{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:42:20Z","timestamp":1787323340715,"version":"build-2736575974"},"reference-count":69,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"3","funder":[{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["22\/06211-2"],"award-info":[{"award-number":["22\/06211-2"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["23\/00256-7"],"award-info":[{"award-number":["23\/00256-7"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["14\/50937-1"],"award-info":[{"award-number":["14\/50937-1"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["2020\/06950-4"],"award-info":[{"award-number":["2020\/06950-4"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Imaging Sci."],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>A classical approach to designing binary image operators is mathematical morphology (MM). We propose the Discrete Morphological Neural Networks (DMNN) for binary image analysis to represent W-operators and estimate them via machine learning. A DMNN architecture, which is represented by a morphological computational graph, is designed as in the classical heuristic design of morphological operators, in which the designer should combine a set of MM operators and Boolean operations based on prior information and theoretical knowledge. Then, once the architecture is fixed, instead of adjusting its parameters (i.e., structuring elements or maximal intervals) by hand, we propose a lattice descent algorithm (LDA) to train these parameters based on a sample of input and output images under the usual machine learning approach. We also propose a stochastic version of the LDA that is more efficient, is scalable, and can obtain small error in practical problems. The class represented by a DMNN can be quite general or specialized according to expected properties of the target operator, i.e., prior information, and the semantic expressed by algebraic properties of classes of operators is a differential relative to other methods. The main contribution of this paper is the merger of the two main paradigms for designing morphological operators: classical heuristic design and automatic design via machine learning. As a proof-of-concept, we apply the DMNN to recognize the boundary of digits with noise, and we discuss many topics for future research.<\/jats:p>","DOI":"10.1137\/23m1598477","type":"journal-article","created":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T10:09:19Z","timestamp":1721902159000},"page":"1650-1689","source":"Crossref","is-referenced-by-count":4,"title":["Discrete Morphological Neural Networks"],"prefix":"10.1137","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6087-4821","authenticated-orcid":true,"given":"Diego","family":"Marcondes","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77843 USA, and Department of Computer Science, Institute of Mathematics and Statistics, University of S\u00e3o Paulo, Brazil."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junior","family":"Barrera","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Institute of Mathematics and Statistics, University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2024,7,25]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","unstructured":"J. Angulo, Some open questions on morphological operators and representations in the deep learning era: A personal vision, in Proceedings of Discrete Geometry and Mathematical Morphology: 1st International Joint Conference, DGMM 2021, Uppsala, Sweden, Springer, 2021, pp. 3\u201319.","DOI":"10.1007\/978-3-030-76657-3_1"},{"key":"ref2","first-page":"59","volume":"3","author":"Angulo J.","year":"2003","journal-title":"Proc. GEOPRO"},{"key":"ref3","unstructured":"R. d. A. Ara\u00fajo, F. Madeiro, R. P. de Sousa, and L. F. Pessoa, Modular morphological neural network training via adaptive genetic algorithm for designing translation invariant operators, in Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, IEEE, 2006."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2017.07.014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2018.03.033"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.08.013"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1137\/0151091"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(93)90015-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1117\/1.482637"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1117\/12.260010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s40863-022-00303-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1117\/12.240717"},{"key":"ref13","first-page":"229","volume":"41","author":"Barrera J.","year":"2000","journal-title":"Fund. Inform."