• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2003년도 하계학술대회 논문집
• /
• pp.94-97
• /
• 2003

본 논문에서는, 웨이브렛 변환과 잡음 섞인 숫자 영상에 대한 최적화 인식 훈련기법을 사용한 다계층 신경망을 제안하고, 이 시스템을 아라비아숫자 인식에 적용한다. 웨이브렛 변환을 이용해 원 영상 정보의 중요한 부분은 최대한 보존하면서 입력벡터의 크기를 줄임으로써 신경망의 노드 수와 학습 수렴시간이 줄어들도록 하였고, 최적화 인식 훈련기법은 데이터의 잡음을 점차적으로 높여가면서 훈련벡터에 적용, 인식률의 변화에 대해 살펴보았다. 잡음이 섞인 숫자 영상의 인식율을 높이기 위해 원 영상에 0, 10, 20, 30, 40, 50㏈의 잡음을 섞은 영상을 훈련에 함께 사용하였다. 테스트 영상에 잡음이 30∼50㏈정도 섞였을 경우에는 원 영상만을 훈련에 이용했을 패와 잡음이 섞인 영상을 이용하여 훈련시켰을 경우에 인식율의 차이가 별로 없지만, 0∼20㏈정도 섞인 영상을 테스트에 사용할때에는 0, 10, 20, 30, 40 , 50㏈의 잡음이 있는 영상을 훈련에 사용했을 때가 원 영상만을 훈련에 이용했을 경우에 비해 인식율이 9% 향상된다.

• 전기학회논문지
• /
• 제57권8호
• /
• pp.1454-1463
• /
• 2008

Blind source separation by independent component analysis (ICA) has applied in signal processing, telecommunication, and image processing to recover unknown original source signals from mutually independent observation signals. Neural networks are learned to estimate the original signals by unsupervised learning algorithm. Because the outputs of the neural networks which yield original source signals are mutually independent, then mutual information is zero. This is equivalent to minimizing the Kullback-Leibler convergence between probability density function and the corresponding factorial distribution of the output in neural networks. In this paper, we present a learning algorithm using information theory and higher order statistics to solve problem of blind source separation. For computer simulation two deterministic signals and a Gaussian noise are used as original source signals. We also test the proposed algorithm by applying it to several discrete images.

• 한국통신학회논문지
• /
• 제21권9호
• /
• pp.2317-2327
• /
• 1996

Original binary image can be reconstructed without any distortion by MS(morphological skeleton) image. Though we reduce some points in a MS image, there is no problem to reconstruct original image by it. And then, there are two methods of LMS and GMS which reduce the redundant points of a MS image. The redundancy degree of a GMS image is zero and it is less than that of LMS. And then, GMS image is the best thing of the three kinds of morphological skeleton image to enhance the compression efficienty by the Elias code. But there are continous SKF=1 points in a GMS image whenever using 2 dimensional structureing element. Those points in a GMS image gives rise to a bad compression efficiency. And then, solving this problem, this paper proposes hybrid structuring elements algorithms for binary image compression.

• 디지털융복합연구
• /
• 제14권6호
• /
• pp.133-142
• /
• 2016

본 연구의 목적은 브랜드의 이미지 및 위조품의 진품과의 제품 유사성이 명품 위조품태도에 미치는 영향을 살펴보는 것이다. 특히 지각된 브랜드 글로벌성의 조절효과와 함께 진품에 대한 태도가 위조품 태도에 미치는 영향도 살펴보았다. 연구의 결과 첫째, 브랜드 이미지는 진품(위조품)태도 모두에 긍정적인 영향을 미치며, 상징적 브랜드 이미지가 진품(위조품)태도 모두에 더 큰 영향을 미치는 것으로 나타났다. 또한 둘째, 지각된 브랜드 글로벌성의 조절효과도 확인되었다. 즉 브랜드이미지가 진품태도에 미치는 영향은 지각된 브랜드 글로벌성에 따라 차이가 유의하지 않았지만, 위조품태도에 미치는 영향은 지각된 브랜드 글로벌성이 높은 경우에 더 선호되는 것으로 나타났다. 셋째, 위조품의 진품과의 제품유사성은 위조품태도에 정(+)의 영향을 미치는 것으로 나타났고, 지각된 품질유사성이 위조품태도에 더 큰 영향을 미치는 것으로 나타났다. 넷째, 진품태도는 위조품 태도에 정(+)의 영향을 미치는 것으로 나타났다. 이와 같은 연구결과는 진품과 위조품의 관계에서 상징적인 측면의 브랜드이미지와 기능적인 측면의 제품유사성이 위조품 태도에 미치는 영향을 종합적으로 이해하는데 이론적 기초를 제공할 것이다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1997년도 Proceedings International Workshop on New Video Media Technology
• /
• pp.101-106
• /
• 1997

