster occurs, a significant number of orchard fruits fall. This has a great impact on the income of farmers. In this paper, we introduce an AI-based method to enhance low-quality raw images. Specifically, we focus on apple images, which are being used as AI training data. In this paper, we utilize both a basic program and an artificial intelligence model to conduct a general image process that determines the number of apples in an apple tree image. Our objective is to evaluate high and low performance based on the close proximity of the result to the actual number. The artificial intelligence models utilized in this study include the Convolutional Neural Network (CNN), VGG16, and RandomForest models, as well as a model utilizing traditional image processing techniques. The study found that 49 red apple fruits out of a total of 87 were identified in the apple tree image, resulting in a 62% hit rate after the general image process. The VGG16 model identified 61, corresponding to 88%, while the RandomForest model identified 32, corresponding to 83%. The CNN model identified 54, resulting in a 95% confirmation rate. Therefore, we aim to select an artificial intelligence model with outstanding performance and use a real-time object separation method employing artificial function and image processing techniques to identify orchard fruits. This application can notably enhance the income and convenience of orchard farmers.

• The Journal of the Korea Contents Association
• /
• v.17 no.9
• /
• pp.159-172
• /
• 2017

This study examined the predisposing, enabling and need factors, based on Andersen's behavioral model, affecting intention to use community organizing services at a community welfare center. 725 people aged 20 and older who lived in Gwang-jin-gu participated in this study and multiple linear regression analyses were utilized to analyze the deputation. The results demonstrate that intention to use is primarily affected by predisposing factors, age and duration of education. Female and more educated people were significantly associated with the intention to use community organizing services. Enabling factors, reputation and image of the community welfare center significantly affect intention to use community organizing services. People are more likely to use community organizing services when there is higher reputation of the community welfare center and better image of the community welfare center. Finally, intention to use is primarily affected by welfare consciousness, a need factor. People who have liberal welfare consciousness are more likely to use community organizing services. These findings provide implications and suggestions for increasing intention to use community organizing services at a community welfare center.

• Journal of Korea Multimedia Society
• /
• v.8 no.3
• /
• pp.379-388
• /
• 2005

Image steganography Is a secret communication scheme to transmit a secret message, which is embedded into an image. The original image and the embedded image are called the cover image and the stego image, respectively. In other words, a sender embeds a secret message into a cover image and transmits a stego image to a receiver, while the receiver takes the stego image, extracts the message from it, and reads the message. General requirements for steganography are great capacity of secret messages, imperceptibility of stego images, and confidentiality between a sender and a receiver. In this paper, we propose a method for being satisfied with three requirements. In order to hide a secret message into a cover image safely, we use a difference value of two consecutive pixels and a secret quantization range. The former is used for the imperceptibility and the latter for the confidentiality. Furthermore, the number of insertion bits is changed according to the difference value for the imperceptibility. Through experiments, we have shown that our method is more good quality of stego images than many other related methods and increases the amount o( message insertion by performing dual insertion processing for some pixels.

• Journal of Fashion Business
• /
• v.20 no.2
• /
• pp.97-106
• /
• 2016

This study aims examine specific image preferences through selected fashion style and evaluation terms. Therefore, this study provided basic information in order to help select a suitable fashion style within a desired image. As times are changing, most people obtain information about fashion through the use of the Internet by utilizing mobile phones and personal computers and less through magazines, newspapers and so on. When people buy clothes, they seem to be more influenced by the design and color than by price and quality. It is not perceived important for buying like company, advertising, the place of purchase etc. The results of the analysis reveal the structural elements of an image having a sense of fashion style and can be categorized as a natural image, romantic image, elegance image, casual image and avant-garde image. Among the six fashion styles, the natural image is regarded the highest A style. The romantic image is the highest B style and elegance image is the C, D, E style. The casual image is the highest F style and avant-garde image is a D style. In regards to appropriate fashion style by ages, the twenty-something population is investigated in finding a fit that is lively and vibrant in style while the thirty-something population is perceived to identify with a more feminine style. The forty-something population has shown to prefer a more luxurious style. Through this observation one can see that there is a distinction is fashion style between ages.

