• 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.

• Journal of the Korean Society of Fashion and Beauty
• /
• v.2 no.1 s.1
• /
• pp.21-33
• /
• 2004

The main focus of this study is to provide the interrelation about the defining fashion model image by the fashion trend since 1960. This is expressed as follows, First, in the 60s'; 1) Image of innocent dolly style, Jean Shrimpton 2) Image of sexual style, Celia Hammond 3) Image of art style with charicteristic mask, Peggy Moffitt 4) Image of immature boyish style, Twiggy. Second, in the 70s'; 1) Image of natural and intelligent style, Larun Hutton 2) Image of exotic style with black beauty, Imman 3) Image of graceful and sexal style, Veruschka 4) Image of glamour and sexual style, Jerry Hall. Third, in the 80s'; 1) Image of unisexual style with power, Grace Jones 2) Image of graceful and noble style, In`es de la Fressange 3) Image of healthy and sexy style, Christie Brinkley 4) Image of sexy style with good sense, super model. And fourth, in the 90s' and now; 1) Image of glamour sexual style with self-consciousness, Claudia Shiffer 2) Image of graceful style with dignity, Christy Turlington 3) Image of asexual and androginous style, Stella Tennant), 4)Image of Twiggy style with immature and slender, Kate Moss 5) Image of new glamour style, Giseel Bundchen 6) Image of new style with unique beauty, Amber Vaiietta 7)Image of exotic style, Devon Aoki 8) Extraordinary, image of various style. The result of thir study, fashion models image have played a role in transmitting the style of fashion trend in their relevancy. Anyway it can be said that fashion models imply figurative meanings of the fashion trend.

• International Journal of Advanced Culture Technology
• /
• v.10 no.2
• /
• pp.252-259
• /
• 2022

Artificial intelligence is used in fusion with image processing techniques using cameras. Image processing technology is a technology that processes objects in an image received from a camera in real time, and is used in various fields such as security monitoring and medical image analysis. If such image processing reduces the accuracy of recognition, providing incorrect information to medical image analysis, security monitoring, etc. may cause serious problems. Therefore, this paper uses a mixture of YOLOv4-tiny model and image processing algorithm and uses the COCO dataset for learning. The image processing algorithm performs five image processing methods such as normalization, Gaussian distribution, Otsu algorithm, equalization, and gradient operation. For RGB images, three image processing methods are performed: equalization, Gaussian blur, and gamma correction proceed. Among the nine algorithms applied in this paper, the Equalization and Gaussian Blur model showed the highest object detection accuracy of 96%, and the gamma correction (RGB environment) model showed the highest object detection rate of 89% outdoors (daytime). The image binarization model showed the highest object detection rate at 89% outdoors (night).

• The Journal of Advanced Prosthodontics
• /
• v.9 no.6
• /
• pp.409-415
• /
• 2017

PURPOSE. Accurate information is essential in dentistry. The image information of missing teeth is used in optically based medical equipment in prosthodontic treatment. To evaluate oral scanners, the standardized model was examined from cases of image recognition errors of linear discriminant analysis (LDA), and a model that combines the variables with reference to ISO 12836:2015 was designed. MATERIALS AND METHODS. The basic model was fabricated by applying 4 factors to the tooth profile (chamfer, groove, curve, and square) and the bottom surface. Photo-type and video-type scanners were used to analyze 3D images after image capture. The scans were performed several times according to the prescribed sequence to distinguish the model from the one that did not form, and the results confirmed it to be the best. RESULTS. In the case of the initial basic model, a 3D shape could not be obtained by scanning even if several shots were taken. Subsequently, the recognition rate of the image was improved with every variable factor, and the difference depends on the tooth profile and the pattern of the floor surface. CONCLUSION. Based on the recognition error of the LDA, the recognition rate decreases when the model has a similar pattern. Therefore, to obtain the accurate 3D data, the difference of each class needs to be provided when developing a standardized model.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1315-1318
• /
• 2003

In this paper, a neural network based approach using a self-organizing feature map is proposed for the segmentation of X ray images. A number of algorithms based on such approaches as histogram analysis, region growing, edge detection and pixel classification have been proposed for segmentation of general images. However, few approaches have been applied to X ray image segmentation because of blur of the X ray image and vagueness of its edge, which are inherent properties of X ray images. To this end, we develop a new model based on the neural network to detect objects in a given X ray image. The new model utilizes Mumford-Shah functional incorporating with a modified adaptive SOFM. Although Mumford-Shah model is an active contour model not based on the gradient of the image for finding edges in image, it has some limitation to accurately represent object images. To avoid this criticism, we utilize an adaptive self organizing feature map developed earlier by the authors.[1] It's learning rule is derived from Mumford-Shah energy function and the boundary of blurred and vague X ray image. The evolution of the neural network is shown to well segment and represent. To demonstrate the performance of the proposed method, segmentation of an industrial part is solved and the experimental results are discussed in detail.

