Development and assessment of novel and accurate methods in shape analysis and computer vision

• Grant number: 99/12765-2
• Support Opportunities: Research Projects - Thematic Grants
• Start date: February 01, 2001
• End date: July 31, 2005
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Luciano da Fontoura Costa
• Grantee: Luciano da Fontoura Costa
• Host Institution: Instituto de Física de São Carlos (IFSC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Pesquisadores principais: Roberto Marcondes Cesar Junior
• Associated scholarship(s): 03/02869-2 - Computerized nuclear morphometry of ductal carcinoma "in situ" and its relation to the development of breast cancer, BP.IC; 02/02504-1 - Dynamic shape analysis, BP.PD

Abstract

Before image processing and vision techniques can be effectively applied in a truly comprehensive fashion, the involved techniques and implementations have to reach high performance standards. A particularly promising possibility for achieving such a relevant and challenging objective consists in comprehensive and integrated approaches to the typical related problems, including shape representation and its use as subsidy for visual analysis, classification, and synthesis. The inherent advantage in such approaches is that the specific demands and qualities of the processes at each subsequent stage (for instance representation and classification) can be properly identified and complemented. At the same time, it becomes essential to devise and apply formal performance validation and comparative assessment procedures, capable of properly characterizing the potential and short comings of the considered and developed techniques. The current project can be divided into the following two principal parts: (a) development and validation of new representations of visual information,(particularly shapes) and their respective use in analysis, classification and synthesis of 2D, 2.5D and 3D shapes, with special emphasis on scale-space approaches based on differential geometry, partial differential equations, signal processing, and skeletonization; and (b) developments and applications in the areas of tunelling microscopy (2.5D images), face recognition, and industrial parts identification. Additional research topics also to be considered in the planned developments include techniques for multiscale image processing and analysis (such as wavelets and mathematical morphology), digital video processing and motion analysis. (AU)

Scientific publications

(29)

(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)

CAMPITELI, MONICA GUIMARAES; COMIN, CESAR HENRIQUE; COSTA, LUCIANO DA FONTOURA; BABU, M. MADAN; CESAR, JR., ROBERTO MARCONDES. A methodology to infer gene networks from spatial patterns of expression - an application to fluorescence in situ hybridization images. MOLECULAR BIOSYSTEMS, v. 9, n. 7, p. 1926-1930, 2013. (11/22639-8, 05/00587-5, 99/12765-2)

COSTA, L. DA F.; BARBOSA, M. S.; MANOEL, E. T. M.; STREICHER, J.; MÜLLER, G. B.. Mathematical characterization of three-dimensional gene expression patterns. Bioinformatics, v. 20, n. 11, p. 1653-1662, Jul. 2004. (02/02504-1, 99/12765-2)

RIS‚ M.; BARRERA‚ J.; MARTINS JR‚ D.C.. U-curve: A branch-and-bound optimization algorithm for U-shaped cost functions on Boolean lattices applied to the feature selection problem. PATTERN RECOGNITION, v. 43, n. 3, p. 557-568, 2010. (01/09401-0, 99/12765-2)

CAMPOS BIANCHI‚ A.G.; DOS SANTOS‚ M.F.; HAMASSAKI BRITTO‚ D.E.; COSTA‚ L.F.. Inferring shape evolution. PATTERN RECOGNITION LETTERS, v. 24, n. 7, p. 1005-1014, 2003. (01/09047-2, 99/12765-2)

COSTA‚ L.F.. The hierarchical backbone of complex networks. Physical Review Letters, v. 93, n. 9, p. 98702, 2004. (99/12765-2)

DA FONTOURA COSTA‚ L.; VIANA‚ M.P.; BELETTI‚ M.E.. Complex channel networks of bone structure. Applied Physics Letters, v. 88, p. 033903, 2006. (99/12765-2)

RODRIGUES‚ E.P.; BARBOSA‚ M.S.; COSTA‚ L.F.. Self-referred approach to lacunarity. Physical Review E, v. 72, n. 1, p. 016707, 2005. (99/12765-2, 02/02504-1)

DA FONTOURA COSTA‚ L.; DIAMBRA‚ L.. Topographical maps as complex networks. Physical Review E, v. 71, n. 2, p. 021901, 2005. (99/12765-2)

