Filters








6,451 Hits in 5.1 sec

OPFython: A Python-Inspired Optimum-Path Forest Classifier [article]

Gustavo Henrique de Rosa, João Paulo Papa, Alexandre Xavier Falcão
2020 arXiv   pre-print
A recent graph-inspired classifier, known as the Optimum-Path Forest, has proven to be a state-of-the-art technique, comparable to Support Vector Machines and even surpassing it in some tasks.  ...  This paper proposes a Python-based Optimum-Path Forest framework, denoted as OPFython, where all of its functions and classes are based upon the original C language implementation.  ...  Acknowledgments The authors are grateful to São Paulo Research Foundation (FAPESP) grants #2013/07375-0, #2014/12236-1, #2017/25908-6, #2018/15597-6, and #2019/02205-5, as well as CNPq grants #307066/2017  ... 
arXiv:2001.10420v2 fatcat:m7vzh7oqfbhuvnjsrgaqvff6yy

Supervised pattern classification based on optimum-path forest

J. P. Papa, A. X. Falcão, C. T. N. Suzuki
2009 International journal of imaging systems and technology (Print)  
By choice of the graph model and connectivity function, one can devise other optimum-path forest classifiers.  ...  We also propose a general algorithm to learn from errors on an evaluation set without increasing the training set, and show the advantages of our method with respect to SVM, ANN-MLP, and k-NN classifiers  ...  Acknowledgments The authors thank Paulo Miranda (IC-UNICAMP) and Nelson Mascarenhas (UFSCar) for their previous contributions and the financial support from CNPq and FAPESP.  ... 
doi:10.1002/ima.20188 fatcat:5vj54hj2xbgzje6ikgwzs5ijbe

Improving the Accuracy of the Optimum-Path Forest Supervised Classifier for Large Datasets [chapter]

César Castelo-Fernández, Pedro J. de Rezende, Alexandre X. Falcão, João Paulo Papa
2010 Lecture Notes in Computer Science  
In this work, a new approach for supervised pattern recognition is presented which improves the learning algorithm of the Optimum-Path Forest classifier (OPF), centered on detection and elimination of  ...  Identification of outliers is based on a penalty computed for each sample in the training set from the corresponding number of imputable false positive and false negative classification of samples.  ...  Conclusions In this work, a novel learning algorithm was presented that improves the time performance and accuracy of the supervised Optimum Path Forest classifier.  ... 
doi:10.1007/978-3-642-16687-7_62 fatcat:n37oq2rwwfc7fm6ehffsxsvfry

Precipitates Segmentation from Scanning Electron Microscope Images through Machine Learning Techniques [chapter]

João P. Papa, Clayton R. Pereira, Victor H. C. de Albuquerque, Cleiton C. Silva, Alexandre X. Falcão, João Manuel R. S. Tavares
2011 Lecture Notes in Computer Science  
Hastelloy C-276 alloy: Support Vector Machines, Optimum-Path Forest, Self Organizing Maps and a Bayesian classifier.  ...  Hence, its automatic identification by image processing and machine learning techniques may lead to reliable and efficient assessments on the materials.  ...  and Technological Development (FUNCAP) for providing financial support through a DCR grant to UNIFOR for third the author.  ... 
doi:10.1007/978-3-642-21073-0_40 fatcat:6ntex4z2hjffblexlgy66x5ype

Supervised Learning Using Local Analysis in an Optimal-Path Forest

Willian Paraguassu Amorim, Marcelo Henriques de Carvalho
2012 2012 25th SIBGRAPI Conference on Graphics, Patterns and Images  
In this paper, we present an OPF-LA (Optimal Path Forest-Local Analysis), a new learning model proposal.  ...  It employs the main ideas of an OPF classifier, suggesting a new procedure in the data training phase.  ...  A recent research that explores this relationship has obtained promising results for supervised and unsupervised learning using the OPF (Optimal Path Forest) classifier [4] [5] .  ... 
doi:10.1109/sibgrapi.2012.53 dblp:conf/sibgrapi/AmorimC12 fatcat:htdvzhlsnne75gluv4jge2y6vm

An incremental linear-time learning algorithm for the Optimum-Path Forest classifier [article]