},{"key":"ref14","doi-asserted-by":"crossref","unstructured":"S. Beucher, Watersheds of functions and picture segmentation, in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 7, IEEE, 1982, pp. 1928\u20131931.","DOI":"10.1109\/ICASSP.1982.1171424"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(02)00217-9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/B:JMIV.0000026558.10581.e6"},{"key":"ref17","unstructured":"J. Clayden, mmand: Mathematical Morphology in Any Number of Dimensions, R package version 1.6.3. 2023, https:\/\/CRAN.R-project.org\/package=mmand."},{"key":"ref18","series-title":"SPIE 1769","first-page":"119","volume-title":"Image Algebra and Morphological Image Processing III","volume":"1992","author":"Davidson J. L."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF01189873"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1117\/12.18085"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"R. P. de Sousa, J. M. de Carvalho, F. M. de Assis, and L. F. Pessoa, Designing translation invariant operations via neural network training, in Proceedings of the International Conference on Image Processing, Vol. 1, IEEE, 2000, pp. 908\u2013911.","DOI":"10.1109\/ICIP.2000.901107"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.888358"},{"key":"ref23","doi-asserted-by":"crossref","unstructured":"N. Dimitriadis and P. Maragos, Advances in morphological neural networks: Training, pruning and enforcing shape constraints, in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2021, pp. 3825\u20133829.","DOI":"10.1109\/ICASSP39728.2021.9415123"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1117\/3.501104"},{"key":"ref25","first-page":"1997","volume":"20","author":"Elsken T.","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/e22040492"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107246"},{"key":"ref28","doi-asserted-by":"crossref","unstructured":"M. Grana and B. Raducanu, Some applications of morphological neural networks, in Proceedings of the International Joint Conference on Neural Networks, IEEE, 2001, pp. 2518\u20132523.","DOI":"10.1109\/IJCNN.2001.938763"},{"key":"ref29","unstructured":"R. Groenendijk, L. Dorst, and T. Gevers, MorphPool: Efficient Non-Linear Pooling & Unpooling in CNNs, preprint, arXiv:2211.14037, 2022."},{"key":"ref30","first-page":"14045","volume":"45","author":"Groenendijk R.","year":"2023","journal-title":"IEEE Trans. Pattern Anal."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106622"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.118"},{"key":"ref33","doi-asserted-by":"crossref","unstructured":"N. S. Hirata, J. Barrera, and E. R. Dougherty, Design of statistically optimal stack filters, in Proceedings of the XII Brazilian Symposium on Computer Graphics and Image Processing, IEEE, 1999, pp. 265\u2013274.","DOI":"10.1109\/SIBGRA.1999.805734"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/math9161854"},{"key":"ref35","unstructured":"N. S. T. Hirata, J. Barrera, R. Terada, E. R. Dougherty, H. Talbot, and R. Beare, The incremental splitting of intervals algorithm for the design of binary image operators, in Proceedings of the 6th ISMM, 2002, pp. 219\u2013228."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1117\/1.1327178"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1006\/rtim.2002.0291"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-1684(99)00162-0"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108893"},{"key":"ref40","doi-asserted-by":"crossref","unstructured":"F. D. Julca-Aguilar and N. S. Hirata, Image operator learning coupled with CNN classification and its application to staff line removal, in Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 1, IEEE, 2017, pp. 53\u201358.","DOI":"10.1109\/ICDAR.2017.18"},{"key":"ref41","doi-asserted-by":"crossref","unstructured":"D. Marcondes and J. Barrera, The lattice overparametrization paradigm for the machine learning of lattice operators, in International Conference on Discrete Geometry and Mathematical Morphology, Springer Nature Switzerland, Cham, 2024, pp. 204\u2013216.","DOI":"10.1007\/978-3-031-57793-2_16"},{"key":"ref42","doi-asserted-by":"crossref","unstructured":"D. Marcondes, M. Feldman, and J. Barrera, An algorithm to train unrestricted sequential discrete morphological neural networks, in International Conference on Discrete Geometry and Mathematical Morphology, Springer Nature Switzerland, Cham, 2024, pp. 178\u2013191.","DOI":"10.1007\/978-3-031-57793-2_14"},{"key":"ref43","volume-title":"Random Sets and Integral Geometry","author":"Matheron G.","year":"1974"},{"key":"ref44","volume-title":"Random Sets and Integral Geometry","author":"Matheron G.","year":"1975"},{"key":"ref45","doi-asserted-by":"crossref","unstructured":"R. Mondal, P. Purkait, S. Santra, and B. Chanda, Morphological networks for image de-raining, in Discrete Geometry for Computer Imagery: 21st IAPR International Conference, DGCI 2019, Marne-la-Vall\u00e9e, France, Proceedings 21, Springer, 2019, pp. 262\u2013275.","DOI":"10.1007\/978-3-030-14085-4_21"},{"key":"ref46","unstructured":"R. Mondal, S. Santra, S. S. Mukherjee, and B. Chanda, Morphological Network: How Far Can We Go with Morphological Neurons? preprint, arXiv:1901.00109, 2019."