• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.10
• /
• pp.1860-1866
• /
• 2016

Helicopter-related collision accidents with structures mostly occur at landing, especially in a limited visibility environment, which necessitates some secondary equipment like a radar that can generate stationary clutter image. In this paper, we propose an algorithm that makes an image of stationary ground clutter in two dimensional range and azimuth angle domain. We present a mathematical model for the received signals from each clutter patch in the iso range ring and analyze their clutter and Doppler characteristics, assuming that a helicopter-borne radar has a rotational antenna. We propose a filter structure, which suppresses side lobe signal components while extracting a main lobe signal component, and suggest a solution for a problem stemmed from the filtering process. Finally, by conducting a simulation we show the performance of the suggested imaging algorithm on a two dimensional virtual scenario of the topographic clutter.

• Journal of Korea Game Society
• /
• v.21 no.3
• /
• pp.13-24
• /
• 2021

This paper shows the face rotation applicable to game character facial illustration. Existing studies limited data to human face data, required a large amount of data, and the synthesized results were not good. In this paper, the following method was introduced to solve the existing problems of existing studies. First, a 3D model with features of the input image was rotated and then rendered as a 2D image to construct a data set. Second, by designing GAN that can learn features of various poses from the data built through the 3D model, the input image can be synthesized at a desired pose. This paper presents the results of synthesizing the game character face illustration. From the synthesized result, it can be confirmed that the proposed method works well.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10a
• /
• pp.366-371
• /
• 2006

퓨리에 시리즈를 사용하면 이미지의 외곽선 특성을 표현할 수 있다. 이미지의 퓨리에 계수를 추출하기 위해서는 우선 이미지를 구성하는 주요 오브젝트를 표현하는 곡선을 추출한다. 이러한 곡선은 오브젝트의 특정 중심점에서 외곽선을 따라 일회전하면서 그 거리를 좌표상에 표시함으로써 얻을 수 있다. 기존의 퓨리에 계수를 추출하는 방법들은 추출된 계수를 이용하여 해당 곡선을 복원했을 때 원래의 곡선에 존재하던 상세한 특성을 표현하지 못한다는 단점이 있으며 이는 결국 이미지로부터 추출한 곡선을 사용하여 이미지를 검색할 때 정확도를 상당히 떨어뜨리게 한다. 이러한 문제점을 해결하기 위해서 본 논문에서는 Binary Range Reduction (BRR) 알고리즘을 제안한다. BRR 알고리즘은 원래의 곡선과 퓨리에 계수를 통해서 복원된 곡선간의 차이를 줄이기 위해서 전체의 곡선을 통해서 하나의 퓨리에 계수 세트를 추출하지 않고, 복원된 곡선이 원래의 곡선과 차이가 일정 크기 이상 나지 않도록 퓨리에 계수를 추출하는 구간을 나누어가며 퓨리에 계수를 추출한다. 이렇게 추출된 다수의 퓨리에 계수 세트를 통해서 복원된 곡선을 사용하여 이미지들 간의 유사도를 비교한다. 실험을 통하여 BRR 알고리즘을 사용하여 곡선에서 추출한 퓨리에 계수로 복원한 곡선이 원래 곡선의 특성을 정확하게 표현하고 있음을 보였고, 퓨리에 계수와 BRR알고리즘을 이미지 검색에 적용하였을 때, 높은 검색 결과를 얻을 수 있음을 보였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.171-176
• /
• 2022

CNN is a type of deep learning and is a neural network used to process images or image data. The filter traverses the image and extracts features of the image to distinguish the image. Deep learning has the characteristic that the more data, the better models can be made, and CNN uses a method of artificially increasing the amount of data by means of data augmentation such as rotation, zoom, shift, and flip to compensate for the weakness of less data. When learning CNN, we would like to check whether outline image learning is helpful in improving performance compared to conventional data augmentation techniques.