• Journal of Korea Trade
• /
• v.25 no.2
• /
• pp.178-195
• /
• 2021

Purpose - This study aims to analyze consumer in the multidimensional aspect of a combination of corporate image and brand personality in order to identify the structural causal relationship between consumer choice and corporate image and brand personality. Design/methodology - This study combined theoretical literature studies with empirical field studies using questionnaire survey methods. To achieve this objective, a hypothetical causal model consisting of three potential variables and nine measurement variables was created based on prior research, and a structural equation model was used to identify the suitability of the model. Findings - The hypothetical model established by this study was judged to be generally appropriate. In particular, corporate image was shown to have significant static direct effects on consumer choice and brand personality. It was also shown that brand personality had a direct static effect on consumer choice, and that corporate image has an indirect significant impact on consumer choice by moderating brand personality. Originality/value - Previous papers have mainly focused on one-dimensional studies of various images, such as companies and brands. However, this paper used a model that analyzed consumer choice through multi-clue information rather than corporate images as the only clue to consumer choice.

• The Journal of the Korean dental association
• /
• v.44 no.2 s.441
• /
• pp.115-122
• /
• 2006

Objective : The purpose of this study was to evaluate the dimensional errors between real tooth, 3D CT image and CARP model. Materials and Methods : Two maxilla and two mandible block bones with intact teeth were taken from two cadavers. Computed tomography was taken either in dry state and in wet state. After then, all teeth were extracted and the dimensions of the real teeth were measured using a digital caliper at mesio-distal and bucco-lingual width both in crown and cervical portion. 3D CT image was generated using the V-works $4.0^{TM}$ (Cybemed Inc., Seoul, Korea) software. Twelve teeth were randomly selected for CARP model fabrication. All the measurements of 3D Ct images and CARP models were made in the same manner of the real tooth group. Dimensional errors between real tooth, 3D CT image model and CARP model was calculated. Results : 1) Average of absolute error was 0.199 mm between real teeth and 3D CT image model, 0.169 mm between 3D CT image model and CARP model and 0.291 mm between real teeth and CARP model, respectively. 2) Average size of 3D CT image was smaller than real teeth by 0.149 mm and that of CARP model was smalier than 3D CT image model by 0.067mm. Conclusion : Within the scope of this study, CARP model with the 0.291 mm average of absolute eror can aid to enhance the success rate cf autogenous tooth transplantation due to the increased accuracy of recipient bone and donor tooth.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.3
• /
• pp.63-73
• /
• 2022

A more accurate understanding of the irrigation water supply is necessary for efficient agricultural water management. Although we measure water levels in an irrigation canal using ultrasonic water level gauges, some errors occur due to malfunctions or the surrounding environment. This study aims to apply CNN (Convolutional Neural Network) Deep-learning-based image classification and segmentation models to the irrigation canal's CCTV (Closed-Circuit Television) images. The CCTV images were acquired from the irrigation canal of the agricultural reservoir in Cheorwon-gun, Gangwon-do. We used the ResNet-50 model for the image classification model and the U-Net model for the image segmentation model. Using the Natural Breaks algorithm, we divided water level data into 2, 4, and 8 groups for image classification models. The classification models of 2, 4, and 8 groups showed the accuracy of 1.000, 0.987, and 0.634, respectively. The image segmentation model showed a Dice score of 0.998 and predicted water levels showed R² of 0.97 and MAE (Mean Absolute Error) of 0.02 m. The image classification models can be applied to the automatic gate-controller at four divisions of water levels. Also, the image segmentation model results can be applied to the alternative measurement for ultrasonic water gauges. We expect that the results of this study can provide a more scientific and efficient approach for agricultural water management.

• Journal of the Korean Society of Costume
• /
• v.66 no.4
• /
• pp.111-127
• /
• 2016

The study aims to examine the forms of 'image expression' and utilization of model poses in fashion photos, and to delve into the characteristics and the intents that make certain model poses effective in expressing an image. The study used the fashion photos in the fashion magazine, Vogue, to analyze the different model poses used to express different images. The results are as follows. First, image expression forms in fashion photos were categorized into 'direct product suggestion expression form', 'sensual image expression form', 'sexual image expression form', 'story telling expression form', 'everyday situation expression form', and 'fantastic image expression form'. The different utilization types of model poses were categorized into 'type utilizing intangible elements', 'type utilizing complicated elements', 'type utilizing living organisms', 'type utilizing props', 'type utilizing clothes', 'type utilizing location', 'type utilizing accessories', and 'type utilizing products'. Second, the most common expression form for fashion photos used in advertisements was the 'direct product suggestion expression form', which was followed by the sensual image expression form. The most popular form used in the editorial fashion photos was the direct suggestion product expression form, which was followed by the story telling expression form. Third, the most common model pose type for direct product suggestion form was the 'type utilizing product'. Fourth, 'direct product suggestion expression form' was mostly used in editorial fashion photos. The most common utilization types of model poses were 'type utilizing clothes', 'type utilizing props', and 'type utilizing place'.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1722-1725
• /
• 1997

This paper presents image analysis method using a Markov random field(MRF) model. Particulary, image esgmentation is to partition the given image into regions. This scheme is first segmented into regions, and the obtained domain knowledge is used to obtain the improved segmented image by a Markov random field model. The method is a maximum a posteriori(MAP) estimation with the MRF model and its associated Gibbs distribution. MAP estimation method is applied to capture the natural image by TMS320C80(MVP) and to realize the segmented image by a MRF model.