期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

一种新的基于分类模式识别的图像编码算法

A NEW IMAGE CODING ALGORITHM BASED ON CLASSIFIED PATTERN RECOGNITION
下载PDF
导出
摘要 提出了一种新的基于分类模式识别的图像编码方案,基本思想是:1)先利用模式识别对图像进行预测,然后进行DCT编码;2)将图像分为高频和低频2个区域分别进行模式库的训练,以提高图像预测效果.实验表明,与基于未分类模式识别的图像编码算法相比,所提算法具有更好的预测编码性能,在压缩比为30∶1时,重建图像的平均峰值信噪比PSNR有1.3 dB的改善. A new image coding algorithm based on classified pattern recognition is proposed. It uses pattern recognition to predict input image, then dose DCT coding on the predicting error image. To improve performance of prediction, a classified SOM algorithm for pattern library training is proposed. Experimental results show that the porposed algorithm has better coding performance than basic coding algorithm based on pattern recognition, with compression ratio is 30： 1, improvement of PSNR is about 1.3 dB using Lena image.
作者 刘波 李达 黎洪松
机构地区 北京师范大学信息科学与技术学院
出处 《北京师范大学学报（自然科学版）》 CAS CSCD 北大核心 2008年第5期491-493,共3页 Journal of Beijing Normal University(Natural Science)
关键词 自组织特征映射 图像模式识别 图像编码 self-organizing feature map pattern recognition image coding
分类号 TN919.81 [电子电信—通信与信息系统] TP391.4 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献11

  • 1黎洪松,李达.一种新的基于自学习神经网络的静止图像编码方案[J].北京师范大学学报（自然科学版）,2006,42(5):498-500. 被引量：2
  • 2李达,黎洪松.一种改进的立体图像编码算法[J].北京师范大学学报（自然科学版）,2007,43(1):50-52. 被引量：3
  • 3黎洪松.一种新的自组织神经网络算法[J].北京师范大学学报（自然科学版）,2005,41(5):496-498. 被引量：5
  • 4Su X, Wah B. Multidescription video streaming with optimized reconstruction based DCT and neural network ompensations[J]. IEEE Trans. Image Processing, 2001, 3(1):123
  • 5Kohonen T. An introduction to neural computing[J]. Neural Networks, 1988,1:3
  • 6Gafiychuk V V, Datsko B Y, lzmaylova J. Analysis of data clusters obtained by self-organizing methods [J]. Physica A-statistical Mechanics and It's Applications, 2004,341(10) :547
  • 7Fang W C, Sheu B J. A VLSI neural processor for image data compression using self-organizing networks [J]. IEEE Trans. on Neural Networks, 1992,3(5):1112
  • 8Shigei N, Miyajima H, Maeda M. Numerical evaluation of incremental vector quantization using stochastic relaxation [J].IEICE Trans. on Fundamentals of Electronics Communcations and Computer, 2004, 87 (9) :2364
  • 9Tan X Y, Chen S C, Zhou Z H. Robust face recognition from a single training image per person with Kernel-based SOM-face[J].Advances in Neural Networks-ISNN 2004, PT1 Lecture Notes in Computer Science, 2004,3173:858
  • 10Tasrabadi N M, Feng Y. Vector quantization of images based upon the Kohobnen self-organizing feature maps [ C ]. International Joint Conference on Neural Networks, San Diego, CA, 1988, 1:101-118

二级参考文献36

  • 1陈善学.图像矢量量化的等误差自组织特征映射算法[J].系统工程与电子技术,2004,26(9):1189-1191. 被引量：3
  • 2刘丽娟,邹雪城,沈绪榜.一种新的矢量量化编码算法[J].小型微型计算机系统,2004,25(10):1831-1835. 被引量：2
  • 3Nasrabadi N M, Feng Y. Vector quantization of images based upon the Kohonen self-organizing feature maps[C]//Pro.Int.Joint Conf. Neural Networks. San Diego,CA, 1988.
  • 4Christophe Amerijckx, Michel Verleysen, Philippe Thissen. Image Compression by Self-Organized Kohonen Maps[J]. IEEE Trans. on Neural Networks, 1998, 9(5):1287.
  • 5Kohonen T. Learning vector quantization., handbook of brain theory and neural networks [M]. 2nd ed.Cambridge: MIT Press, 2002 : 631-635.
  • 6Kohonen T. An introduction to neural computing[J].Neural Networks, 1988,1 : 3.
  • 7Gafiychuk V V, Datsko B Y, Izmaylova J. Analysis of data clusters obtained by self-organizing methods [J].Physica A-statistical Mechanics and It's Applications,2004, 341(10) :547.
  • 8Fang W C, Sheu B J. A VLSI neural processor for image data compression using self-organizing networks [J].IEEE Trans. On Neural Networks, 1992, 3(5):1112.
  • 9Shigei N, Miyajima H, Maeda M. Numerical evaluation of incremental vector quantization using stochastic relaxation [J]. IEICE Trans. on Fundamentals of Electronics Communcations and Computer, 2004,87 (9) :2364.
  • 10Tan X Y, Chen S C, Zhou Z H. Robust face recognitionfrom a single training image per person with Kernel-based SOM-face [J]. Advances in Neural Networks-ISNN2004, PT 1 Lecture Notes in Computer Science, 2004,3173 : 858.

共引文献5

北京师范大学学报（自然科学版）
2008年 第5期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部