• Journal of Korea Multimedia Society
• /
• v.18 no.12
• /
• pp.1453-1461
• /
• 2015

Since digital images and videos are rapidly increasing in the internet with the spread of mobile computers and smartphones, research on image retrieval has gained tremendous momentum. Color, shape, and texture are major features used in image retrieval. Especially, color information has been widely used in image retrieval, because it is robust in translation, rotation, and a small change of camera view. This paper proposes a new method for histogram refinement based on local color difference. Firstly, the proposed method converts a RGB color image into a HSV color image. Secondly, it reduces the size of color space from 256³ to 32. It classifies pixels in the 32-color image into three groups according to the color difference between a central pixel and its neighbors in a 3x3 local region. Finally, it makes a color difference vector(CDV) representing three refined color histograms, then image retrieval is performed by the CDV matching. The experimental results using public image database show that the proposed method has higher retrieval accuracy than other conventional ones. They also show that the proposed method can be effectively applied to search low resolution images such as thumbnail images.

• Journal of Biomedical Engineering Research
• /
• v.30 no.1
• /
• pp.34-40
• /
• 2009

Transforms including translation and rotation are required for registering two or more images. In medical applications, different registration methods have been applied depending on the structures: for rigid bodies such as bone structures, affine transformation was widely used. In most previous research, a single transform was used for registering the whole images, which resulted in low registration accuracy especially when the degree of deformation was high between two images. In this paper, a novel registration method is introduced which is based image sub-division and bilinear interpolation of transformations. The proposed method enhanced the registration accuracy by 40% comparing with Trimmed ICP for registering color and MRI images.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.3
• /
• pp.515-521
• /
• 2020

Deep learning methods have been effectively used to provide great improvement in various research fields such as machine learning, image processing and computer vision. One of the most frequently used deep learning methods in image processing is the convolutional neural networks. Compared to the traditional artificial neural networks, convolutional neural networks do not use the predefined kernels, but instead they learn data specific kernels. This property makes them to be used as feature extractors as well. In this study, we compared the quality of CNN features for traditional texture feature extraction methods. Experimental results demonstrate the superiority of the CNN features. Additionally, the recognition process and result of a pioneering CNN on MNIST database are presented.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.11
• /
• pp.2711-2722
• /
• 1993

Most of the current 2-D object recognition systems are model-based. In such systems, the representation of each of a known set of objects are precompiled and stored in a database of models. Later, they are used to recognize the image of an object in each instance. In this thesis, the approach method for the 2-D object recognition is treating an object boundary as a string of structral units and utilizing string matching to analyze the scenes. To reduce string matching time, models are rebuilt by means of fuzzy c-means clustering algorithm. In this experiments, the image of objects were taken at initial position of a robot from the CCD camera, and the models are consturcted by the proposed algorithm. After that the image of an unknown object is taken by the camera at a random position, and then the unknown object is identified by a comparison between the unknown object and models. Finally, the amount of translation and rotation of object from the initial position is computed.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.418-420
• /
• 1993

In this paper, we proposed a new FMS Landmark recognition algorithm using color images. Firstly, a NTSC image fame is captured, and then it is converted to a field image in order to reduce the image blurring from the AGV motion. Secondly, the landmark is detected via the comparison of the color vectors of image pixels with the landmark color. Finally, the identification of FMS landmark is executed using a newly designed landmark pattern with a set of reference points. The landmark pattern is normalized against its translation, rotation, and scaling. And then, its vertical projection data are fisted for the pattern classification using the standard data set. Experimental results show that our scheme performs well.

• Proceedings of the KIEE Conference
• /
• 1994.11a
• /
• pp.353-355
• /
• 1994

This work describes a hardware implementation of a precision image tracking system which employs a CCD camera mounted on pan/tilt device. Unknown translation between two successive images of a moving object is estimated by using a generalized least-squares method. Estimated position error obtained by the tracking algorithm is used to drive DC motors built in the pan/tilt device for the camera to follow the image. An experimental result shows a sub-resolution tracking error for a image moving with a uniform velocity.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.415-418
• /
• 2019

본 논문에서 grayscale 이미지를 그럴듯한 컬러 이미지로의 전환을 다루고자 한다. 기존의 CNN Network 를 통해 실제 Image 를 만들어내려는 기법들은 모든 Pixel 의 Error 를 Loss 로 사용한다. 각 픽셀별로 가장 완벽한 답을 찾으려고 하기보다는, 전체 픽셀의 관점에서의 Loss 를 줄이려고 하기 때문에, 픽셀 값이 정확한 값대신 안전한 값으로 넘어간다는 단점이 있다. 이 문제를 해결하기 위해 본 논문에서 GAN 기반의 Image-to-Image Translation 기법에 NIN(Network in Network) 적용해 이 문제를 해결할 수 있음을 보인다. 전통 CNN 기법보다 더 Photo-realistic 한 이미지를 생성할 수 있게 된다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.497-500
• /
• 2022

High-quality images and videos are being generated as technologies for deep learning-based image style translation and conversion of static images into dynamic images have developed. However, it takes a lot of time and resources to manually transform images, as well as professional knowledge due to the difficulty of natural image transformation. Therefore, in this paper, we study natural style mixing through a style conversion network using GAN and natural dynamic image generation using the First Order Motion Model network (FOMM).

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.252-253
• /
• 2023

Container terminal automation might offer many potential benefits, such as increased productivity, reduced cost, and improved safety. Autonomous trucks can lead to more efficient container transport. A robust lane detection method is proposed using score-based generative modeling through stochastic differential equations for image-to-image translation. Image processing techniques are combined with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Genetic Algorithm (GA) to ensure lane positioning robustness. The proposed method is validated by a dataset collected from the port terminals under different environmental conditions and tested the robustness of the lane detection method with stochastic noise.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.9-16
• /
• 2020

In the Image processing and computer vision, the problem of reconstructing from one image to another or generating a new image has been steadily drawing attention as hardware advances. However, the problem of computer-generated images also continues to emerge when viewed with human eyes because it is not natural. Due to the recent active research in deep learning, image generating and improvement problem using it are also actively being studied, and among them, the network called Generative Adversarial Network(GAN) is doing well in the image generating. Various models of GAN have been presented since the proposed GAN, allowing for the generation of more natural images compared to the results of research in the image generating. Among them, pix2pix is a conditional GAN model, which is a general-purpose network that shows good performance in various datasets. pix2pix is based on U-Net, but there are many networks that show better performance among U-Net based networks. Therefore, in this study, images are generated by applying various networks to U-Net of pix2pix, and the results are compared and evaluated. The images generated through each network confirm that the pix2pix model with Attention, R2, and Attention-R2 networks shows better performance than the existing pix2pix model using U-Net, and check the limitations of the most powerful network. It is suggested as a future study.