• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.167-174
• /
• 2023

This paper attempted to improve the accuracy of the colorectal cancer diagnosis model using image data augmentation in convolutional neural network. Image data augmentation was performed by flipping, rotation, translation, shearing and zooming with basic image manipulation method. This study split 4000 training data and 1000 test data for 5000 image data held, the model is learned by adding 4000 and 8000 images by image data augmentation technique to 4000 training data. The evaluation results showed that the clasification accuracy for 4000, 8000, and 12,000 training data were 85.1%, 87.0%, and 90.2%, respectively, and the improvement effect depending on the increase of image data was confirmed.

• The Research Journal of the Costume Culture
• /
• v.15 no.4
• /
• pp.604-619
• /
• 2007

Aesthetic consciousness of the body determines the form of clothing, reflecting the time and culture as well as the individual and society. Using 'body' to analyze the clothing form, my study develops a framework by which to classify the representation and non-representation of the body in fashion. Theoretically, this study draws from Jean Baudrillard's Simulation theory which maintains that simulation develops the whole edifice of representation. My study substitutes the successive phases of the image to that of (non) representing body in fashion. The correspondences between them are; first, 'image is the reflection of a basic reality' for the representation of physicality, second, 'image masks and perverts a basic reality' for the manipulation of physicality, third, 'image masks the absence of a basic reality' for the absence of physicality, and fourth, 'image bears no relation to any reality whatever' for the absence of body in fashion. Aesthetic ideal of the body is visualized in the form of a dress. Fashion continues to explore forms and images that transcend the traditional representations of the clothed body. My study suggests a framework to analyze bodily representation in fashion, focusing on the relationship between the clothes and body.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.885-889
• /
• 2003

The e-catalog system consists of e-catalog database. e-catalog manager. and a web server, and provides e-catalog web service by displaying e-catalog documents that contain web 3D images. product specifications and manuals. Various web contents such as the 3D images of products, which offer basic viewpoints/movement handles and function simulations, product specifications, product manuals and product features, can be integrated into e-catalog documents in XML format through image manipulation and database connection by using the e-catalog manager tool. By reducing time and cost for publication and management of an e-catalog web service, the competitiveness of companies is expected to be intensified in the perspective of e-business activities.

• Imaging Science in Dentistry
• /
• v.39 no.4
• /
• pp.185-189
• /
• 2009

Purpose : The purpose of this study was to investigate how to detect proximal caries using line profile and validate linear measurements of proximal caries lesions by basic digital manipulation of radiographic images. Materials and Methods : The X-ray images of control group (15) and caries teeth (15) from patients were used. For each image, the line profile at the proximal caries-susceptible zone was calculated. To evaluate the contrast as a function of line profile to detect proximal caries, a difference coefficient (D) that indicates the relative difference between caries and sound dentin or intact enamel was measured. Results : Mean values of D were $0.0354{\pm}0.0155$ in non-caries and $0.2632{\pm}0.0982$ in caries (p<0.001). Conclusion : The mean values of caries group were higher than non-caries group and there was correlation between proximal dental caries and D. It is demonstrated that the mean value of D from caries group was higher than that of control group. From the result, values of D possess great potentiality as a new detection parameter for proximal dental caries.