• Title/Summary/Keyword: Complex Images

Search Result 1,009, Processing Time 0.025 seconds

EDMFEN: Edge detection-based multi-scale feature enhancement Network for low-light image enhancement

  • Canlin Li;Shun Song;Pengcheng Gao;Wei Huang;Lihua Bi
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.18 no.4
    • /
    • pp.980-997
    • /
    • 2024
  • To improve the brightness of images and reveal hidden information in dark areas is the main objective of low-light image enhancement (LLIE). LLIE methods based on deep learning show good performance. However, there are some limitations to these methods, such as the complex network model requires highly configurable environments, and deficient enhancement of edge details leads to blurring of the target content. Single-scale feature extraction results in the insufficient recovery of the hidden content of the enhanced images. This paper proposed an edge detection-based multi-scale feature enhancement network for LLIE (EDMFEN). To reduce the loss of edge details in the enhanced images, an edge extraction module consisting of a Sobel operator is introduced to obtain edge information by computing gradients of images. In addition, a multi-scale feature enhancement module (MSFEM) consisting of multi-scale feature extraction block (MSFEB) and a spatial attention mechanism is proposed to thoroughly recover the hidden content of the enhanced images and obtain richer features. Since the fused features may contain some useless information, the MSFEB is introduced so as to obtain the image features with different perceptual fields. To use the multi-scale features more effectively, a spatial attention mechanism module is used to retain the key features and improve the model performance after fusing multi-scale features. Experimental results on two datasets and five baseline datasets show that EDMFEN has good performance when compared with the stateof-the-art LLIE methods.

Study on the 3D Modeling Data Conversion Algorithm from 2D Images (2D 이미지에서 3D 모델링 데이터 변환 알고리즘에 관한 연구)

  • Choi, Tea Jun;Lee, Hee Man;Kim, Eung Soo
    • Journal of Korea Multimedia Society
    • /
    • v.19 no.2
    • /
    • pp.479-486
    • /
    • 2016
  • In this paper, the algorithm which can convert a 2D image into a 3D Model will be discussed. The 2D picture drawn by a user is scanned for image processing. The Canny algorithm is employed to find the contour. The waterfront algorithm is proposed to find foreground image area. The foreground area is segmented to decompose the complex shapes into simple shapes. Then, simple segmented foreground image is converted into 3D model to become a complex 3D model. The 3D conversion formular used in this paper is also discussed. The generated 3D model data will be useful for 3D animation and other 3D contents creation.

Fast Reference Region Adjustment Using Sizing Factor Generation in Correlation-Based Image Tracking

  • Sung, Si-Hun;Chien, Sung-Il
    • Journal of Electrical Engineering and information Science
    • /
    • v.3 no.2
    • /
    • pp.230-238
    • /
    • 1998
  • When size and shape of moving object have been changed, a correlator often accumulates walk-off error. A success of correlation-based tracking largely depends on choosing suitable window size and position and thus transferring the proper reference image to the next frame. For this, we propose the Adaptive Window Algorithm with Four-Direction Sizing Factors (AWA-FSF) for fast adjusting a reference region to enhance reliability of correlation-based image tracking in complex cluttered environments. Since the AWA-FSF is capable of adjusting a reference image size more rapidly and properly, we can minimize the influence of complex background and clutter. In addition, we can finely tune the center point of the reference image repeatedly after main tracking process. Thus we have increased stability and reliability of correlation-based image tracking. We tested performance of the AWA-FSF using 45 real image sequences made of over 3400 images and had the satisfied results for most of them.

  • PDF

Surface Analysis of LB Films and Monolayer for IMI-O Polymer (IMI-O 고분자의 단분자막과 LB막에 대한 표면분석)

  • Jung, Sang-Burm;Yoo, Seung-Yeop;Park, Jae-Chul;Kwon, Young-Soo
    • Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
    • /
    • 2000.05b
    • /
    • pp.265-268
    • /
    • 2000
  • We fabricated an IMI-O polymer containing an imidazole group that could form a complex structure between the monolayer and the metal ions at the air-water interface. Also. the monolayer behavior at the air-water interface and the surface morphology of metal-complexed Langmuir-Blodgett(LB) films were investigated by using Brewster angle microscopy(BAM) and Scanning Maxwell-stress Microscopy(SMM). The difference in the BAM and SMM images between the pure water and the aqueous metal ions is attributed to the interactions of the copolymers with the metal ions at the interface and the consequent change of the monolayer organization.

  • PDF

Experimental Study on Turbulent Structure of Flow over a Micro Riblet Plate (미세 Riblet 평판에서의 난류구조 변화에 관한 실험적 연구)

  • Choi, Yong-Seok;Lee, Sang-Joon
    • 유체기계공업학회:학술대회논문집
    • /
    • 2006.08a
    • /
    • pp.375-376
    • /
    • 2006
  • Turbulent structure of a boundary-layer over a flat plate coated with micro riblet film(MRF) has been investigated experimentally. The turbulent structure was visualized using a dynamic particle image velocimetry (Dynamic PIV) system. We identified the vortex structures from 2-D velocity field data by applying the complex eigenvalue definition. The velocity field images acquired by using the complex eigenvalue definition showed the whole 2-D vortex structures clearly. In addition, the spatial distributions of small-scale vortices as well as large-scale vortices were obtained with high accuracy. The difference of vortex structures between the MRF coated flat plate and the smooth flat plate was analysed in detail. With varying upstream flow speed, the characteristics of vortex structure over the MRF coated flate plate was compared with those over the smooth flat plate.

