• Journal of Internet Computing and Services
• /
• v.19 no.4
• /
• pp.7-13
• /
• 2018

The methods for detecting copy move frogery (CMF) are divided into two categories, block-based methods and keypoint-based methods. Block-based methods have a high computational cost because a large number of blocks should be examined for CMF detection. In addition, the forgery detection may fail if a tampered region undergoes geometric transformation. On the contrary, keypoint-based methods can overcome the disadvantages of the block-based approach, but it can not detect a tampered region if the CMF forgery occurs in the low entropy region of the image. Therefore, in this paper, we propose a method to detect CMF forgery in all areas of image by combining keypoint-based and block-based methods. The proposed method first performs keypoint-based CMF detection on the entire image. Then, the areas for which the forgery check is not performed are selected and the block-based CMF detection is performed for them. Therefore, the proposed CMF detection method makes it possible to detect CMF forgery occurring in all areas of the image. Experimental results show that the proposed method achieves better forgery detection performance than conventional methods.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.177-179
• /
• 2022

딥러닝의 발전과 함께 합성곱 신경망 기반의 이미지 내 글자 영역 검출(Scene Text Detection) 방법들이 제안됐다. 그러나 이러한 방법들은 대부분 데이터셋이 제공하는 단어의 위치 정보만을 이용할 뿐 글자 영역이 갖는 고유한 정보인 글자 수는 활용하지 않는다. 따라서 본 논문에서는 글자 수 정보를 학습하여 효과적으로 이미지 내의 글자 영역을 검출하는 모듈을 제안한다. 제안하는 방법은 간단한 합성곱 신경망으로 구성된 이미지 내 글자 영역 검출 모델에 글자 수를 예측하는 모듈을 추가하여 학습을 진행하였다. 글자 영역 검출 성능 평가에 널리 사용되는 ICDAR 2015 데이터셋을 통해 기존 방법 대비 성능이 향상됨을 보였고, 글자 수 정보가 글자 영역을 감지하는 데 유효한 정보임을 확인했다.

• Journal of the Korea Convergence Society
• /
• v.10 no.5
• /
• pp.27-34
• /
• 2019

In this paper, we propose a method to remove the background area by analyzing the pattern of the character area. In the character detection result of the MSER(Maximally Stable External Regions) method which distinguishes a region having a constant contrast background regions were detected. To solve this problem, we use the MSER method in natural images, the background is removed by calculating the change rate by searching the character area and the background area which are not different from the areas where the contrast values are different from each other. However, in the background removed image, using the LBP(Local Binary Patterns) method, the area with uniform values in the image was determined to be a character area and character detection was performed. Experiments were carried out with simple images with backgrounds, images with frontal characters, and images with slanted images. The proposed method has a high detection rate of 1.73% compared with the conventional MSER and MSER + LBP method.

• Bulletin of the Korean Space Science Society
• /
• 2010.04a
• /
• pp.25.2-25.2
• /
• 2010

MIRIS는 과학기술위성 3호의 주 탑제체로 우주 및 지구의 적외선 관측을 위한 두 개의 카메라 시스템을 가지고 있으며 이를 위한 적외선 검출용 이미지 센서가 각각 장착되어 있다. 이미지 센서를 통해 검출된 이미지 데이터를 읽기 위해 고속의 데이터 처리가 요구되어 FPGA 구성방식으로 전용 제어기를 구성하였다. 우주 및 지구의 적외선 관측용 이미지 센서는 구성 및 동작방법이 달라 요구기능을 만족하는 각각의 전용 이미지 센서 제어기를 개발했다. FPGA를 이용한 이미지 센서 제어기에는 검출된 이미지를 읽기위한 센서 제어 신호발생기, 아날로그 이미지 신호를 디지털 정보로 변환하는 ADC 제어용 신호 발생기, ADC의 출력 신호를 고속의 직렬 통신선로로 출력 하는 기능 외에 동작 모드 및 동작 상태 입력용 DSP 인터페이스, 고속의 직렬 통신 선로에 MIRIS 상태정보 삽입 기능, 제어기의 기능을 원격지에서 확인 할 수 있는 이미지 패턴 생성기능 등을 가지고 있다. 특히, 이미지를 읽기 위한 동작 시에만 클록 주파수를 인가하는 방법으로 FPGA 내부 회로를 구성하여 전류의 소모량을 최소화 하였다.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.79-84
• /
• 2023

Image generation models have been applied in various fields to overcome data sparsity, time and cost issues. However, it has limitations in generating images from regular pattern images and detecting defects in such data. In this paper, we verified the feasibility of the image generation model to generate pattern images and applied it to data augmentation for defect detection of OLED panels. The data required to train an OLED defect detection model is difficult to obtain due to the high cost of OLED panels. Therefore, even if the data set is obtained, it is necessary to define and classify various defect types. This paper introduces an OLED panel defect data acquisition system that acquires a hypothetical data set and augments the data with an image generation model. In addition, the difficulty of generating pattern images in the diffusion model is identified and a possibility is proposed, and the limitations of data augmentation and defect detection data augmentation using the image generation model are improved.

