基于超像素的条件随机场图像分类

计算机应用 ›› 2012, Vol. 32 ›› Issue (05): 1272-1275.

基于超像素的条件随机场图像分类

张微,汪西莉

陕西师范大学计算机科学学院，西安 710062

收稿日期:2011-11-15 修回日期:2012-01-11 发布日期:2012-05-01 出版日期:2012-05-01
通讯作者: 汪西莉
作者简介:张微（1987-)，女，陕西西安人，硕士研究生，主要研究方向：模式识别、图像处理；汪西莉（1969-)，女，陕西西安人，教授，博士，主要研究方向：智能信息处理、模式识别、图像处理。
基金资助:
国家自然科学基金资助项目（41171338）;中央高校基本科研业务费专项基金资助项目（GK200902015）;陕西师范大学青年科技项目（201001003）

Superpixel-based conditional random field for image classification

ZHANG Wei,WANG Xi-li

School of Computer Science, Shaanxi Normal University, Xi'an Shaanxi 710062, China

Received:2011-11-15 Revised:2012-01-11 Online:2012-05-01 Published:2012-05-01
Contact: WANG Xi-li

摘要/Abstract

摘要： 针对图模型在推导和参数估计中时间复杂度较高的问题，在条件随机场(CRF)中引入了超像素的概念，提出了一种基于超像素的CRF图像分类方法。该方法首先通过均值漂移算法将图像过分割成小的均匀区域（称为超像素），然后以超像素为节点、空间相邻的节点以边连接建立图模型，给出了相应的CRF的定义，实现了模型的参数估计和推导。实验结果表明，基于超像素的CRF模型在得到较好分类结果的同时，极大地缩短了运行时间，提高了效率。

关键词: 条件随机场, 超像素, 均值漂移, 图像分类, 参数估计

Abstract: Concerning the high time complexity of inference and parameter estimation in graph model，the concept of superpixel was introduced into the Conditional Random Field (CRF)，and a superpixel-based CRF image classification method was proposed. This method first over segmented the image into small homogeneous regions which were called superpixels by using mean shift method. Then the graphical model was constructed with superpixels as nodes and the neighboring nodes as edges. The corresponding definition of CRF and the methods for parameter estimation and labeling inference were proposed and implemented. The experimental results show that better classification results are obtained by the superpixel-based CRF model. At the same time, running time is largely reduced.

Key words: Conditional Random Field (CRF), superpixel, mean shift, image classification, parameter estimation

中图分类号:

TP391.41

张微汪西莉. 基于超像素的条件随机场图像分类[J]. 计算机应用, 2012, 32(05): 1272-1275.

ZHANG Wei WANG Xi-li. Superpixel-based conditional random field for image classification[J]. Journal of Computer Applications, 2012, 32(05): 1272-1275.

参考文献

［1］LI S Z. Markov random field modeling in image analysis ［M］.3rd ed. Berlin:Springer, 2009.

［2］LAFFERTY J, MCCALLUM A, PEREIRA F. Conditional random fields: Probabilistic models for segmenting and labeling sequence data ［C］ // Proceedings of the 18th International Conference on Machine Learning. San Francisco: Morgan Kaufmann Publishers, 2001:282-289.

［3］ NEAPOLITAN R E. Learning Bayesian networks ［M］. Upper Saddle Riner,NJ,USA:Prentice Hall, 2004.

［4］DUDA R O, HART P E, STORK D G. Pattern classification ［M］2nd ed. Singapore: Wiley Interscience, 2001.

［5］BISHOP C M. Pattern recognition and machine learning ［M］. Berlin: Springer, 2006.

［6］SHI J B, MALIK J. Normalized cuts and image segmentation ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905.

［7］WANG S, SISKIND J M. Image segmentation with ratio cut ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(6):675-690.

［8］ CASELLES V, KIMMEL R, SAPIRO G. Geodesic active contours ［J］. International Journal of Computer Vision, 1997, 22(1):61-79.

［9］KASS M, WITKIN A, TERZOPOULOS D. Snakes: Active contour models ［J］. International Journal of Computer Vision, 1988, 1(4):321-331.
［10］WANG Y, LOE K F, WU J K. A dynamic conditional random field model for foreground and shadow segmentation ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28 (2): 279-289.

［11］HE X M, ZEMEL R S, CARREIRA-PERPINAN M A. Multiscale conditional random fields for image labeling ［C］ // Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2005: 695-702.

［12］KUMAR S, HEBERT M. Discriminative random fields: Adiscriminative framework for contextual interaction in classification ［C］// Proceedings of the 9th IEEE International Conference on Computer Vision. Washington, DC: IEEE Computer Society, 2003:1150-1157.

［13］REYNOLDS J, MURPHY K. Figure-ground segmentation using a hierarchical conditional random field ［C］// Proceedings of the 4th Canadian Conference on Computer and Robot Vision. Washington, DC: IEEE Computer Society, 2007:175-182.