• Journal of Internet of Things and Convergence
• /
• v.9 no.1
• /
• pp.131-138
• /
• 2023

This paper is related to performance improvement of Image-to-Image translation using Relativistic Average Patch GAN and Residual in Residual Dense Block. The purpose of this paper is to improve performance through technical improvements in three aspects to compensate for the shortcomings of the previous pix2pix, a type of Image-to-Image translation. First, unlike the previous pix2pix constructor, it enables deeper learning by using Residual in Residual Block in the part of encoding the input image. Second, since we use a loss function based on Relativistic Average Patch GAN to predict how real the original image is compared to the generated image, both of these images affect adversarial generative learning. Finally, the generator is pre-trained to prevent the discriminator from being learned prematurely. According to the proposed method, it was possible to generate images superior to the previous pix2pix by more than 13% on average at the aspect of FID.

• Journal of the Korean Applied Science and Technology
• /
• v.35 no.3
• /
• pp.886-904
• /
• 2018

The 3D(dimension) vritual reality(VR) has already been used in various sports fields, especially in the training of elite athletes. It is mainly used to maximize the effectiveness of image training, and the use of VR-based image training has received special attention as evidence-based pratices for its feasibility, practicality, and appropriateness. However, in recent years, the use of VR is no longer used only for the training of elite athletes, but is widely used in social sports. This is because, the advantage of exercise in VR is that it is highly stable and has fewer restrictions from the external environment. Considering these advantages, it can be used for the elderly physical activity. This study identifies and reviews studies applying VR-based image training. Several recommendations for the future study on VR-based image training for the older such as interdisciplinary approach to VR-based image training, support needs regarding characteristics of the older, and generalization and maintenance of acquired technology were discussed.

• Proceedings of the Optical Society of Korea Conference
• /
• 1999.08a
• /
• pp.34-35
• /
• 1999

• The Research Journal of the Costume Culture
• /
• v.24 no.5
• /
• pp.642-652
• /
• 2016

The purpose of this study is to understand the concept of a sexual image and verify the method of its design expression through case studies of the sexual image evening dress shown in an Haute Couture Collection over the last 10 years (2005~2014). The results of analysis are as follows: First, "expression by the seeing through of the natural body" expressed a natural sexual image that combined fashion of the previous times with the beauty of the natural body by using a see-through material and classic or ethnic image. Second, "expression of a sexual-image look that emphasizes romantic detail" illustrated a romantic sexual image that emphasizes feminine sensitivity by mixing various ornamental elements such as see-through material and symbolism of underwear image. Third, "creation of a nude look using skin color" expressed sexual image of an evening dress by inducing erotic sexual association through a combination of opaque material of skin color and design shape that is intended for body exposure. Fourth, "combination of sexual symbol and heterogeneous elements" expressed a decadent, avant-garde and futuristic sexual images by using women's underwear and a sexual symbol as design motif and mixed with mismatching elements. Fifth, "use of a fantastic black image" expressed an exclusive and refined sexual image and a decadent and primitive sexual image by using a fantastic image of black color. The results of this study are expected to be used for the design process of the evening-dress industry that aims for quality improvement.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.5
• /
• pp.471-478
• /
• 2011

High resolution Pan-sharpening technique is becoming increasingly important in the field of remote sensing image analysis as an essential image processing to improve the spatial resolution of original multispectral image. The general scheme of pan-sharpening technique consists of upsampling process of multispectral image and high-pass detail injection process using the panchromatic image. The upsampling process, however, brings about image blurring, and this lead to spectral distortion in the pan-sharpening process. In order to solve this problem, this paper presents a new method that adopts image restoration techniques based on optimization theory in the pan-sharpening process, and evaluates its efficiency and application possibility. In order to evaluate the effect of image restoration techniques on the pansharpening process, the result obtained using the existing method that used bicubic interpolation were compared visually and quantitatively with the results obtained using image restoration techniques. The quantitative comparison was done using some spectral distortion measures for use to evaluate the quality of pan-sharpened image.

• The Journal of the Korea Contents Association
• /
• v.7 no.8
• /
• pp.134-141
• /
• 2007

In 3D animation rendering process, Although we can render the output as a movie file format, most productions use image sequences in their rendering pipelines. This Image Sequence rendering process is extremely important step in final compositing in movie industries. Although there are various type of making image rendering processes, TGA format Is one of most widely used bitmap file formats using in industries. People may ask TGA format is most suitable for in any case. As we know 3D softwares have their own image formats. so we need to testify on this. In this paper, we are going to focus on Alias' 3D package software called MAYA which we will analyze of compressing image sequence, Image quality, supporting Alpha channels in compositing, and Z-depth information. The purpose of this paper is providing to 3D Pipeline as a guideline about effective image sequence format.