Moacir Ponti, Mateus Riva
2016 arXiv   pre-print
We present a classification method with incremental capabilities based on the Optimum-Path Forest classifier (OPF).  ...  Our algorithm includes new instances in an OPF in linear-time, while keeping similar accuracies when compared with the original quadratic-time model.  ...  Introduction The optimum-path forest (OPF) classifier [1] a classification method that can be used to build simple, multiclass and parameter independent classifiers.  ... 
arXiv:1604.03346v5 fatcat:guma4e7mqbhodehyxmgj7czzqy

A New Parallel Training Algorithm for Optimum-Path Forest-Based Learning [chapter]

Aldo Culquicondor, César Castelo-Fernández, João Paulo Papa
2017 Lecture Notes in Computer Science  
In this work, we present a new parallel-driven approach to speed up Optimum-Path Forest (OPF) training phase.  ...  In addition, we show how to make OPF up to five times faster for training using a simple parallel-friendly data structure, which can achieve the same accuracy results to the ones obtained by traditional  ...  Acknowledgments The authors would like to thank Capes PROCAD grant 2966/2014, CNPq grants #306166/2014-3 and #470571/2013-6, FAPESP grant #2014/16250-9 and Universidad Católica San Pablo (UCSP) for their  ... 
doi:10.1007/978-3-319-52277-7_24 fatcat:j46yb2r2wne4tk6r4pjcucla3a

Improving semi-supervised learning through optimum connectivity

Willian P. Amorim, Alexandre X. Falcão, João P. Papa, Marcelo H. Carvalho
2016 Pattern Recognition  
We present a semi-supervised learning approach that connects unlabeled and labeled samples as nodes of a minimum-spanning tree and partitions the tree into an optimum-path forest rooted at the labeled  ...  The annotation of large data sets by a classifier is a problem whose challenge increases as the number of labeled samples used to train the classifier reduces in comparison to the number of unlabeled samples  ...  Acknowledgment The authors are grateful to Fundect-MS, CNP q grants: #303673/ 2010-9, #479070/2013-0, #302970/2014-2, #303182/2011-3, #470571/2013-6 and #306166/2014-3 and FAPESP grants: #2013/ 20387-7  ... 
doi:10.1016/j.patcog.2016.04.020 fatcat:rs3iksjrjzfhhbexcx5k2nhmn4

Efficient supervised optimum-path forest classification for large datasets

João P. Papa, Alexandre X. Falcão, Victor Hugo C. de Albuquerque, João Manuel R.S. Tavares
2012 Pattern Recognition  
We have tried to circumvent the problem by reducing it into the fast computation of an optimum-path forest (OPF) in a graph derived from the training samples.  ...  The forest is a classifier which assigns to any new sample the label of its most strongly connected root. This methodology has been successful with different graph topologies and learning techniques.  ...  Acknowledgments The authors thank the financial support from FAPESP (grants 2009/16206-1 and 2007/52015-0) and CNPq (grant 481556/2009-5).  ... 
doi:10.1016/j.patcog.2011.07.013 fatcat:gf6lbvpbn5a2jkilpev4jmbj6m

On the Training Patterns Pruning for Optimum-Path Forest [chapter]

João P. Papa, Alexandre X. Falcão
2009 Lecture Notes in Computer Science  
The OPF classifier reduces the problem of pattern recognition to a computation of an optimum-path forest in the feature space induced by a graph, creating discrete optimal partitions, which are optimum-path  ...  In that way, we present here a pruning algorithm for the OPF classifier that learns the most irrelevant samples and eliminate them from the training set, without compromising the classifier's accuracy.  ...  Acknowledgements We would like to acknowledge the grants from projects BioCore (CNPq 550890/ 2007-6), CNPq 302617/2007-8 and FAPESP 07/52015-0.  ... 
doi:10.1007/978-3-642-04146-4_29 fatcat:ejzmzipd2zawrfit2knz7cjhpa