［14］褚一平,张引,叶修梓，等.基于隐条件随机场的自适应视频分割算法［J］.自动化学报, 2007,33(12): 1252-1258.
［15］ TSECHPENAKIS G, METAXAS D. CoCRF deformable model: A geometric model driven by collaborative conditional random fields ［J］. IEEE Transactions on Image Processing, 2009, 18 (10): 2316-2329.

［16］REN X F, MALIK J. Learning a classification model forsegmentation ［C］// Proceedings of the 9th International Conference on Computer Vision. Washington, DC: IEEE Computer Society, 2003: 10-17.

［17］WEGNER J D, SOERGEL U, ROSENHAHN B. Segment-based building detection with conditional random fields ［C］// 2011 Joint Urban Remote Sensing Event.[S.l.]:IEEE,2011:205-208.

［18］ZHANG L. A unified probabilistic graphical model and its applica-tion to image segmentation ［D］.New York: Rensselaer Polytechnic Institute, 2009.

［19］COMANICIU D, MEER P. Mean shift: a robust approach toward feature space analysis ［J］.IEEE Transactions on Pattern Analysis and machine Intelligence, 2002, 24(5):603-619.

［20］李敏花,王春恒,肖柏华，等.一种基于条件随机场的复杂背景图像文本抽取方法［J］.模式识别与人工智能,2009,22(6):827-832.

［21］BESAG J. Statistical analysis of non-lattice data ［J］. Journal of the Royal Statistical Society, 1975, 24(3):179-195.

［22］MURPHY K P, WEISS Y, JORDAN M I. Loopy belief propagation for approximate inference: an empirical study ［C］ // Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence. San Francisco: Morgan Kaufmann Publishers,1999:467-475.

[1]	杨瑞, 钱晓军, 孙振强, 许振. 自然场景下多区域特征融合的混合航拍图像分割算法[J]. 计算机应用, 2021, 41(8): 2445-2452.
[2]	贾鹤鸣, 郎春博, 姜子超. 基于轻量级卷积神经网络的植物叶片病害识别方法[J]. 计算机应用, 2021, 41(6): 1812-1819.
[3]	韩艳茹, 尹梦晓, 覃子轩, 苏鹏, 杨锋. 图像和视频的低多边形渲染[J]. 计算机应用, 2021, 41(2): 504-510.
[4]	欧跃发, 杨鸣坤, 慕德俊, 柯捷, 马文涛. 基于广义最大Versoria准则的稀疏自适应滤波算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3325-3331.
[5]	许学斌, 张佳达, 刘伟, 路龙宾, 赵雨晴. 融合空间和通道特征的高精度乳腺癌分类方法[J]. 计算机应用, 2021, 41(10): 3025-3032.
[6]	汪虹余, 张彧, 杨恒, 穆楠. 基于蚁群优化算法的弱光图像显著性目标检测[J]. 计算机应用, 2021, 41(10): 2970-2978.
[7]	郑延斌, 韩梦云, 樊文鑫. 基于二维主成分分析与卷积神经网络的手写体汉字识别[J]. 计算机应用, 2020, 40(8): 2465-2471.
[8]	胡甜甜, 但雅波, 胡杰, 李想, 李少波. 基于注意力机制的Bi-LSTM结合CRF的新闻命名实体识别及其情感分类[J]. 计算机应用, 2020, 40(7): 1879-1883.
[9]	边小勇, 江沛龄, 赵敏, 丁胜, 张晓龙. 基于多分支神经网络模型的弱监督细粒度图像分类方法[J]. 计算机应用, 2020, 40(5): 1295-1300.
[10]	吴立人, 刘政浩, 张浩, 岑悦亮, 周维. 聚焦图像对抗攻击算法PS-MIFGSM[J]. 计算机应用, 2020, 40(5): 1348-1353.
[11]	郭志强, 胡永武, 刘鹏, 杨杰. 基于特征融合的室外天气图像分类[J]. 计算机应用, 2020, 40(4): 1023-1029.
[12]	张凯琳, 阎庆, 夏懿, 章军, 丁云. 基于焦点损失的半监督高光谱图像分类[J]. 计算机应用, 2020, 40(4): 1030-1037.
[13]	徐戈, 肖永强, 汪涛, 陈开志, 廖祥文, 吴运兵. 基于视觉误差与语义属性的零样本图像分类[J]. 计算机应用, 2020, 40(4): 1016-1022.
[14]	张盼盼, 李其申, 杨词慧. 基于轻量级分组注意力模块的图像分类算法[J]. 计算机应用, 2020, 40(3): 645-650.
[15]	史梦安, 陆振宇. 基于YOLO-tiny-RFB模型的电站旋钮开关状态识别[J]. 计算机应用, 2020, 40(12): 3679-3686.