• Korean Journal of Remote Sensing
• /
• v.31 no.1
• /
• pp.21-28
• /
• 2015

The essential idea of de-noising is referring to neighboring pixels of a center pixel to be updated. Conventional adaptive de-noising filters use local statistics, i.e., mean and variance, of neighboring pixels including the center pixel. The drawback of adaptive de-noising filters is that their performance becomes low when edges are contained in neighboring pixels, while anisotropic diffusion de-noising filters remove adaptively noises and preserve edges considering intensity difference between neighboring pixel and the center pixel. The anisotropic diffusion de-noising filters, however, use only intensity difference between neighboring pixels and the center pixel, i.e., local statistics of neighboring pixels and the center pixel are not considered. We propose a new connectivity function of two adjacent pixels using statistics of neighboring pixels and apply connectivity function to diffusion coefficient. Experimental results using an aerial image corrupted by uniform and Gaussian noises showed that the proposed algorithm removed more efficiently noises than conventional diffusion filter and median filter.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.11
• /
• pp.1-7
• /
• 2018

In this paper, we propose soft dead pixels detection method by analysing different response at hot and cold images. Abnormal pixels are able to effect detecting a small target. It also makes confusing real target or not cause of changing target size. Almost exist abnormal pixels after image signal processing even if dead pixels are removed by dead pixel compensation are called soft dead pixels. They are showed defect in final image. So removing or compensating dead pixels are very important for detecting object. The key idea of this proposed method, detecting dead pixels, is that most of soft deads have different response characteristics between hot image and cold image. General infrared cameras do NUC to remove FPN. Working 2-reference NUC must be needed getting data, hot & cold images. The way which is proposed dead pixel detection is that we compare response, NUC gain, at each pixel about two different temperature images and find out dead pixels if the pixels exceed threshold about average gain of around pixels.

• Current Optics and Photonics
• /
• v.6 no.5
• /
• pp.463-472
• /
• 2022

At certain wavelengths, single-pixel imaging is considered to be a solution that can achieve high quality imaging and also reduce costs. However, achieving imaging of complex scenes is an overhead-intensive process for single-pixel imaging systems, so low efficiency and high consumption are the biggest obstacles to their practical application. Improving efficiency to reduce overhead is the solution to this problem. Salient object detection is usually used as a pre-processing step in computer vision tasks, mimicking human functions in complex natural scenes, to reduce overhead and improve efficiency by focusing on regions with a large amount of information. Therefore, in this paper, we explore the implementation of salient object detection based on single-pixel imaging after a single pixel, and propose a scheme to reconstruct images based on Fourier bases and use U²Net models for salient object detection.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.1
• /
• pp.1-10
• /
• 2001

In order to generate the gray scale image by the binary state imaging devices such as a digital printer, the gray scale image needs to be converted into the binary image by the halftoning techniques. This paper presents a new error diffusion technique to achieve the homogeneous dot distributions on the binary images. In this paper,'the minimum pixel distance'from the current pixel under binarization to the nearest minor pixel is defined first. Also, the gray levels of the input image are converted into a new variable based on the principal distance for the error diffusion. In the proposed method, the difference in the principal distances is utilized for the error propagation, whereas the gray level difference due to the binarization is diffused to the neighboring pixels in the existing error diffusion techniques. The quantization is accomplished by comparing the updated principal distance with the minimum pixel distance. In order to calculate the minimum pixel distance, MPOA(Minor Pixel Offset Array) is employed to reduce the computational loads and memory resources.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.4
• /
• pp.965-970
• /
• 2013

It is important work to extract saliency regions from an image as preprocessing for various image processing methods. In this paper, we introduce an improved method to estimate saliency value of each pixel from an image. The proposed method is an improved work of the previously studied method using color and statistical framework to estimate saliency values. At first, saliency value of each pixel is calculated using the local contrast of an image region at various scales and the most significant saliency pixel is determined using saliency value of each pixel. Then, saliency value of each pixel is again estimated using gauss weight with respect to the most significant saliency pixel and the saliency of each pixel is determined to calculate initial probability. At last, the saliency value of each pixel is calculated by Bayes' rule. The experiments show that our approach outperforms the current statistical based method.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.727-731
• /
• 2003

