• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.269-274
• /
• 2021

With the development of artificial intelligence, society is moving to a different world. As a result, amid growing interest in artificial intelligence education, research on how to teach artificial intelligence is also being conducted more actively in Korea. However, a lot of research is being conducted around the upper grades of elementary school, and curriculum and programs for the lower grades are insufficient. Therefore, this study developed an artificial intelligence program for lower grades. Among them, it was developed focusing on artificial intelligence image recognition. It compares image recognition methods of people, animals, and computers, identifies the characteristics of fallen leaves, and helps them understand the image recognition process of artificial intelligence by classifying them according to the characteristics of fallen leaves. I hope this program will help elementary school students understand the image recognition principle of artificial intelligence in the future.

• Journal of Conservation Science
• /
• v.37 no.1
• /
• pp.1-12
• /
• 2021

In the digital era, large archives of information and Internet accessibility make information search, including image search, easier and affordable, even from remote locations. Information transmission and sharing can be performed instantly, at any moment. In the case of images, there are risks of transmitting and recklessly sharing intentionally modified images. Such modified images can also be transmitted and used as an additional source of information by followers. In this study, historical portraits of Yu Kil-Chun are shown, who was the first Korean student to study in both Japan and the United States. He was an intellectual, writer, politician, and independence activist of Korea's late Joseon Dynasty. Using image processing software, the portrait images were compared to investigate aging effects and artificial modifications. Statistics of red (R), green (G), blue (B), and L^*, a^*, and b^* values of every pixel in the selected identical areas of the portraits were compared to identify possible causes of variations, including aging effects and artificial modifications. Sepia toning, used in black and white photographs until the 1930s, and modern digital sepia toning can be very confusing owing to their aging effects. The importance of preservation of physical copies and preservation of context (interconnections between data and between documents) is discussed from archiving and conservation science perspectives.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• Proceedings of the Korean Institute of Interior Design Conference
• /
• 2003.05a
• /
• pp.183-186
• /
• 2003

Light is important as to say that it completes space and form. Space that is made by light is not only functional but it can be seen as a place where space and people communicate to each other. Recently mass media is embossed as communication method. Light is the most instant and affluent factor among what consists of the image of space to express sensitivity. Especially the artificial lighting plays an important role in the presentation of space in the mass media with the progress of technology. Therefore this study's purposes are to search how the artificial light present the image of space in the mass media and to suggest alternative methods to present the image with artificial lighting.

• Journal of Korean Ophthalmic Optics Society
• /
• v.7 no.1
• /
• pp.21-23
• /
• 2002

Compared visual acuity that is measured in a artificial myopia with the numerical calculation. Calculation included image's height as well as blur circle that is formed to retina. The blur circle calculated in geometrical optics model, and height of retinal image calculated by refractive power and visual acuity that is measured in a artificial myopia. Define this result as "blur ratio" about blur circle and height of retinal image, and investigated blur ratio relationship about visual acuity in a artificial myopia.

• Journal of KIBIM
• /
• v.12 no.1
• /
• pp.1-9
• /
• 2022

Concrete formwork is a crucial component for any construction project. Artificial intelligence offers great potential to automate formwork design by offering various design options and under different criteria depending on the requirements. This study applied image segmentation in 2D formwork drawings to extract sheathing, strut and pipe support formwork elements. The proposed artificial intelligence model can recognize, classify, and extract formwork elements from 2D CAD drawing image and training and test results confirmed the model performed very well at formwork element recognition with average precision and recall better than 80%. Recognition systems for each formwork element can be implemented later to generate 3D BIM models.

• 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).

• Design & Manufacturing
• /
• v.15 no.3
• /
• pp.1-6
• /
• 2021

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.

• ETRI Journal
• /
• v.39 no.2
• /
• pp.163-172
• /
• 2017

A high performance license plate recognition system (LPRS) is proposed in this work. The proposed LPRS is composed of the following three main stages: (i) plate region determination, (ii) character segmentation, and (iii) character recognition. During the plate region determination stage, the image is enhanced by image processing algorithms to increase system performance. The rectangular license plate region is obtained using edge-based image processing methods on the binarized image. With the help of skew correction, the plate region is prepared for the character segmentation stage. Characters are separated from each other using vertical projections on the plate region. Segmented characters are prepared for the character recognition stage by a thinning process. At the character recognition stage, a three-layer feedforward artificial neural network using a backpropagation learning algorithm is constructed and the characters are determined.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.2
• /
• pp.76-82
• /
• 2017

Malware, including ransomware to quickly detect, in this study, to provide an analysis method of malicious code through the image analysis that has been learned in the deep learning of artificial intelligence. First, to analyze the 2,400 malware data, and learning in artificial neural network Convolutional neural network and to image data. Extracts subgraphs to convert the graph of abstracted image, summarizes the set represent malware. The experimentally analyzed the malware is not how similar. Using deep learning of artificial intelligence by classifying malware and It shows the possibility of accurate malware detection.