• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05a
• /
• pp.24-27
• /
• 2004

An enhancement of tracking capacity to find a position of the Iris images is presented in this paper. The propose algorithm is called FFDP (Four Points Diagonal Positioning) that the image is positioned with arbitrary 4 points on the edge of iris and the selective 4 points are drawn by a diagonal line on the cross. The experiment result shows that the algorithm is efficient to track on the eyelid.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.1C
• /
• pp.50-58
• /
• 2004

An image enhancement method using modified anisotropic diffusion filter is proposed in this paper. It employs sensor noise estimation and scale space methods based on the minimum reliable scale. Then the anisotropic diffusion filter is modified by the calculated critical value function and local gradient. Through simulation, it is verified that the proposed algorithm has the capability of little or no noise amplification in homogenous region as well as superior edge enhancement.

• Korean Journal of Remote Sensing
• /
• v.32 no.1
• /
• pp.13-24
• /
• 2016

This paper presents a method to evaluate the performance of subpixel localization operators using target image data. Subpixel localization of edges is important to extract the precise shape of objects from images. In this study, each target image was designed to provide reference lines and edges to which the localization operators can be applied. We selected two types of moment-based operators: Gray-level Moment (GM) operator and Spatial Moment (SM) operator for comparison. The original edge localization operators with kernel size 5 are tested and their extended versions with kernel size 7 are also tested. Target images were collected with varying Camera-to-Object Distance (COD). From the target images, reference lines are estimated and edge profiles along the estimated reference lines are accumulated. Then, evaluation of the performance of edge localization operators was performed by comparing the locations calculated by each operator and by superimposing them on edge profiles. Also, enhancement of edge localization by increasing the kernel size was also quantified. The experimental result shows that the SM operator whose kernel size is 7 provides higher accuracy than other operators implemented in this study.

• The Korean Journal of Applied Statistics
• /
• v.33 no.6
• /
• pp.813-821
• /
• 2020

Recently, research using unstructured data such as images and videos has been actively conducted in various fields. Edge detection is one of the most useful image enhancement techniques to improve the quality of the image process. However, it is very difficult to perform edge detection in noise images because the edges and noise having high frequency components. This paper uses a linear model and standard deviation as an effective edge detection method for noise images. The edge is detected by the difference between the standard deviation of the pixels included in the pixel block and the standard deviation of the residual obtained by fitting the linear model. The results of edge detection are compared with the results of the Sobel edge detector. In the original image, the Sobel edge detection result and the proposed edge detection result are similar. Proposed method was confirmed that the edge with reduced noise was detected in the various levels of noise images.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.89-100
• /
• 2023

Recently, on-device artificial intelligence (AI) solutions using mobile devices and embedded edge devices have emerged in various fields, such as computer vision, to address network traffic burdens, low-energy operations, and security problems. Although vision transformer deep learning models have outperformed conventional convolutional neural network (CNN) models in computer vision, they require more computations and parameters than CNN models. Thus, they are not directly applicable to embedded edge devices with limited hardware resources. Many researchers have proposed various model compression methods or lightweight architectures for vision transformers; however, there are only a few studies evaluating the effects of model compression techniques of vision transformers on performance. Regarding this problem, this paper presents a performance evaluation of vision transformers on embedded platforms. We investigated the behaviors of three vision transformers: DeiT, LeViT, and MobileViT. Each model performance was evaluated by accuracy and inference time on edge devices using the ImageNet dataset. We assessed the effects of the quantization method applied to the models on latency enhancement and accuracy degradation by profiling the proportion of response time occupied by major operations. In addition, we evaluated the performance of each model on GPU and EdgeTPU-based edge devices. In our experimental results, LeViT showed the best performance in CPU-based edge devices, and DeiT-small showed the highest performance improvement in GPU-based edge devices. In addition, only MobileViT models showed performance improvement on EdgeTPU. Summarizing the analysis results through profiling, the degree of performance improvement of each vision transformer model was highly dependent on the proportion of parts that could be optimized in the target edge device. In summary, to apply vision transformers to on-device AI solutions, either proper operation composition and optimizations specific to target edge devices must be considered.

