A Novel Region Segmentation Algorithm with Neural Network for Segmented Image Coding

ZHAO Rong-chang; MA Yi-de

doi:10.3969/j.issn.0372-2112.2014.07.006

您当前的位置：

首页 >

文章列表页 >

A Novel Region Segmentation Algorithm with Neural Network for Segmented Image Coding

更新时间：2025-07-16

- A Novel Region Segmentation Algorithm with Neural Network for Segmented Image Coding
- Acta Electronica Sinica Vol. 42, Issue 7, Pages: 1277-1283(2014)
- 作者机构：
  
  1. 兰州大学信息科学与工程学院电路与系统研究所,甘肃,兰州,730000
  2. 中南大学信息科学与工程学院,湖南,长沙,410083
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61175012, No.60872109);New Century Excellent Talents Foundation in University of Ministry of Education of China (No.NECT-06-0900)
- DOI：10.3969/j.issn.0372-2112.2014.07.006
  CLC： TP391
- Published：2014
- 稿件说明：
移动端阅览
ZHAO Rong-chang, MA Yi-de. A Novel Region Segmentation Algorithm with Neural Network for Segmented Image Coding[J]. Acta Electronica Sinica, 2014, 42(7): 1277-1283.
DOI：

ZHAO Rong-chang, MA Yi-de. A Novel Region Segmentation Algorithm with Neural Network for Segmented Image Coding[J]. Acta Electronica Sinica, 2014, 42(7): 1277-1283. DOI： 10.3969/j.issn.0372-2112.2014.07.006.

摘要

为了适应图像分割编码的需要，提高编码性能和效率，本文研究了一种图像区域分割新方法.源于人眼成像原理和视神经网络的知觉分割特性，首先提出一种具有脉冲耦合和梯度锐化能力的神经元网络模型.然后通过构造一个拟合函数对相邻神经元的相似刺激输入进行平滑处理，而对具有不连续变化特性的刺激输入进行锐化，使得神经元比较容易地感知到均匀亮度区域和目标边缘的准确位置.最后通过实验验证了该算法的有效性.本文算法能够准确、有效地的分割出均匀区域，并且与原始图像具有很好的对应关系.在将本文算法应用到图像区域分割编码中，能够大大提高编码的效率，并得到高质量的重建图像.

Abstract

A novel image region segmentation method is proposed to improve the efficiency and characteristic for segmented image coding.Based on human visual system and perceptive segmentation

a neural network with pulse-coupled and gradient-sharpened is introduced firstly.Then

a fitting function is used to smooth the neighboring similar stimulus and sharpen the non-continuous.In this way

neurons could find the accurate location of uniform regions and objective boundaries.At last

experimental results show the efficiency of the algorithm.The homogenous regions can be segmented from its background effectively and accurately.In addition

the segmented regions are corresponding to objects in scene.There are high-quality constructed image if this segmentation algorithm is adopted by segmented image coding.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Enhanced PFCM Algorithm for Noisy Image Segmentation Combining Regional and Neighborhood-Level Information

SwinT-Unet: Ultrasound Image Segmentation Based on Two-Channel Self-Attention Mechanism

A Variational Level Set Model Based on Beer-Lambert Law

ED-NAS: Ceramic Grain Segmentation Based on Neural Architecture Search Using SEM Images

New Theories and Methods of Image Segmentation

Related Author

WANG Xiao-peng

WANG Hai-zhou

CHEN Hao-ran

SONG Yan-tao

LU Yun-li

TANG Li-ming

XIONG Dian-hua

FANG Zhuang

Related Institution

School of Electronic and Information Engineering, Lanzhou Jiaotong University

Institute of Big Data Science & Industry, Shanxi University

School of Computer & Information Technology, Shanxi University

College of Mathematics and Statistics, Hubei Minzu University

College of Mathematics, ABa Teachers University, Wenchuan

⁰