  • PDF

A Novel Image Dehazing Algorithm Based on Dual-tree Complex Wavelet Transform

  • Huang, Changxin;Li, Wei;Han, Songchen;Liang, Binbin;Cheng, Peng
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.12 no.10
    • /
    • pp.5039-5055
    • /
    • 2018
  • The quality of natural outdoor images captured by visible camera sensors is usually degraded by the haze present in the atmosphere. In this paper, a fast image dehazing method based on visible image and near-infrared fusion is proposed. In the proposed method, a visible and a near-infrared (NIR) image of the same scene is fused based on the dual-tree complex wavelet transform (DT-CWT) to generate a dehazed color image. The color of the fusion image is regulated through haze concentration estimated by dark channel prior (DCP). The experiment results demonstrate that the proposed method outperforms the conventional dehazing methods and effectively solves the color distortion problem in the dehazing process.

A Study on the Changed by Spatial Structure Element for the Space Planning of Apartment Complex (아파트 단지 계획을 위한 공간구성요소의 변화 분석)

  • 오진안
    • Journal of the Korean housing association
    • /
    • v.7 no.2
    • /
    • pp.91-98
    • /
    • 1996
  • View From the point of change of the land of the land of the nation. The advancement in the modern civilization has led to building many apartments characterized by high buildings and building complexes due to population concentration into big cities. This tendency not only causes serious problems in terms of city images but also produces considerable discords in the matter of harmonized beauty of the complex itself.At the stage of space planning for the apartment complexes only economic and functional aspects were considered. So in many cases the space, which dose not contribute to environmental improvement which must go in parallel with the quantity increase of apartments and improvements of welfare and living standards of the apartment inhabitants.

  • PDF

The effect of B-Bi-Zn on properties of NZCF (NCZF의 특성에 미치는 B-Bi-Zn의 영향)

  • 김태원;전석택;김성수;최우성
    • Journal of the Korean Institute of Electrical and Electronic Material Engineers
    • /
    • v.13 no.4
    • /
    • pp.343-348
    • /
    • 2000
  • NCZF ferrites doped with B-Bi-Zn(35-25-40) glass ceramics were prepared to investigate the magnetic properties. The XRD peaks of all of samples were observed only spinel phase. As the additive increased at sintering temperature 750$^{\circ}C$ and 850$^{\circ}C$ for 3 hours, the density and shrinkage of the samples increased until 5.28 g/cm$^3$ and 20% respectively. And other samples showed constant trends having the density about 5.4g/cm$^3$. According to SEM images the growth of grain progressed rapidly at sintering temperature of 850$^{\circ}C$ for 3 hours. Increasing the additive initial permeability and complex permeability decreased. The high values of complex permeability as a function of frequency showed that NCZF doped with 3 wt%, 5wt%, samples at sintered temperature of 850$^{\circ}C$/3h and 900$^{\circ}C$/3h.

  • PDF

Efficient Derivation of Closed-Form Green`s Functions for a Microstrip Structure

  • Oh, Byoung-Hee;Kim, Eui-Joong;Lee, Young-Soon;Young-Ki
    • Journal of electromagnetic engineering and science
    • /
    • v.1 no.1
    • /
    • pp.63-66
    • /
    • 2001
  • In order to derive simple and accurate closed-form spatial Greep’s functions for the thick microstrip substrate, an efficient method based on the two-level approach, which circumvents the burdensome steps (i.e., without necessity of extraction of quasi-static contributions and subsequent determination of approximation parameters) in the previous complex image method, is considered in conjunction with the use of the original Prony`s method. The present method is observed to give more accurate results for the evaluation of the Green`s functions over wider frequency range independently of the source-to-field distances than the previous method.

  • PDF

Characterization of biotin-avidin recognition system constructed on the solid substrate

  • Lim, Jung-Hyurk
    • Analytical Science and Technology
    • /
    • v.18 no.6
    • /
    • pp.460-468
    • /
    • 2005
  • The biotin-avidin complex, as a model recognition system, has been constructed through N-hydroxysuccinimide(NHS) reaction on a variety of substrates such as a smooth Au film, electrochemically roughened Au electrode and chemically modified mica. Stepwise self-assembled monolayers (SAMs) of biotin-avidin system were characterized by surface-enhanced resonance Raman scattering (SERRS) spectroscopy, atomic force microscopy (AFM) and surface plasmon resonance (SPR). A strong SERRS signal of rhodamine tags labeled in avidin from the SAMs on a roughened gold electrode indicated the successful complex formation of stepwise biotin-avidin recognition system. AFM images showed the circular shaped avidin aggregates (hexamer) with ca. $60{\AA}$ thick on the substrate, corresponding to one layer of avidin. The surface coverage and concentration of avidin molecules were estimated to be 90% and $7.5{\times}10^{-12}mol/cm^2$, respectively. SPR technique allowed one to monitor the surface reaction of the specific recognition with high sensitivity and precision.