• Journal of Broadcast Engineering
• /
• v.14 no.2
• /
• pp.253-264
• /
• 2009

This paper presents an algorithm, aims at practical applications, for the high speed processing and performance enhancement of lane detection base on vision processing system. As a preprocessing for high speed lane detection, the vanishing line estimation and the optimal extraction of region of interest for lane boundary (ROI-LB) can be processed to reduction of detection region in which high speed processing is enabled. Image feature information is extracted only in the ROI-LB. Road lane is extracted using a non-parametric model fitting and Hough transform within the ROI-LB. With simultaneous processing of noise reduction and edge enhancement using the Laplacian filter, the reliability of feature extraction can be increased for various road lane patterns. Since outliers of edge at each block can be removed with clustering of edge orientation for each block within the ROI-LB, the performance of lane detection can be greatly improved. The various real road experimental results are presented to evaluate the effectiveness of the proposed method.

• Journal of Korean Society for Atmospheric Environment
• /
• v.20 no.4
• /
• pp.503-514
• /
• 2004

In Seoul metropolitan area, nocturnal variation of surface ozone concentrations observed at 27 monitoring sites from 1998 to 2002 showed that high ozone levels occurred frequently during the spring. Frequency distributions for nighttime ozone indicated that elevated concentrations in spring were influenced by advection of different air mass compared to other seasons. Surface wind analysis during the spring revealed that relatively strong southwesterly winds were associated with nocturnal ozone enhancement, which can be attributed to the regional transport of ozone. In order to identify the origin of nocturnal ozone enhancement in spring, 3-day backward trajectories were calculated by HYSPLIT 4 for the episode days and then classified. The results showed that NW, W, and SW flows, indicating influence of polluted air masses from the China continent, have 51% in a]1 the episode days, which suggest that the nocturnal ozone enhancement can occur under the effect of long-range transport of ozone-laden air mass on a regional scale. Case study of nocturnal ozone maxima associated with long-range transport was discussed in more detail in the light of meteorological conditions. Southwesterly synoptic flow along the outer edge of moving high-pressure system was found to be the important cause of nocturnal ozone maxima in Seoul. This flow could lead to be long-range transport of ozone that had effectively accumulated in the stagnating portion of the system located eastern coast of China. Low atmosphere soundings, backward trajectories, and elevated ozone and CO levels at the back-ground tiles gave evidence for regional effects on nocturnal ozone enhancement In Seoul.

• Journal of Information Processing Systems
• /
• v.19 no.4
• /
• pp.417-426
• /
• 2023

To improve the effect of image restoration and solve the image detail loss, an image dehazing enhancement algorithm based on mean guided filtering is proposed. The superpixel calculation method is used to pre-segment the original foggy image to obtain different sub-regions. The Ncut algorithm is used to segment the original image, and it outputs the segmented image until there is no more region merging in the image. By means of the mean-guided filtering method, the minimum value is selected as the value of the current pixel point in the local small block of the dark image, and the dark primary color image is obtained, and its transmittance is calculated to obtain the image edge detection result. According to the prior law of dark channel, a classic image dehazing enhancement model is established, and the model is combined with a median filter with low computational complexity to denoise the image in real time and maintain the jump of the mutation area to achieve image dehazing enhancement. The experimental results show that the image dehazing and enhancement effect of the proposed algorithm has obvious advantages, can retain a large amount of image detail information, and the values of information entropy, peak signal-to-noise ratio, and structural similarity are high. The research innovatively combines a variety of methods to achieve image dehazing and improve the quality effect. Through segmentation, filtering, denoising and other operations, the image quality is effectively improved, which provides an important reference for the improvement of image processing technology.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.612-615
• /
• 2003

The error diffusion is a good method to reconstruct the continuous tones of an image to the bilevel tones However the reconstruction of edge characteristic by the nor diffusion is represented work when power spectrum is analyzed fer display error. In this paper, we present an edge enhanced error diffusion method to preprocess original image to achieve the enhancement for the edge characteristic. The preprocessing algorithm consist of two processes. First the difference value between the current pixel and the local average of the surrounding pixel in original image is obtained. Second, the weighting function is composed by the magnitude and the sign of the local average. To confirm the effect of the proposed method, it is compared with the conventional edge enhanced error diffusion methods by measuring the radially averaged power spectrum densities (RAPSDs) for their display errors. The comparison result demonstrate the superiority of the proposed method over the conventional ones.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.4
• /
• pp.422-433
• /
• 2001

In this paper, we propose a flew edge detection method based on water flow model, in which gradient image surface is considered as a 3-dimensional (3-D) geographical feature. The edges of the objects in the background can be detected by the large gradient magnitude areas and to make the edges immersed it is required to invert the gradient image. The proposed edge detector uses a water flow model based enhancement and locally adaptive thresholding technique applied to the inverted gradient image resulting in better noise performance. Computer simulations with a few synthetic and real images show that the Proposed method can extract edge contour effectively.