Randomized neural network based descriptors for shape classification

被引:14
作者
de Mesquita Sa Junior, Jarbas Joaci [1 ,2 ]
Backes, Andre Ricardo [3 ]
Bruno, Odemir Martinez [1 ]
机构
[1] Univ Sao Paulo, Sao Carlos Inst Phys, POB 369, BR-13560970 Sao Carlos, SP, Brazil
[2] Univ Fed Ceara, Dept Comp Engn, Campus Sobral,Rua Estanislau Frota 563, BR-62010560 Sobral, CE, Brazil
[3] Univ Fed Uberlandia, Sch Comp Sci, Av Joao Naves de Avila 2121, BR-38408100 Uberlandia, MG, Brazil
基金
巴西圣保罗研究基金会;
关键词
Shape classification; Randomized neural network; Contour-based analysis; RECOGNITION; SEGMENTATION; FOURIER; SNAKES; SYSTEM; GRAPH;
D O I
10.1016/j.neucom.2018.05.099
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Shape analysis is a very important field in computer vision. This work presents a novel and highly discriminative shape analysis method based on the weights of a Randomized Neural Network (RNN). Two approaches are proposed to extract the contour signature: Neighborhood approach uses the distance of each contour pixel and its immediate neighboring pixels and Contour portion approach, which uses metrics computed from contour sections to model the shape as RNN. We also proposed a signature that combines the feature vectors resulting from both approaches, thus resulting in a set of features tolerant to affine transformations, such as rotation and scale. We compared our approach with other shape analysis methods in 6 different shapes datasets. We calculated the accuracy as measure performance and obtained 97.98%, 99.07%, 84.67%, 87.67%, 88.92% and 80.58% for Kimia, Fish, Leaf, Rotated Leaf, Scaled Leaf and Noised Leaf datasets, respectively. The achieved performance of our method surpassed the results of several compared methods in most of these datasets, thus proving that our proposed signature can be applied successfully in shape analysis problems. (C) 2018 Elsevier B.V. All rights reserved.
引用
收藏
页码:201 / 209
页数:9
相关论文
共 50 条
[11]   Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry [J].
Cao, Jiale ;
Pang, Yanwei ;
Li, Xuelong .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 25 (12) :5538-5551
[12]  
Gonzalez R.C., 2002, DIGITAL IMAGE PROCES
[13]   Histogram of Radon transform with angle correlation matrix for distortion invariant shape descriptor [J].
Hasegawa, Makoto ;
Tabbone, Salvatore .
NEUROCOMPUTING, 2016, 173 :24-35
[14]   Support Vector Shape: A Classifier-Based Shape Representation [J].
Hien Van Nguyen ;
Porikli, Fatih .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (04) :970-982
[15]   VISUAL-PATTERN RECOGNITION BY MOMENT INVARIANTS [J].
HU, M .
IRE TRANSACTIONS ON INFORMATION THEORY, 1962, 8 (02) :179-&
[16]   Angular Pattern and Binary Angular Pattern for Shape Retrieval [J].
Hu, Rong-Xiang ;
Jia, Wei ;
Ling, Haibin ;
Zhao, Yang ;
Gui, Jie .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2014, 23 (03) :1118-1127
[17]   Extreme learning machine: Theory and applications [J].
Huang, Guang-Bin ;
Zhu, Qin-Yu ;
Siew, Chee-Kheong .
NEUROCOMPUTING, 2006, 70 (1-3) :489-501
[18]   SNAKES - ACTIVE CONTOUR MODELS [J].
KASS, M ;
WITKIN, A ;
TERZOPOULOS, D .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1987, 1 (04) :321-331
[19]  
Lehmer Derrick H, 1951, Annu. Comput. Lab. Harvard Univ., V26, P141
[20]   Insights into randomized algorithms for neural networks: Practical issues and common pitfalls [J].
Li, Ming ;
Wang, Dianhui .
INFORMATION SCIENCES, 2017, 382 :170-178