http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Recursive HDR Image Generation from Differently Exposed Images based on Local Image Properties
Andrey Vavilin,Kang-Hyun Jo 제어로봇시스템학회 2008 제어로봇시스템학회 국제학술대회 논문집 Vol.2008 No.10
Dynamic range limitation of CCD-cameras may cause distortions and data loses in images. Such limitations are strongly effect to the further image processing. This paper describes method of combining information from differently exposed images for increasing dynamic range. Initially image is decomposed into set of regions. For each of region we compute detail evaluation function which represents its local properties. Namely mean intensity, intensity deviation and entropy. This function is used to detect regions with high dynamic range. The regions with high dynamic range are then recursively decomposed. This process iterates until all HDR regions are processed, or the size of these regions is too small for decomposition. During the process of decomposition we select the best exposure for each sub-region. For smoothing interregional transaction we used Gaussian-based smoothing function. Proposed technique allows recovering details in overexposed and underexposed parts of image. Our experiments show effectiveness of algorithm for the scenes with high dynamic range. Proposed method shows robust results even if the exposure difference between input images is 2-stops or higher.
임희철,Andrey Vavilin,조강현 제어로봇시스템학회 2008 제어로봇시스템학회 국내학술대회 논문집 Vol.2008 No.10
Road sign recognition (RSR) is one of the most important topics of using computer vision and pattern recognition in intelligent transportation systems. The road sign (RS) includes direction of road, place name, intersection and road number for understanding information of roads. In order to recognize a road sign efficiently, the location of the RS in most cases, must be detected in the initial step. In this paper an efficient method of RSR algorithm is proposed. In this method, 1) the road sign region is extracted by using color and shape, 2) characters of the road sign are segmented by using vertical and horizontal histograms, and 3) each character is recognized by using sum of absolute difference (SAD). In the proposed RSR method, by using color and geometrical properties, we detect candidates of road sign. Input images are obtained from mounted camera in vehicle. Candidate of road sign information segment by using position histogram for verifying candidate road sign. The RSR algorithm calculates SAD value using normalization of road sign and character size. The proposed method is very effective in complex environment.
Wide-field optical coherence microscopy of the mouse brain slice
Min, Eunjung,Lee, Junwon,Vavilin, Andrey,Jung, Sunwoo,Shin, Sungwon,Kim, Jeehyun,Jung, Woonggyu The Optical Society 2015 Optics letters Vol.40 No.19
<P>The imaging capability of optical coherence microscopy (OCM) has great potential to be used in neuroscience research because it is able to visualize anatomic features of brain tissue without labeling or external contrast agents. However, the field of view of OCM is still narrow, which dilutes the strength of OCM and limits its application. In this study, we present fully automated wide-field OCM for mosaic imaging of sliced mouse brains. A total of 308 segmented OCM images were acquired, stitched, and reconstructed as an en-face brain image after intensive imaging processing. The overall imaging area was 11.2??7.0??????mm (horizontal??vertical), and the corresponding pixel resolution was 1.2??1.2??????관m. OCM images were compared to traditional histology stained with Nissl and Luxol fast blue (LFB). In particular, the orientation of the fibers was analyzed and quantified in wide-field OCM.</P>
조강현,코식뎁,Andrey Vavilin,김정선 제어·로봇·시스템학회 2010 International Journal of Control, Automation, and Vol.8 No.5
Tilt correction is a very crucial and inevitable task in the automatic recognition of the vehicle license plate (VLP). In this paper, according to the least square fitting with perpendicular offsets (LSFPO), the VLP region is fitted to a straight line. After the line slope is obtained, rotation angle of the VLP is es-timated. Then the whole image is rotated for tilt correction in horizontal direction by this angle. Tilt correction in vertical direction by minimizing the variance of coordinates of the projection points is proposed. Character segmentation is performed after horizontal correction and character points are projected along the vertical direction after shear transform. Despite the success of VLP detection approaches in the past decades, a few of them can effectively locate license plate (LP), even when vehicle bodies and LPs have similar color. A common drawback of color-based VLP detection is the failure to detect the boundaries or border of LPs. In this paper, we propose a modified recursive la-beling algorithm for solving this problem and detecting candidate regions. According to different col-ored LP, these candidate regions may include LP regions. Geometrical properties of the LP such as area, bounding box and aspect-ratio are then used for classification. Various LP images were used with a va-riety of conditions to test the proposed method and results are presented to prove its effectiveness.
Pedestrian Detection Approach Based on Modified Haar-Like Features and AdaBoost
Van-Dung Hoang,Andrey Vavilin,Kang-Hyun Jo 제어로봇시스템학회 2012 제어로봇시스템학회 국제학술대회 논문집 Vol.2012 No.10
Pedestrian detection is an important task in many applications such as intelligent transportation systems, image retrieval, surveillance systems, automated personal assistance, etc. This paper proposes a set of modified Haar-like features that have parallelogram shapes. Using the proposed feature descriptors to develop a rapid detection system for pedestrian detection based on decision tree structure used boosting algorithm. The experimental results showed that the proposed method could produce high accuracy detection rate with lower false positive rate and higher recall rate than original Haar-like features and it is efficiency with different resolutions and gestures under a variety of backgrounds as well as lighting.