• Smart Media Journal
• /
• v.9 no.2
• /
• pp.9-15
• /
• 2020

In this paper, we propose a network model composed of Multi path Encoder-Decoder branches that can recognize each instance from the image. The network has two branches, Dot branch and Segmentation branch for finding the center point of each instance and for recognizing area of the instance, respectively. In the experiment, the CVPPP dataset was studied to distinguish leaves from each other, and the center point detection branch(Dot branch) found the center points of each leaf, and the object segmentation branch(Segmentation branch) finally predicted the pixel area of each leaf corresponding to each center point. In the existing segmentation methods, there were problems of finding various sizes and positions of anchor boxes (N > 1k) for checking objects. Also, there were difficulties of estimating the number of undefined instances per image. In the proposed network, an effective method finding instances based on their center points is proposed.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.988-992
• /
• 2006

본 논문은 PC카메라 환경에서 명암왜곡에 강인한 얼굴검출을 위한 컴포넌트 기반 얼굴검출 기법을 제시한다. 영상 내의 얼굴검출을 위해 에지(edge) 분석, 색상 분석, 형판정합(template matching), 신경망(Neural Network), PCA(Principal Component Analysis), LDA(Linear Discriminant Analysis) 등의 기법들이 사용되고 있고, 영상의 왜곡을 보정하기 위해 히스토그램 분석(평활화, 명세화), gamma correction, log transform 등의 영상 보정 방법이 사용되고 있다. 그러나 기존의 얼굴검출 방법과 영상보정 방법은 검출대상 객체의 부분적인 잡음 및 조명의 왜곡에 대처하기가 어려운 단점이 있다. 특히 PC카메라 환경에서 획득된 이미지와 같이 전면과 후면, 상하좌우에서 비추어지는 조명에 의해 검출 대상 객체의 일부분이 왜곡되는 상황이 발생될 경우 기존의 방법으로는 높은 얼굴 검출 성능을 기대할 수 없는 상황이 발생된다. 본 논문에서는 기울어진 얼굴 및 부분적으로 명암 왜곡된 얼굴을 효율적으로 검출할 수 있도록 얼굴의 좌우 대칭성을 고려한 가로방향의 대칭평균화로 얼굴검출을 위한 모델을 생성하여 얼굴검출에 사용한다. 이 방법은 부분적으로 명암왜곡된 얼굴이미지를 기존의 영상 보정기법을 적용한 것 보다 잘 표현하며, 얼굴이 아닌 후보는 비얼굴 이미지의 형상을 가지게 하는 특성이 있다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1171-1179
• /
• 2021

Image forensic is performed to check image limpidness. In this paper, a robust scheme is discussed to detect median filtering in low quality images. Detection of median filtering assists in overall image forensic. Improved spatial statistical features are extracted from the image to classify pristine and median filtered images. Image array data is rescaled to enhance the spatial statistical information. Features are extracted using Markov model on enhanced spatial statistics. Multiple difference arrays are considered in different directions for robust feature set. Further, texture operator features are combined to increase the detection accuracy and SVM binary classifier is applied to train the classification model. Experimental results are promising for images of low quality JPEG compression.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.6
• /
• pp.1054-1062
• /
• 2022

The population of Korea's solar salt-producing regions is rapidly aging, resulting in a decrease in the number of productive workers. In solar salt production, salt collection is the most labor-intensive operation because existing salt collection vehicles require human operators. Therefore, we intend to develop an unmanned solar salt collection vehicle to reduce manpower requirements. The unmanned solar salt collection vehicle is designed to identify the salt collection status and location in the salt plate via color detection, the color detection performance is a crucial consideration. Therefore, an image processing algorithm was developed to improve color detection performance. The algorithm generates an around-view image by using resizing, rotation, and perspective transformation of the input image, set the RoI to transform only the corresponding area to the HSV color model, and detects the color area through an AND operation. The detected color area was expanded and noise removed using morphological operations, and the area of the detection region was calculated using contour and image moment. The calculated area is compared with the set area to determine the location case of the collection vehicle within the salt plate. The performance was evaluated by comparing the calculated area of the final detected color to which the algorithm was applied and the area of the detected color in each step of the algorithm. It was confirmed that the color detection performance is improved by at least 25-99% for salt detection, at least 44-68% for red color, and an average of 7% for blue and an average of 15% for green. The proposed approach is well-suited to the operation of unmanned solar salt collection vehicles.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.159-162
• /
• 2002

영상분석의 한 분야로서 에지 검출을 이용하는 많은 분야가 있다. 영상의 에지는 입력 영상에 대한 많은 정보를 제공해 준다. 본 논문에서는 입력영상에 대한 에지검출을 통한 윤곽선 추출을 하여 각각의 픽셀에 대한 에지검출 결과값을 비교하였다. 입력영상으로는 얼굴이미지를 사용하였으며 서로 다른 이미지에 대한 Sobel Filter의 검출의 결과 데이터를 각 픽셀마다 비교함으로써 원영상에 대한 동일인임을 판단하는 기준을 제시하였다.