A method is proposed to generalize the image transformation from an image to another one according to a pair of example images. When an original image and its target image are given, the unknown image transformation from the original image to the target one in automatically approximated by a sequence of several known image transformation filters by the method. The target image is assumed to be generated manually by using a drawing software. In this method, the order of image transformation filers is regarded as the chromosome of a virtual living thing and is evolved according to Genetic Algorithm. This method can be applied to automatic construction of expert systems for image processing.

• International Journal of Internet, Broadcasting and Communication
• /
• 제13권3호
• /
• pp.50-55
• /
• 2021

In this paper, we proposed a technique for hiding the double-encrypted confidential data in the image using the pixel value of the image and the spatial encryption technique. The proposed technique inserts encrypted confidential data into the LSB of an image pixel in order to maintain high image quality. The stego-image generated by hiding the encrypted confidential data has very good quality and is visually indistinguishable from the original cover image, so that it is impossible to recognize whether the confidential data is hidden in the stego-image. It is possible to extract the original confidential data from the stego-image without loss. By conducting an experiment on the proposed technique, it was confirmed that the proposed technique is an effective technique for the practical application of data hiding. The proposed technique can be used in applications such as military and intellectual property protection that require high security.

• Korean Journal of Radiology
• /
• 제24권4호
• /
• pp.294-304
• /
• 2023

Objective: We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. Materials and Methods: We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. Results: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). Conclusion: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.358-360
• /
• 2004

The digital images contain a significant amount of redundancy and require a large amount of data for their storage and transmission. Therefore, the image compression is necessary to treat digital images efficiently. The goal of image compression is to reduce the number of bits required for their representation. The image compression can reduce the size of image data using contractive mapping of original image. Among the compression methods, the mapping is affine transformation to find the block(called range block) which is the most similar to the original image. In this paper, we applied the neural network(SOM) in encoding. In order to improve the performance of image compression, we intend to reduce the similarities and unnecesaries comparing with the originals in the codebook. In standard image coding, the affine transform is performed with eight isometries that used to approximate domain blocks to range blocks.

• 한국멀티미디어학회논문지
• /
• 제18권12호
• /
• pp.1462-1467
• /
• 2015

Pixel values of original image can be changed by XORing pixel values of original image and pixel values of the basis image obtained by pseudo random sequences. This is a simple method for image encryption. This method is an effect method for easy hardware implementation and image encryption with high speed. In this paper we propose a method to obtain basis image with pseudo random sequences with large nonlinearity using nonlinear cellular automata and maximum length linear cellular automata. And experimental results showed that the proposed image encryption scheme has large key space and low correlation of adjacent cipher pixel values.

• 한국컴퓨터산업학회논문지
• /
• 제7권5호
• /
• pp.467-472
• /
• 2006

본 논문에서는 훼손된 영상 신호를 복원하는 기존의 나가오 필터의 수식 과정 중 일부를 제거하여 처리시간을 단축하고 그 효과는 유지하는 방법에 대해서 연구하였다. 기존의 나가오 필터를 이용한 신호처리 복원 방법으로는 계산량이 많아 한 화소를 처리하기 위해서는 많은 시간이 소요된다. 따라서 본 논문에서는 기존의 나가오 필터의 수식 과정 중 표준편차를 구화는 과정을 제거함으로써 처리시간이 단축되면서 그 효과는 유지됨을 확인한다. 모의 실험을 통하여 이 방법의 우수성을 확인한다.