计算机科学 ›› 2016, Vol. 43 ›› Issue (9): 289-294.doi: 10.11896/j.issn.1002-137X.2016.09.058

• 图形图像与模式识别 • 上一篇    下一篇

基于非监督特征学习的兴趣点检测算法

周来恩,王晓丹   

  1. 空军工程大学防空反导学院 西安710051,空军工程大学防空反导学院 西安710051
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金:基于多特征融合和集成学习的多目标识别技术研究(61273275)资助

Unsupervised Feature Learning Based Interest Point Detection Algorithm

ZHOU Lai-en and WANG Xiao-dan   

  • Online:2018-12-01 Published:2018-12-01

摘要: 由于兴趣点是图像中的基础、关键特征,因此兴趣点检测是图像配准、图像检索以及图像识别的关键步骤。基于兴趣点对于图像特征响应较为强烈的特性,结合非监督特征学习算法可以自主地从无标签的样本中提取特征的思想,提出了UFL-ID兴趣点检测算法。该算法无监督学习了图像的底层特征,对特征进行信息量和各向同性的评价,并利用特征的卷积响应及评价参数寻找图像中的兴趣点。与其他常见的兴趣点检测算法的对比实验表明,该算法具有良好的重复性与抗噪能力。

关键词: 机器学习,非监督特征学习,自动编码器,兴趣点检测,特征提取

Abstract: Interest point is of great importance in digital image processing as a kind of critical feature at low level.So the interest point detection is the committed step in image registration,image retrieval and image recognition.In this paper,an unsupervised feature learning based interest point detection (UFL-ID) was presented based on the fact that interest points have stronger feature convolution response than others.The new UFL-based interest point detection algorithm firstly learns low level features in digital images,evaluates the information content and isotropy of learned features,and finally uses features and its evaluation to find interest points.The comparison result demonstrates that using UFL produces great improvements of repeatability and anti-noise property.

Key words: Machine learning,Unsupervised feature learning,Auto-encoder,Interest point detection,Feature detection

[1] Moravec H P.Towards automatic visual obstacle avoidance[C]∥Proc.5th Int.Joint Conf.on Artif.Intell.,Cambridge:MA,1977
[2] Harris C,Stephens M.A combined corner and edge detector[C]∥Proc.4th Alvey Vision Conf..Mancheste,1988:147-151
[3] Smith S M,Brady J M.Susan-a new approach to low level ima-ge processing[J].International Journal of Computer Vision,1997,3(1):45-78
[4] Zhang X,Wang H,Hong M,et al.Robust image corner detection based on scale evolution difference of planar curves[J].Pattern Recognit.Lett.,2009,30(1):449-455
[5] Luo Xiao-hui,Li Jian-wei.DOG Model-Based Detector of Corner[J].Computer Engineering and Applications,2003(11):87-99(in Chinese) 罗晓晖,李见为.双高斯差模型用于角点检测研究[J].计算机工程与应用,2003(11):87-99
[6] Rosten E,Porter R,Drummond T.Faster and better:a machine learning approach to corner detection[J].IEEE Trans.Pattern.Anal.Mach.Intell.,2010,32(1):105-119
[7] Dias P G T,Kassim A A,Srinivasan V.A neural network based corner detection method[C]∥Proceedings of the IEEE International Conference on Neural Networks (ICNN’95).IEEE,1995:2116-2120
[8] Sun Wei,Yang Xuan.Image corner detection using topologylearning[J].Journal of China Universities of Posts and Telecommunications,2010,17(6):101-105
[9] Prudent Y,Ennaji A.An Incremental Growing Neural GasLearns Topologies[C]∥Proceedings of International Joint Conference on Neural Networks.2005(2):1211-1216
[10] Goodfellow I,Le Q,Saxe A,et al.Measuring invariances in deep networks[J].Neural Information Processing Systems,2009,22:646-654
[11] Wagner R,Thom M,Schweiger R,et al.Learning Convolutional Neural Networks From Few Samples[C]∥International Joint Conference on Neural Networks (IJCNN).Dallas,Texas,USA,2013:1-7
[12] Rumelhart D E,Hinton G E,Williams R J.Learning representations by back-propagating errors[J].Neurocomputing:Foundations of Research,1988,323(6088):696-699
[13] Olshausen B A,Field D J.Sparse coding of sensory inputs[J].Current Opinion in Neurobiology,2004,4(4):481-487
[14] Mairal J,Bach F,Ponce J,et al.Supervised dictionary learning[C]∥Proceedings of the Advances in Neural Information Processing Systems (NIPS).2009:1033-1040
[15] Schmid C,Mohr R,Bauckhage C.Evaluation of interest pointdetectors[J].International Journal of Computer Vision,2000,37(2):151-172
[16] Zanchettin C,Ludermir Teresa B,A lmeida Leandro M.Hybrid Training Method for MLP:Optimization of Architecture and Training[J].IEEE Transactions on Systems Man And Cybernetics Part B-Cybernetics,2011,41(4):1097-1109
[17] Sun Jian-ye.Learning algorithm and hidden node selectionscheme for local coupled feedforward neural network classifier[J].Neurocomputing,2012,9(3):158-163

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!