A Novel Approach for Optimum-Path Forest Classification Using Fuzzy Logic

Renato W. R. De Souza, Joao Vitor Chaves De Oliveira, Leandro A. Passos, Weiping Ding, Joao P Papa, Victor Albuquerque
2019 IEEE transactions on fuzzy systems  
Some years ago, a new framework for both supervised, semi-supervised, and unsupervised learning named Optimum-Path Forest (OPF) was proposed with competitive results in several applications, besides comprising  ...  In this paper, we propose the Fuzzy Optimum-Path Forest, an improved version of the standard OPF classifier that learns the samples' membership in an unsupervised fashion, which are further incorporated  ...  ACKNOWLEDGEMENTS The authors are grateful to CNPq 304315/2017-  ... 
doi:10.1109/tfuzz.2019.2949771 fatcat:hsy4vnx2ibfzjar57rs53ynhvq

Incorporating multiple distance spaces in optimum-path forest classification to improve feedback-based learning

André Tavares da Silva, Jefersson Alex dos Santos, Alexandre Xavier Falcão, Ricardo da S. Torres, Léo Pini Magalhães
2012 Computer Vision and Image Understanding  
Keywords: Content-based image retrieval Optimum-path forest classifiers Composite descriptor Genetic programming Multi-scale parameter search Image pattern analysis a b s t r a c t In content-based image  ...  This work improves the retrieval process by incorporating multiple distance spaces in a recent method based on optimum-path forest (OPF) classification.  ...  The OPF classifier uses the Image Foresting Transform algorithm [22] , which is a generalization of Dijkstra's algorithm for multiple sources and more general path-cost functions in a graph.  ... 
doi:10.1016/j.cviu.2011.12.001 fatcat:w7jt7ti7org4xmj4gp5ffuqppa

Improving Accuracy and Speed of Optimum-Path Forest Classifier Using Combination of Disjoint Training Subsets [chapter]

Moacir P. Ponti, João P. Papa
2011 Lecture Notes in Computer Science  
The Optimum-Path Forest (OPF) classifier is a recent and promising method for pattern recognition, with a fast training algorithm and good accuracy results.  ...  Given a fixed number of subsets, the algorithm chooses random samples, without replacement, from the original training set. Each subset accuracy is improved by a learning procedure.  ...  Regarding OPF implementation we used the LibOPF [12] , a free library for the implementation of optimum-path forest-based classifiers.  ... 
doi:10.1007/978-3-642-21557-5_26 fatcat:ry244znry5hihaeo3dcl5vltua

SMS Spam Filtering Through Optimum-Path Forest-Based Classifiers

Dheny Fernandes, Kelton A.P. da Costa, Tiago A. Almeida, Joao Paulo Papa
2015 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA)  
In this paper, we introduced the Optimum-Path Forest classifier to the context of spam filtering in SMS messages, as well as we compared it against with some state-of-the-art supervised pattern recognition  ...  In the past years, SMS messages have shown to be a profitable revenue to the cell-phone industries, being one of the most used communication systems to date.  ...  ACKNOWLEDGMENTS The authors thank to Capes, CNPq grants #306166/2014-3 and #470571/2013-6, as well as FAPESP grants #2014/16250-9 and #2015/00801-9 for the financial support.  ... 
doi:10.1109/icmla.2015.71 dblp:conf/icmla/FernandesCAP15 fatcat:llsyk4jfwnbg7nlnr64wi2b42i

RECENT ADVANCES ON OPTIMUM-PATH FOREST FOR DATA CLASSIFICATION: SUPERVISED, SEMI-SUPERVISED, AND UNSUPERVISED LEARNING [chapter]

João Paulo Papa, Willian Paraguassu Amorim, Alexandre Xavier Falcão, João Manuel R. S. Tavares
2015 Handbook of Pattern Recognition and Computer Vision  
In this book chapter, we revisited the Optimum-Path Forest (OPF) classifier, which has been evaluated over the last years in a number of applications that consider supervised, semi-supervised and unsupervised  ...  learning problems.  ...  Acknowledgments The authors would like to thank all support given by several research foundations during the last years under the following grants: Capes, FAPESP #2009/16206-1, FAPESP #2014/16250-9, CNPq  ... 
doi:10.1142/9789814656535_0006 fatcat:avne5qqksjdhfcisuuekpsz3bu
« Previous Showing results 1 — 15 out of 6,451 results