A New Automatic Parameter Setting Method of a Simplified PCNN for Image Segmentation

被引：177

作者：

Chen, Yuli ^{[1
,2
]}

Park, Sung-Kee ^{[2
]}

Ma, Yide ^{[1
]}

Ala, Rajeshkanna ^{[2
]}

机构：

[1] Lanzhou Univ, Sch Informat Sci & Engn, Lanzhou 730000, Gansu, Peoples R China

[2] Korea Inst Sci & Technol, Ctr Cognit Robot Res, Robot Syst Div, Seoul 136791, South Korea

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2011年 / 22卷 / 06期

基金：

美国国家科学基金会;

关键词：

Automatic parameter setting; dynamic property; general formulae; image segmentation; optimal histogram threshold; simplified pulse coupled neural network; standard deviation; static property; sub-intensity range; COUPLED NEURAL-NETWORKS; ROTATION; LINKING; SCALE;

D O I：

10.1109/TNN.2011.2128880

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An automatic parameter setting method of a simplified pulse coupled neural network (SPCNN) is proposed here. Our method successfully determines all the adjustable parameters in SPCNN and does not need any training and trials as required by previous methods. In order to achieve this goal, we try to derive the general formulae of dynamic threshold and internal activity of the SPCNN according to the dynamic properties of neurons, and then deduce the sub-intensity range expression of each segment based on the general formulae. Besides, we extract information from an input image, such as the standard deviation and the optimal histogram threshold of the image, and attempt to build a direct relation between the dynamic properties of neurons and the static properties of each input image. Finally, the experimental segmentation results of the gray natural images from the Berkeley Segmentation Dataset, rather than synthetic images, prove the validity and efficiency of our proposed automatic parameter setting method of SPCNN.

引用

页码：880 / 892

页数：13

共 39 条

[1] Automatic design of pulse coupled neurons for image segmentation [J].

Berg, Henrik ;

Olsson, Roland ;

Lindblad, Thomas ;

Chilo, Jose .

NEUROCOMPUTING, 2008, 71 (10-12) :1980-1993

[2]

BI Y, 2004, ADV NEURAL NETWORKS, V3174, P199

[3] Feature Linking via Synchronization among Distributed Assemblies: Simulations of Results from Cat Visual Cortex [J].

Eckhorn, R. ;

Reitboeck, H. J. ;

Arndt, M. ;

Dicke, P. .

NEURAL COMPUTATION, 1990, 2 (03) :293-307

[4]

Eckhorn R., 1989, MODELS BRAIN FUNCTIO, P255, DOI DOI 10.1139/W00-039

[5] The intersecting cortical model in image processing [J].

Ekblad, U ;

Kinser, JM ;

Atmer, J ;

Zetterlund, N .

NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 2004, 525 (1-2) :392-396

[6]

Gu XD, 2005, IEEE IJCNN, P1836

[7] Image shadow removal using pulse coupled neural network [J].

Gu, XD ;

Yu, DH ;

Zhang, LM .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (03) :692-698

[8] Feature extraction using unit-linking pulse coupled neural network and its applications [J].

Gu, Xiaodong .

NEURAL PROCESSING LETTERS, 2008, 27 (01) :25-41

[9]

Johnson J. L., 1994, J AM COLL RADIOL, V55, P47

[10] Overview of pulse coupled neural network (PCNN) special issue [J].

Johnson, JL ;

Padgett, ML ;

Omidvar, O .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (03) :461-463

← 1 2 3 4 →