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.10.002"},{"key":"ref48","doi-asserted-by":"crossref","unstructured":"I. S. Montagner, R. Hirata, N. S. Hirata, and S. Canu, Kernel approximations for W-operator learning, in Proceedings of the 29th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), IEEE, 2016, pp. 386\u2013393.","DOI":"10.1109\/SIBGRAPI.2016.060"},{"key":"ref49","doi-asserted-by":"crossref","unstructured":"A. Monteiro da Silva and P. Sussner, A brief review and comparison of feedforward morphological neural networks with applications to classification, in Artificial Neural Networks-ICANN 2008: 18th International Conference, Prague, Czech Republic, Proceedings, Part II, 18, Springer, 2008, pp. 783\u2013792.","DOI":"10.1007\/978-3-540-87559-8_81"},{"key":"ref50","doi-asserted-by":"crossref","unstructured":"J. Pastore, A. Bouchet, M. Brun, and V. Ballarin, New windows based color morphological operators for biomedical image processing, J. Phys. Conf. Ser. 705, IOP Publishing, Bristol, UK, 2016, 012023.","DOI":"10.1088\/1742-6596\/705\/1\/012023"},{"key":"ref51","doi-asserted-by":"crossref","unstructured":"L. F. Pessoa and P. Maragos, Morphological\/rank neural networks and their adaptive optimal design for image processing, in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings, Vol. 6, IEEE, 1996, pp. 3398\u20133401.","DOI":"10.1109\/ICASSP.1996.550607"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(99)00157-0"},{"key":"ref53","unstructured":"R Core Team, R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing, Vienna, Austria, 2021, https:\/\/www.R-project.org\/."},{"key":"ref54","doi-asserted-by":"crossref","unstructured":"M. S. Reis, G. Estrela, C. E. Ferreira, and J. Barrera, Optimal Boolean lattice-based algorithms for the U-curve optimization problem, Inform. Sci., 471 (2019), pp. 97\u2013114.","DOI":"10.1016\/j.ins.2018.08.060"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2009.08.018"},{"key":"ref56","doi-asserted-by":"crossref","unstructured":"G. X. Ritter, L. Iancu, and G. Urcid, Morphological perceptrons with dendritic structure, in Proceedings of the 12th IEEE International Conference on Fuzzy Systems, Vol. 2, IEEE, 2003, pp. 1296\u20131301.","DOI":"10.1109\/FUZZ.2003.1206618"},{"key":"ref57","doi-asserted-by":"crossref","unstructured":"G. X. Ritter and P. Sussner, An introduction to morphological neural networks, in Proceedings of 13th International Conference on Pattern Recognition, Vol. 4, IEEE, 1996, pp. 709\u2013717.","DOI":"10.1109\/ICPR.1996.547657"},{"key":"ref58","unstructured":"S. Ruder, An Overview of Gradient Descent Optimization Algorithms, preprint, arXiv:1609.04747, 2016."},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2009.03.019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(89)90032-7"},{"key":"ref61","volume-title":"Image Analysis and Mathematical Morphology","volume":"1","author":"Serra J.","year":"1984"},{"key":"ref62","volume-title":"Image Analysis and Mathematical Morphology. Volume 2: Theoretical Advances","author":"Serra J.","year":"1988"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/BF01189221"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.10.031"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging9070139"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04512-7_7"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(96)00113-4"},{"key":"ref68","volume-title":"Statistical Learning Theory","volume":"3","author":"Vapnik V.","year":"1998"},{"key":"ref69","series-title":"SPIE 1445","first-page":"297","volume-title":"Medical Imaging V: Image Processing","author":"Vincent L. M.","year":"1991"}],"container-title":["SIAM Journal on Imaging Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/23M1598477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T13:56:36Z","timestamp":1787320596000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/23M1598477"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,25]]},"references-count":69,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1137\/23M1598477"],"URL":"https:\/\/doi.org\/10.1137\/23m1598477","relation":{},"ISSN":["1936-4954"],"issn-type":[{"value":"1936-4954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,25]]}}}