• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.224-230
• /
• 2013

Lane boundary detection plays a key role in the driver assistance system. This study proposes a robust method for detecting lane boundary in severe environment. First, a horizontal line detects form the original image using improved Vertical Mean Distribution Method (iVMD) and the sub-region image which is under the horizontal line, is determined. Second, we extract the lane marking from the sub-region image using Canny edge detector. Finally, K-means clustering algorithm classifi left and right lane cluster under variant illumination, cracked road, complex lane marking and passing traffic. Experimental results show that the proposed method satisfie the real-time and efficient requirement of the intelligent transportation system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.9-16
• /
• 2008

Recently, there are a lot of multimedia products using image interpolation system. However, most interpolation systems in existence suffer visually to some extents from the effects of blurred edges and jagged artifacts in the image. In this paper, we propose a new adaptive linear interpolation system that uses the sub-pixel. The proposed system calculate the warped distance among the pixels of an image by optimizing length parameter. A new cost function is introduced to reflect frequency properties of the origin data in order to improve image quality. Experimental results show that our new algorithm significantly outperforms conventional interpolation methods in subjective quality, and in most cases, in terms of PSNR as well.

• Current Optics and Photonics
• /
• v.5 no.4
• /
• pp.421-430
• /
• 2021

The multifocal multiphoton microscopy (MMM) enables high-speed imaging by the concurrent scanning and detection of multiple foci generated by lenslet array or diffractive optical element. The MMM system mainly suffers from crosstalk generated by scattered emission photons that form ghost images among adjacent channels. The ghost image which is a duplicate of the image acquired in sub-images significantly degrades overall image quality. To eliminate the ghost image, the photon reassignment method was established using maximum likelihood estimation. However, this post-processing method generally takes a longer time than image acquisition. In this regard, we propose a novel strategy for rapid noise reduction in the MMM system based upon Monte-Carlo (MC) simulation. Ballistic signal, scattering signal, and scattering noise of each channel are quantified in terms of photon distribution launched in tissue model based on MC simulation. From the analysis of photon distribution, we successfully eliminated the ghost images in the MMM sub-images. If the priori MC simulation under a certain optical condition is established at once, our simple, but robust post-processing technique will continuously provide the noise-reduced images, while significantly reducing the computational cost.

• Communications of the Korean Mathematical Society
• /
• v.38 no.3
• /
• pp.755-772
• /
• 2023

Our aim is to establish certain image formulas of the (p, q)-extended modified Bessel function of the second kind M_ν,p,q(z) by employing the Marichev-Saigo-Maeda fractional calculus (integral and differential) operators including their composition formulas and using certain integral transforms involving (p, q)-extended modified Bessel function of the second kind M_ν,p,q(z). Corresponding assertions for the Saigo's, Riemann-Liouville (R-L) and Erdélyi-Kober (E-K) fractional integral and differential operators are deduced. All the results are represented in terms of the Hadamard product of the (p, q)-extended modified Bessel function of the second kind M_ν,p,q(z) and Fox-Wright function _rΨ_s(z).

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.2
• /
• pp.31-40
• /
• 2012

Face recognition refers to the process of identifying individuals based on their facial features. It has recently become one of the most popular research areas in the fields of computer vision, machine learning, and pattern recognition because it spans numerous consumer applications, such as access control, surveillance, security, credit-card verification, and criminal identification. However, illumination variation on face generally cause performance degradation of face recognition systems under practical environments. Thus, this paper proposes an novel face recognition system using a fusion approach based on local binary pattern and two-dimensional principal component analysis. To minimize illumination effects, the face image undergoes the local binary pattern operation, and the resultant image are divided into two sub-images. Then, two-dimensional principal component analysis algorithm is separately applied to each sub-images. The individual scores obtained from two sub-images are integrated using a weighted-summation rule, and the fused-score is utilized to classify the unknown user. The performance evaluation of the proposed system was performed using the Yale B database and CMU-PIE database, and the proposed method shows the better recognition results in comparison with existing face recognition techniques.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.447-451
• /
• 2010

In this paper, we propose a simple but effective algorithm to increase the speed of Emphysema region classification. Emphysema region classification method based on CT image consumes a lot of time because of the large number of subregions due to the large size of CT image. Some of the sub-regions contain no Emphysema and the classification of these regions is worthless. To speed up the classification process, we create an algorithm to select Emphysema region candidates and only use these candidates in the Emphysema region classification instead of all of the sub-regions. First, the lung region is detected. Then we threshold the lung region and only select the dark pixels because Emphysema only appeared in the dark area of the CT image. Then the thresholded pixels are clustered into a region that called the Emphysema pre-detected region or Emphysema region candidate. This region is then divided into sub-region for the Emphysema region classification. The experimental result shows that Emphysema region classification using predetected Emphysema region decreases the size of lung region which will result in about 84.51% of time reduction in Emphysema region classification.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.76-85
• /
• 2019

We introduce a vision-based object detection method for real-time video surveillance system in low-end edge computing environments. Recently, the accuracy of object detection has been improved due to the performance of approaches based on deep learning algorithm such as Region Convolutional Neural Network(R-CNN) which has two stage for inferencing. On the other hand, one stage detection algorithms such as single-shot detection (SSD) and you only look once (YOLO) have been developed at the expense of some accuracy and can be used for real-time systems. However, high-performance hardware such as General-Purpose computing on Graphics Processing Unit(GPGPU) is required to still achieve excellent object detection performance and speed. To address hardware requirement that is burdensome to low-end edge computing environments, We propose sub-frame analysis method for the object detection. In specific, We divide a whole image frame into smaller ones then inference them on Convolutional Neural Network (CNN) based image detection network, which is much faster than conventional network designed forfull frame image. We reduced its computationalrequirementsignificantly without losing throughput and object detection accuracy with the proposed method.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.341-343
• /
• 1995

In this paper, an algorithm is presented to recogniz the driving direction of a vehicle and obstacles in front of it based on highway road image. The algorithm employs a neural network with 27 sub sets obtained from the road image as its input. The outputs include the direction of the vehicle movement and presence or absence of obstacles. The road image, obtained by a video camera, was digitized and processed by a personal computer equipped with an image processing board.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.12-16
• /
• 2022

In this paper, a method for measuring image pattern widths is proposed using gaussian interpolation, in order to improve inconsistent results coming from the different directions in image patterns. The performance of our method is evaluated using image patterns with 9 directions, and compared with previous methods. It is confirmed that the proposed method gives accurate and consistent width results regardless of pattern directions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.1
• /
• pp.658-665
• /
• 2015

In the production of medical images, noise reduction and contrast enhancement are important methods to increase qualities of processing results. By using the edge-based denoising and adaptive nonlinear histogram stretching, a novel medical image enhancement algorithm is proposed. First, a medical image is decomposed by wavelet transform, and then all high frequency sub-images are decomposed by Haar transform. At the same time, edge detection with Sobel operator is performed. Second, noises in all high frequency sub-images are reduced by edge-based soft-threshold method. Third, high frequency coefficients are further enhanced by adaptive weight values in different sub-images. Finally, an adaptive nonlinear histogram stretching method is applied to increase the contrast of resultant image. Experimental results show that the proposed algorithm can enhance a low contrast medical image while preserving edges effectively without blurring the details.