This paper presents an efficient compression-oriented segmentation algorithm for computer-generated document images. In this algorithm, a document image is represented in a block-based multiscale pyramid. Then, image ...
详细信息
This paper presents an efficient compression-oriented segmentation algorithm for computer-generated document images. In this algorithm, a document image is represented in a block-based multiscale pyramid. Then, image blocks will be characterized based on their entropy values of the intensity histogram, and the entropy distribution are assumed to be Gaussian priors in this work. We will discuss two methods, i.e., off-line and online training, to estimate model parameters. We use the multiscale Bayesian estimation to refine the classification results and generate the final segmentation result, where image blocks are classified into four classes, i.e., background, text, graphic and picture. It is expected that the proposed entropy-based segmentation will be suitable for compound document compression and two training approaches apply to different applications.
作者：
Liu, YongMinsker, Barbara S.Saied, Faisal4163 NCEL
Department of Civil and Environmental Engineering University of Illinois at Urbana-Champaign 205 North Mathews Avenue Urbana IL 61801 United States 3230D NCEL
Department of Civil and Environmental Engineering University of Illinois at Urbana-Champaign 205 North Mathews Avenue Urbana IL 61801 United States National Center for Supercomputing Applications
University of Illinois at Urbana-Champaign 605 E. Springfield Avenue Champaign IL 61820 United States
multiscalemethods have been demonstrated to be highly efficient techniques for solving partial differential equations. In this paper, the idea of applying multiscale computation to an optimal control model of groundw...
详细信息
This book constitutes revised papers from the 12th International conference on Large-Scale Scientific Computing, LSSC 2019, held in Sozopol, Bulgaria, in June 2019. The 70 papers presented in this volume were car...
详细信息
ISBN:
(数字)9783030410322
ISBN:
(纸本)9783030410315
This book constitutes revised papers from the 12th International conference on Large-Scale Scientific Computing, LSSC 2019, held in Sozopol, Bulgaria, in June 2019. The 70 papers presented in this volume were carefully reviewed and selected from 81 submissions. The book also contains two invited talks. The papers were organized in topical sections named as follows: control and optimization of dynamical systems; meshfree and particle methods; fractional diffusion problems: numerical methods, algorithms and applications; pore scale flow and transport simulation; tensors based algorithms and structures in optimization and applications; HPC and big data: algorithms and applications; large-scale models: numerical methods, parallel computations and applications; monte carlo algorithms: innovative applications in conjunctions with other methods; application of metaheuristics to large-scale problems; large scale machine learning: multiscale algorithms and performance guarantees; andcontributed papers.
暂无评论