• Journal of Korea Multimedia Society
• /
• v.21 no.2
• /
• pp.138-146
• /
• 2018

In this paper, we describe an algorithm for extracting depth information from a single image based on CNN. When acquiring three-dimensional information from a single two-dimensional image using a deep-learning technique, it is difficult to accurately predict the edge portion of the depth image because it is a part where the depth changes abruptly. in this paper, we introduce the concept of pixel-wise confidence to take advantage of these characteristics. We propose an algorithm that estimates depth information from a highly reliable flat part and propagates it to the edge part to improve the accuracy of depth estimation.

• International Journal of Advanced Culture Technology
• /
• v.6 no.2
• /
• pp.123-128
• /
• 2018

Learning data is composed of 100 characters with 10 different fonts, and test data is composed of 10 characters with a new font that is not used for the learning data. In order to consider the variety of learning data with several different fonts, 10 learning masks are constructed by accumulating pixel values of same characters with 10 different fonts. This process eliminates minute difference of characters with different fonts. After finding maximum values of learning masks, test data is expanded by multiplying these maximum values to the test data. The algorithm calculates sum of differences of two corresponding pixel values of the expanded test data and the learning masks. The learning mask with the smallest value among these 10 calculated sums is selected as the result of the recognition process for the test data. The proposed algorithm can recognize various types of fonts, and the learning data can be modified easily by adding a new font. Also, the recognition process is easy to understand, and the algorithm makes satisfactory results for character recognition.

• Journal of Korea Multimedia Society
• /
• v.2 no.2
• /
• pp.137-144
• /
• 1999

Error diffusion is excellent for reproducing grey-scale images to binary images. The output of conventional error diffusion produces correlated pattern. In this paper, a new error diffusion coefficient set is proposed to reduce correlated pattern and to enhance edge through frequency analysis of the error diffusion coefficients. The error diffusion coefficients of the previous line are designed to enhance the edge. The error diffusion coefficient of the previous pixel of the current pixel is selected to symmeterize the coefficient set. Because the proposed coefficient-set consists of 1 and 2, a few computations are required. As results of experiments, it is shown that the binary image using the proposed coefficients have better quality than conventional ones.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1362-1364
• /
• 2003

As non-isothermal mixed pixel is widely existed, the pixel-mean temperature cannot adequately represent the actual thermal state of land surface. The row crop was chosen as target to discuss the problem of component temperature retrieval. At first, the matrix model was found to express the thermal radiant directionality of the target. Then correlation of multi-angle infrared radiance was analyzed. In order to increase the retrieving accuracy, we chose the retrievable parameters and established the iterative method combining with inverse matrix to retrieve component temperature. It was proved by field experiment that the method could improve the retrieving accuracy and stability remarkably.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.442-446
• /
• 2010

본 논문에서는 거리변환 기반의 정밀한 fiducial 마크 정렬 알고리즘을 제안한다. 거리변환은 물체의 중심에 가중치를 가지는 특성이 있는데 이는 AOI 공정에서 에칭, 이동과 같은 다양한 요소들로부터 획득되는 타겟영상에 대하여 강인하게 물체의 중심으로 매칭할 수 있도록 한다. 제안한 방법은 우선 입력 타겟영상에 대하여 이진화를 진행하고, 다음 모델과 타겟영상에 대하여 거리변환을 이용하여 거리특징을 추출하고, 추출된 모델과 타겟영상에 대한 거리특징을 NCC(Normalized Cross Correlation)를 이용하여 매칭한 후, 매칭 스코어에 대하여 Sub-pixel 분석을 진행하여 sub-pixel 레벨의 정확도를 가지도록 한다. 실험결과로부터 제안한 거리특징을 이용한 매칭 알고리즘이 기존의 픽셀 밝기 값을 이용한 매칭보다 강인하고 정확하게 매칭됨을 확인할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3406-3418
• /
• 2022

Reversible data hiding is an algorithm that has ability to extract the secret data and to restore the marked image to its original version after data extracting. However, some previous schemes offered the low image quality of marked images. To solve this shortcoming, a new reversible data hiding scheme based on pixel value ordering and edge detection mechanism is proposed. In our proposed scheme, the edge image is constructed to divide all pixels into the smooth regions and rough regions. Then, the pixels in the smooth regions are separated into non overlapping blocks. Then, by taking advantages of the high correlation of current pixels and their adjacent pixels in the smooth regions, PVO algorithm is applied for embedding secret data to maintain the minimum distortion. The experimental results showed that our proposed scheme obtained the larger embedding capacity. Moreover, the greater image quality of marked images are achieved by the proposed scheme than that other previous schemes while the high EC is embedded.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.53.4-53.4
• /
• 2019

We reconstruct the underlying dark matter (DM) density distribution of the local universe within 20Mpc/h cubic box by using the galaxy position and peculiar velocity. About 1,000 subboxes in the Illustris-TNG cosmological simulation are used to train the relation between DM density distribution and galaxy properties by using UNet-like convolutional neural network (CNN). The estimated DM density distributions have a good agreement with their truth values in terms of pixel-to-pixel correlation, the probability distribution of DM density, and matter power spectrum. We apply the trained CNN architecture to the galaxy properties from the Cosmicflows-3 catalogue to reconstruct the DM density distribution of the local universe. The reconstructed DM density distribution can be used to understand the evolution and fate of our local environment.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.75.1-75.1
• /
• 2019

We introduce a novel method for reconstructing the projected dark matter mass maps of merging galaxy clusters by applying the convolutional neural network (CNN) to their weak lensing maps. We generate synthesized grayscale images from given weak lensing maps that preserve their averaged galaxy ellipticity. We then apply them to multi-layered CNN with architectures of alternating convolution and trans-convolution filters to predict the mass maps. We train our architecture with 1,000 Subaru/Suprime-Cam mock weak lensing maps, and our method have better mass map prediction than the Kaiser-Squires method with the following three aspects: (1) better pixel-to-pixel correlation, (2) more accurate finding of density peak position, and (3) free from mass-sheet degeneracy. We also apply our method to the HST weak lensing map of the El Gordo cluster and compare our result to the previous studies.

• Journal of Korea Multimedia Society
• /
• v.13 no.2
• /
• pp.185-195
• /
• 2010

In this paper, we propose an efficient inter and intra prediction algorithms for fast encoding of H.264/AVC. First, inter prediction mode decision method decides early using temporal/spatial correlation information and pixel direction information. Second, intra prediction mode decision method selects block size judging smoothness degree with inner/outer pixel value variation and decides prediction mode using representative pixel and reference pixel. Lastly, adaptive motion search region restriction sets search region using mode information of neighboring block and predicted motion vector. The experimental results show that proposed method can achieve about 18~53% reduction compared with the existing JM 14.1 in the encoding time. In RD performance, the proposed method does not cause significant PSNR value losses while increasing bitrates slightly.

• Journal of Internet Computing and Services
• /
• v.19 no.1
• /
• pp.105-111
• /
• 2018

This paper presents the analysis of image quality with FHD(Full HD) resolution camera equipped DIC(Digital Image Correlation) platform for the measurement of the architectural structure's relative displacement. DIC platform was designed based on i.MX6 of Freescale. Displacement measurement based on DIC method, the error is affected by image quality factors as pixel number, brightness, contrast, and SNR[dB](Signal to Noise Ratio). The effect were analyzed. The displacement of ROI(Region Of Interest) area within the image was measured by sub-pixel units based on DIC method. The non-contact telemetry property of DIC method, it can be used to long distance non-contact measurement. The various displacement results was measured and analyzed with the image quality factor adjustment according to the distance(25m, 35m, 50m).