An Algorithm to Train Unrestricted Sequential Discrete Morphological Neural Networks

被引:2
作者
Marcondes, Diego [1 ,2 ]
Feldman, Mariana [1 ]
Barrera, Junior [1 ]
机构
[1] Univ Sao Paulo, Inst Math & Stat, Dept Comp Sci, Sao Paulo, Brazil
[2] Texas A&M Univ, Dept Elect & Comp Engn, College Stn, TX USA
来源
DISCRETE GEOMETRY AND MATHEMATICAL MORPHOLOGY, DGMM 2024 | 2024年 / 14605卷
基金
巴西圣保罗研究基金会;
关键词
discrete morphological neural networks; image processing; mathematical morphology; U-curve algorithms; stochastic lattice descent algorithm; OPERATIONS;
D O I
10.1007/978-3-031-57793-2_14
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
There have been attempts to insert mathematical morphology (MM) operators into convolutional neural networks (CNN), and the most successful endeavor to date has been the morphological neural networks (MNN). Although MNN have performed better than CNN in solving some problems, they inherit their black-box nature. Furthermore, in the case of binary images, they are approximations that loose the Boolean lattice structure of MM operators and, thus, it is not possible to represent a specific class of W-operators with desired properties. In a recent work, we proposed the Discrete Morphological Neural Networks (DMNN) for binary image transformation to represent specific classes of W-operators and estimate them via machine learning. We also proposed a stochastic lattice descent algorithm (SLDA) to learn the parameters of Canonical Discrete Morphological Neural Networks (CDMNN), whose architecture is composed only of operators that can be decomposed as the supremum, infimum, and complement of erosions and dilations. In this paper, we propose an algorithm to learn unrestricted sequential DMNN, whose architecture is given by the composition of general W-operators. We illustrate the algorithm in a practical example.
引用
收藏
页码:178 / 191
页数:14
相关论文
共 38 条
[1]  
Aouad T., 2023, ICCV 2023 INT C COMP
[2]   BINARY MORPHOLOGICAL NEURAL NETWORK [J].
Aouad, Theodore ;
Talbot, Hugues .
2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2022, :3276-3280
[3]   A morphological neural network for binary classification problems [J].
Araujo, Ricardo de A. ;
Oliveira, Adriano L. I. ;
Meira, Silvio .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2017, 65 :12-28
[4]   Differential evolution training algorithm for dendrite morphological neural networks [J].
Arce, Fernando ;
Zamora, Erik ;
Sossa, Humberto ;
Barron, Ricardo .
APPLIED SOFT COMPUTING, 2018, 68 :303-313
[5]   A fast Branch-and-Bound algorithm for U-curve feature selection [J].
Atashpaz-Gargari, Esmaeil ;
Reis, Marcelo S. ;
Braga-Neto, Ulisses M. ;
Barrera, Junior ;
Dougherty, Edward R. .
PATTERN RECOGNITION, 2018, 73 :172-188
[6]  
Barrera J., 2000, Fundamenta Informaticae, V41, P229
[7]   Set operations on closed intervals and their applications to the automatic programming of morphological machines [J].
Barrera, J ;
Salas, GP .
JOURNAL OF ELECTRONIC IMAGING, 1996, 5 (03) :335-352
[8]   From Mathematical Morphology to machine learning of image operators [J].
Barrera, Junior ;
Hashimoto, Ronaldo F. ;
Hirata, Nina S. T. ;
Hirata, R., Jr. ;
Reis, Marcelo S. .
SAO PAULO JOURNAL OF MATHEMATICAL SCIENCES, 2022, 16 (01) :616-657
[9]  
da Silva AM, 2008, LECT NOTES COMPUT SC, V5164, P783, DOI 10.1007/978-3-540-87559-8_81
[10]  
DAVIDSON JL, 1992, P SOC PHOTO-OPT INS, V1769, P119, DOI 10.1117/12.60637