Max-Tree: theory, algorithms and applications

• Grant number: 13/23514-0
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: April 01, 2014
• End date: May 31, 2017
• Field of knowledge: Engineering - Electrical Engineering
• Principal Investigator: Roberto de Alencar Lotufo
• Grantee: Roberto Medeiros de Souza
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated scholarship(s): 15/12127-0 - Max-trees applied to medical images segmentation, BE.EP.DR

Abstract

The Max-Tree represents a grey-scale image through a hierarchical relationship of itslevel connected components. It is a structure that can be built and processed in real time, andit has been successfully used in many applications, such as location and tracking of objects,image segmentation, image filtering, 3D visualization, among others.This Ph.D. research project is the continuation of a M.Sc. program, where theMaximal Max-Tree Simplification (MMS) filter along with its possible applications wereproposed. The main goal of the current research is to investigate further the Max-Tree, whichwe believe is a tool with potential for solving many practical problems with competitiveresults, but that is still not much explored by the scientific community. This investigation hastwo principal research approaches. The first involves studying the Max-Tree for automaticsegmentation, and compare its performance with other methods, like the WatershedTransform and automatic and dynamic thresholding methods, such as Otsu and Niblack. Thesecond approach will study new methodologies to detect, characterize and extract invariantattributes that consider the hierarchical relationship of the Max-Tree nodes, and its applicationto matching and content based image retrieval problems. These new methodologies will becompared to state-of-the-art tools, such as SIFT, SURF and MSER.

Scientific publications

(10)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

GHAMISI, PEDRAM; SOUZA, ROBERTO; BENEDIKTSSON, JON ATLI; RITTNER, LETICIA; LOTUFO, ROBERTO; ZHU, XIAO XIANG. Hyperspectral Data Classification Using Extended Extinction Profiles. IEEE Geoscience and Remote Sensing Letters, v. 13, n. 11, p. 1641-1645, NOV 2016. (13/23514-0, 15/12127-0, 13/07559-3)

SOUZA, ROBERTO; RITTNER, LETICIA; MACHADO, RUBENS; LOTUFO, ROBERTO. iamxt: Max-tree toolbox for image processing and analysis. SOFTWAREX, v. 6, p. 81-84, 2017. (13/07559-3, 13/23514-0)

SOUZA, ROBERTO; LUCENA, OESLLE; GARRAFA, JULIA; GOBBI, DAVID; SALUZZI, MARINA; APPENZELLER, SIMONE; RITTNER, LETICIA; FRAYNE, RICHARD; LOTUFO, ROBERTO. An open, multi-vendor, multi-field-strength brain MR dataset and analysis of publicly available skull stripping methods agreement. NeuroImage, v. 170, n. SI, p. 482-494, APR 15 2018. (13/23514-0, 13/07559-3, 16/18332-8)

TAVARES, LUIS A.; SOUZA, ROBERTO M.; RITTNER, LETICIA; MACHADO, RUBENS C.; LOTUFO, ROBERTO A.; IEEE. A max-tree simplification proposal and applications for the interactive max-tree visualization tool. 2016 29TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), v. N/A, p. 8-pg., 2016-01-01. (13/07559-3, 13/23514-0)

GHAMISI, PEDRAM; SOUZA, ROBERTO; BENEDIKTSSON, JON ATLI; ZHU, XIAO XIANG; RITTNER, LETICIA; LOTUFO, ROBERTO A.. Extinction Profiles for the Classification of Remote Sensing Data. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, v. 54, n. 10, p. 5631-5645, OCT 2016. (15/12127-0, 13/07559-3, 13/23514-0)

RODRIGUES, LIVIA; RITTNER, LETICIA; LOTUFO, ROBERTO; SOUZA, ROBERTO; FRAYNE, RICHARD; IEEE. Common Carotid Artery Lumen Segmentation from Cardiac Cycle-resolved Cine Fast Spin Echo Magnetic Resonance Imaging. 2017 30TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), v. N/A, p. 8-pg., 2017-01-01. (13/23514-0, 13/07559-3)

GHAMISI, PEDRAM; RASTI, BEHNOOD; ZHU, XIAO X.; IEEE. FEATURE FUSION OF HYPERSPECTRAL AND LIDAR DATA USING EXTINCTION PROFILES AND TOTAL VARIATION. 2017 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), v. N/A, p. 4-pg., 2017-01-01. (15/12127-0, 13/23514-0)

GHAMISI, PEDRAM; SOUZA, ROBERTO; RITTNER, LETICIA; BENEDIKTSSON, JON A.; LOTUFO, ROBERTO; ZHU, XIAO X.; IEEE. EXTINCTION PROFILES: A NOVEL APPROACH FOR THE ANALYSIS OF REMOTE SENSING DATA. 2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), v. N/A, p. 4-pg., 2016-01-01. (15/12127-0, 13/23514-0)

SOUZA, ROBERTO; LUCENA, OESLLE; GARRAFA, JULIA; GOBBI, DAVID; SALUZZI, MARINA; APPENZELLER, SIMONE; RITTNER, LETICIA; FRAYNE, RICHARD; LOTUFO, ROBERTO. An open, multi-vendor, multi-field-strength brain MR dataset and analysis of publicly available skull stripping methods agreement. NeuroImage, v. 170, p. 13-pg., 2018-04-15. (13/07559-3, 13/23514-0, 16/18332-8)

GHAMISI, PEDRAM; SOUZA, ROBERTO; BENEDIKTSSON, JON A.; ZHU, XIAO XIANG; RITTNER, LETICIA; LOTUFO, ROBERTO; IEEE. EXTENDED EXTINCTION PROFILE FOR THE CLASSIFICATION OF HYPERSPECTRAL IMAGES. 2016 8TH WORKSHOP ON HYPERSPECTRAL IMAGE AND SIGNAL PROCESSING: EVOLUTION IN REMOTE SENSING (WHISPERS), v. N/A, p. 4-pg., 2016-01-01. (15/12127-0, 13/23514-0)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

SOUZA, Roberto Medeiros de. Árvore máxima: teoria, algoritmos e aplicações. 2017. Doctoral Thesis - Universidade Estadual de Campinas (UNICAMP). Faculdade de Engenharia Elétrica e de Computação Campinas, SP.