• Journal of IKEEE
• /
• v.18 no.4
• /
• pp.603-611
• /
• 2014

When image sensor and lens are fixed on the module, mechanical errors often induce tilt, rotation, or narrow field-of-view of the acquired image. Therefore, the optical characteristics of image sensor modules should be tested by test equipments. This paper explains how to test the optical characteristics of images sensors. It also proposes the standardized description methods of optical characteristics tests which are similar with those of image acquisition characteristics tests. The proposed method helps the test equipments to perform image acquisition characteristics tests and optical characteristics tests together.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.1-2
• /
• 2023

본 연구는 환경 요인이 통제되어 있는 실험실 데이터에 산업 현장에서 발생하는 유사 잡음을 노이즈로 추가하였을 때, SNR비에 따른 노이즈별 STFT Log Spectrogram, Mel-Spectrogram, CWT Spectrogram 총 3가지의 이미지를 생성하고, 각 이미지를 입력으로 한 CNN 결함 분류 모델의 성능 결과를 확인하였다. 원본 데이터의 영향력이 큰 0db 이상의 SNR비로 합성할 경우 원본 데이터와 분류 결과상 큰 차이가 존재하지 않았으며, 노이즈 데이터의 영향이 큰 0db 이하의 SNR비로 합성할 경우, -20db의 STFT 이미지 기준 약 26%의 성능 저하가 발생하였다. 또한, Wiener Filtering을 통한 디노이징 처리 이후, 노이즈를 효과적으로 제거하여 분류 성능의 결과가 높아지는 점을 확인하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.1
• /
• pp.201-207
• /
• 2015

The smartphone with camera can easily generate an image instead of a scanner. However the document image through a smartphone can have distortions related rotation or perspective. In this paper, we proposed a method to generate the document image in that distortions are reduced from the captured document image through a smartphone. For this, the original document image through a smartphone is preprocessed using the MSER-b technique to reduce the light effect. Then, the text area contour is extracted using the characteristics of the document image. Lastly, rotation or perspective distortions are reduced using the extracted text area contour. For experiments, the proposed method is compared two other products. Through experiments, we show that the distortions within the captured document image through smartphone can be effectively reduced.

• Journal of Korea Multimedia Society
• /
• v.15 no.2
• /
• pp.179-194
• /
• 2012

Digital image forgery is becoming a topic of great interest with regard to honesty in imaging. We can often see forged digital images in a variety of places, such as the internet, and magazines, and in images used in political ads, etc. These can reduce the reliability and factual basis of the information contained in image. Therefore, objectivity is needed to determine if the image is forged so as to prevent confusion in the viewing public. Most digital forgeries consist of image resizing, rotating including the following interpolations. To find evidence of interpolation in forged images, this paper proposes a new method for detecting digital image forgery using general interpolation factors analyzed through re-interpolation algorithm of the forged images in order to determine the differences in the patterns. Through the re-interpolation algorithm we could detect the forged region and filtering region used image retouching included to interpolation.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.415-418
• /
• 2024

본 논문에서는 텍스처 합성을 할 때 CNN을 사용하여 효율성을 높이고 방향을 고려하여 동적인 결과로 품질을 개선시킬 수 있는 방법을 제안한다. 자유로운 회전 각도로 방향성을 고려하여 동적인 결과물을 생성할 수 있도록 하였으며, 기존 접근법인 사각형 형태의 마스크 블록이 아닌 다양한 회전 각도를 고려하여 학습을 했기 때문에 텍스처 합성 과정에서 방향성 특징을 좀 더 잘 표현할 수 있다.

• Journal of KIISE:Databases
• /
• v.35 no.4
• /
• pp.345-355
• /
• 2008

SIFT is popularly used in computer vision application such as object recognition, motion tracking, and 3D reconstruction among various shape descriptors. However, it is not easy to apply SIFT into the image similarity search as it is since it uses many high dimensional keypoint vectors. In this paper, we present a SIFT based image similarity search method using an edge image pyramid and an interesting region detection. The proposed method extracts keypoints, which is invariant to contrast, scale, and rotation of image, by using the edge image pyramid and removes many unnecessary keypoints from the image by using the hough transform. The proposed hough transform can detect objects of ellipse type so that it can be used to find interesting regions. Experimental results demonstrate that the retrieval performance of the proposed method is about 20% better than that of traditional SIFT in average recall.