ASTER image has some advantages for classification such as 15 spectral bands and 15m ${\sim}$ 90m spatial resolution. However, in the classification using general remote sensing image, shadow areas are often classified into water area. It is very difficult to divide shadow and water. Because reflectance characteristics of water is similar to characteristics of shadow. Many land cover items are consisted in one pixel which is 15m spatial resolution. Nowadays, very high resolution satellite image (IKONOS, Quick Bird) and Digital Surface Model (DSM) by air borne laser scanner can also be used. In this study, mixed pixel analysis of ASTER image has carried out using IKONOS image and DSM. For mixed pixel analysis, high accurated geometric correction was required. Image matching method was applied for generating GCP datasets. IKONOS image was rectified by affine transform. After that, one pixel in ASTER image should be compared with corresponded 15×15 pixel in IKONOS image. Then, training dataset were generated for mixed pixel analysis using visual interpretation of IKONOS image. Finally, classification will be carried out based on Linear Mixture Model. Shadow extraction might be succeeded by the classification. The extracted shadow area was validated using shadow image which generated from 1m${\sim}$2m spatial resolution DSM. The result showed 17.2% error was occurred in mixed pixel. It might be limitation of ASTER image for shadow extraction because of 8bit quantization data.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.1087-1098
• /
• 2023

The rapid advancement of artificial intelligence (AI) technology has led to its proactive utilization across various fields. However, this widespread adoption of AI-based systems has raised concerns about the increasing threat of attacks on these systems. In particular, deep neural networks, commonly used in deep learning, have been found vulnerable to adversarial attacks that intentionally manipulate input data to induce model errors. In this study, we propose a method to protect image classification models from visually imperceptible One-Pixel attacks, where only a single pixel is altered in an image. The proposed defense technique utilizes an autoencoder model to remove potential threat elements from input images before forwarding them to the classification model. Experimental results, using the CIFAR-10 dataset, demonstrate that the autoencoder-based defense approach significantly improves the robustness of pretrained image classification models against One-Pixel attacks, with an average defense rate enhancement of 81.2%, all without the need for modifications to the existing models.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.6
• /
• pp.1363-1368
• /
• 2011

This paper describes an analysis on the granular noise in pixel-to-pixel mapping-based computational integral imaging. The pixel mapping-based method provides a high-resolution reconstructed images and also its computational cost is very lower than the previous back-projection-based method. In this paper, a signal model for the pixel mapping-based method is introduced, which defines and analyzes the granular noise. Computer experiments provides the granular noise properties based on the proposed signal model. The experimental results indicates that the granular noise pattern differs from that of the back-projection based method. The results is also utilized in the pixel mapping-based method.

• Journal of Korea Game Society
• /
• v.3 no.1
• /
• pp.86-93
• /
• 2003

In this paper, we propose a new antialiasing method using filtering technique which is base on morphological pixel structure Aliasing occurs along the edge of lines and polygons. This undesirable effect happens because there are not enough pixels available on a typical monitor to properly display mathematically smooth lines and polygon edges. Aliasing can be very distracting. In a typical graphic scene, aliasing artifact will be visible along the edges of all objects that greatly diminish of realism. The proposed antialiasing method attempts to smooth extreme jagged contour lines and edges by properly handling pixel's structure, surface type and adjusting the pixel color according to the amount of pixel coverage. Next, we use filtering technique considering morphological pixel structure. Experimental results have shown that the propose algorithm achieves better performance in reducing noise for antialiasing. The method will be widely applied to basic antialiasing technique for computer graphic applications.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.4C
• /
• pp.380-387
• /
• 2009

In this paper, optical image encryption using integral imaging and pixel-scrambling technologies is proposed. In the encryption process, we use pixel scrambling to change the order of subsections into which the cover image is divided, and the utilize the integral imaging scheme to obtain the elemental image from the scrambled image. In order to achieve higher security, we reuse pixel scrambling to the elemental image. In the decryption process, we employ optical integral imaging reconstruction technique and inverse pixel scrambling methode. Computer simulation results prove the feasibility of the proposed method and robustness against data loss and noise.