• 한국인공지능학회지
• /
• 제11권1호
• /
• pp.17-24
• /
• 2023

With the continuous growth in the amount of data collected and analyzed, deep learning has become increasingly popular for extracting meaningful insights from various fields. However, hardware limitations pose a challenge for achieving meaningful results with limited data. To address this challenge, this paper proposes an algorithm that leverages the characteristics of convolutional neural networks (CNNs) to reduce the size of image datasets by 20% through smoothing and shrinking the size of images using color elements. The proposed algorithm reduces the learning time and, as a result, the computational load on hardware. The experiments conducted in this study show that the proposed method achieves effective learning with similar or slightly higher accuracy than the original dataset while reducing computational and time costs. This color-centric dataset construction method using image smoothing techniques can lead to more efficient learning on CNNs. This method can be applied in various applications, such as image classification and recognition, and can contribute to more efficient and cost-effective deep learning. This paper presents a promising approach to reducing the computational load and time costs associated with deep learning and provides meaningful results with limited data, enabling them to apply deep learning to a broader range of applications.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.132-134
• /
• 2004

This paper proposes partial image encryption system for secure transmission of images. Partial image encryption is suitable for real-time processing purpose of multimedia data that needs compression and encryption. Compression part uses modified SPIHT algorithm and encryption part uses AES. Partial image encryption is significant reduction in encryption time in comparison with whole image encryption.

• 대한디지털의료영상학회논문지
• /
• 제12권1호
• /
• pp.19-25
• /
• 2010

This study is mainly for the reduction of exposure dose by using a heavy elements filter(Gd) in the digital radiology. They contained heavy elements filter of Gd and X-ray beam hardening filters such as Al and Cu. According to the results of experimental evaluation, X-ray property was not changed with variety of kVp in the case of the Gd filter. The surface dose and absorption dose were increased in order of Cu and Al. The contrast of image showed the higher value in order of Cu, Al and Gd. While the use of Gd has increased the numerical value of the CR image, and grayscale has decreased noise value of the DR image.

• 전기학회논문지
• /
• 제60권5호
• /
• pp.1023-1029
• /
• 2011

In the industrial vision systems, image correction has great influence on the overall performance of measurement or inspection. The overall area of distorted image is usually splitted into small control areas, and each area is corrected by its control points. The performance of correction methods using control points can be improved by reduction of control areas because the computational time and memory highly depend on the number of control areas. We develop a merging algorithm that reduces control areas and preserves the correction accuracy. The algorithm merges the splitted control areas by use of quad tree method. Experimental results are presented to verify the usefulness of the proposed method.

• Journal of Astronomy and Space Sciences
• /
• 제27권4호
• /
• pp.309-318
• /
• 2010

We introduce a technical approach for reducing three-dimensional infrared (IR) spectroscopic data generated by integral field spectroscopy or slit-scanning observations. The first part of data reduction using IRAF presents a guideline for processing spectral images from long-slit IR spectroscopy. Multichannel image reconstruction, Image Analysis and Display (MIRIAD) is used in the later part to construct and analyze the data cubes which contain spatial and kinematic information of the objects. This technic has been applied to a sample data set of diffuse 2.1218 ${\mu}m$ $H_2$ 1-0 S(1) emission features observed by slit-scanning around Sgr A East in the Galactic center. Details of image processing for the high-dispersion infrared data are described to suggest a sequence of contamination cleaning and distortion correction. Practical solutions for handling data cubes are presented for survey observations with various configurations of slit positioning.

• International Journal of Precision Engineering and Manufacturing
• /
• 제9권2호
• /
• pp.28-33
• /
• 2008

In a scanning electron microscope (SEM), outside acoustic noise causes image noise that distorts observations of the specimen being examined. A SEM that is less sensitive to acoustic noise is highly desirable. This paper investigates the image noise problem by addressing the mode shapes of the base plate and the transmission path of the acoustic noise and vibration. By arranging the position of the rib, a new SEM base plate was developed that had twisting as the 1st and 2nd modes. In those two twisting modes, vibration nodes existed near the center of the base plate where the specimen chamber is placed. Less vibration was transmitted to the chamber and to the specimen by the twisting modes compared to bending ones, which are the 2nd and 3rd modes for a rectangular plain base plate. An SEM with the developed base plate installed exhibited a significant reduction of image noise when exposed to acoustic noises below 250 Hz.

• 한국멀티미디어학회논문지
• /
• 제22권1호
• /
• pp.10-17
• /
• 2019

In High Dynamic Range (HDR) image processing, tone mapping is the process to compress an input image into a Low Dynamic Range (LDR) image. In most cases, the reason that detail preservation is prior to take over tone mapping is that the dynamic range is significantly different between input and output images. In the case of iCAM06, details are separated by using a bilateral filter, however, it causes noise amplification at the dim surround region. Thus, we suggest that the detail signal, which is separated from the bilateral filter, is combined with the base signal after an adaptive Kalman filter is applied according to the local standard deviation. We confirmed that the proposed method enhances the HDR images quality by checking the noise reduction in a dim surround region.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2018년도 추계학술대회
• /
• pp.73-76
• /
• 2018

A Gaussian noise is caused by surrounding environment or channel interference when transmitting image. The noise reduces not only image quality degradation but also high-level image processing performance. The Non-Local Means (NLM) filter finds similarity in the neighboring sets of pixels to remove noise and assigns weights according to similarity. The weighted average is calculated based on the weight. The NLM filter method shows low noise cancellation performance and high complexity in the process of finding the similarity using weight allocation and neighbor set. In order to solve these problems, we propose an algorithm that shows an excellent noise reduction performance by using Summed Square Image (SSI) to reduce the complexity and applying the weighting function based on a cosine Gaussian kernel function. Experimental results demonstrate the effectiveness of the proposed algorithm.

• 디지털산업정보학회논문지
• /
• 제17권2호
• /
• pp.1-11
• /
• 2021

Salt and pepper is a type of impulse noise. It may appear due to an error in the image transmission process and image storage memory. This noise changes the pixel value at any position in the image to 0 (in case of pepper noise) or 255 (in case of salt noise). In this paper, we present an algorithm for SAP noise reduction. The proposed method consists of three steps. In the first step, the location of the SAP noise is detected, and in the second step, the pixel value of the detected location is restored using a weighted average of the surrounding pixel values. In the last step, a reliability matrix around the reconstructed pixels is constructed, and additional correction is performed with a weighted average using this. As a result of the experiment, the proposed method appears to have similar or higher objective and subjective image quality than previous methods for almost all SAP noise ratios.

• Journal of the Korean Wood Science and Technology
• /
• 제31권6호
• /
• pp.15-21
• /
• 2003

Image processing technique was adapted for exploring the more convenient ways to investigate the drying characteristics of wood. The acquisition of information about drying characteristics is indispensable for the development or improvement of dry-kiln schedules. A small internal fan type wood dry kiln was combined with image-processing and data-acquisition systems to monitor continuously the formation of checks and moisture reduction during drying. All the images and data were analyzed to improve or estimate the dry-kiln schedules and predict the drying time which would be required to dry green wood to 10% moisture content in internal fan type kiln. Samples of 20 mm- and 50 mm-thick Metasequoia glyptostrobodies, Paulownia coreana Uyeki, Pinus densiflora Sieb. Et Zucc., Platanus occidentalis L., Quercus acutissima and Robinia pseudo-acacia were used to verify the potentiality of this technique.