DA FONTOURA COSTA‚ L.; MANOEL‚ E.T.M.. A percolation approach to neural morphometry and connectivity. NEUROINFORMATICS, v. 1, n. 1, p. 65-80, 2003. (99/12765-2)

DIAMBRA‚ L.; DA FONTOURA COSTA‚ L.. Pattern formation in a gene network model with boundary shape dependence. Physical Review E, v. 73, n. 3, p. 031917, 2006. (99/12765-2)

DA FONTOURA COSTA‚ L.. Biological sequence analysis through the one-dimensional percolation transform and its enhanced version. Bioinformatics, v. 21, n. 5, p. 608-616, 2005. (99/12765-2)

DA FONTOURA COSTA‚ L.. Learning about knowledge: A complex network approach. Physical Review E, v. 74, n. 2, p. 026103, 2006. (99/12765-2)

DA FONTOURA COSTA‚ L.; ROCHA‚ F.; ARAÚJO DE LIMA‚ S.M.. Statistical mechanics characterization of neuronal mosaics. Applied Physics Letters, v. 86, n. 9, p. 093901-093901, 2005. (99/12765-2)

DA F COSTA‚ L.; DOS REIS‚ S.F.; ARANTES‚ R.A.T.; ALVES‚ A.C.R.; MUTINARI‚ G.C.. Biological shape analysis by digital curvature. PATTERN RECOGNITION, v. 37, n. 3, p. 515-524, 2004. (99/12765-2)

DA FONTOURA COSTA‚ L.. Reinforcing the resilience of complex networks. Physical Review E, v. 69, n. 6, p. 066127, 2004. (99/12765-2)

COSTA‚ L.F.. Estimating derivatives and curvature of open curves. PATTERN RECOGNITION, v. 35, n. 11, p. 2445-2451, 2002. (99/12765-2)

BELETTI‚ ME; COSTA‚ L.F.; VIANA‚ MP. A computational approach to characterization of bovine sperm chromatin alterations. BIOTECHNIC & HISTOCHEMISTRY, v. 79, n. 1, p. 17-23, 2004. (99/12765-2)

DA S TORRES‚ R.; FALCAO‚ AX; DA F COSTA‚ L.. A graph-based approach for multiscale shape analysis. PATTERN RECOGNITION, v. 37, n. 6, p. 1163-1174, 2004. (99/12765-2)

CESAR‚ R.M.; BENGOETXEA‚ E.; BLOCH‚ I.; LARRAÑAGA‚ P.. Inexact graph matching for model-based recognition: Evaluation and comparison of optimization algorithms. PATTERN RECOGNITION, v. 38, n. 11, p. 2099-2113, 2005. (99/12765-2)

DIAMBRA‚ L.; COSTA‚ L.F.. Complex networks approach to gene expression driven phenotype imaging. Bioinformatics, v. 21, n. 20, p. 3846-3851, 2005. (99/12765-2)

BARBOSA‚ M.S.; DA FONTOURA COSTA‚ L.; DE SOUSA BERNARDES‚ E.. Neuromorphometric characterization with shape functionals. Physical Review E, v. 67, n. 6, p. 061910, 2003. (99/12765-2)

DA FONTOURA COSTA‚ L.. L-percolations of complex networks. Physical Review E, v. 70, n. 5, p. 056106, 2004. (99/12765-2)

COSTA‚ L.F.; CINTRA‚ L.C.; SCHUBERT‚ D.. An integrated approach to the characterization of cell movement. Cytometry Part A, v. 68, n. 2, p. 92-100, 2005. (99/12765-2)

DA FONTOURA COSTA‚ L.; ROCHA‚ F.; DE LIMA‚ S.M.A.. Characterizing polygonality in biological structures. Physical Review E, v. 73, n. 1, p. 011913, 2006. (99/12765-2)

GONCALVES, WESLEY NUNES; DA SILVA, NUBIA ROSA; COSTA, LUCIANO DA FONTOURA; BRUNO, ODEMIR MARTINEZ. Texture recognition based on diffusion in networks. INFORMATION SCIENCES, v. 364, p. 51-71, OCT 10 2016. (11/21467-9, 10/08614-0, 05/00587-5, 11/01523-1, 99/12765-2)

DA F COSTA‚ L.; RODRIGUES‚ F.A.; TRAVIESO‚ G.. Protein domain connectivity and essentiality. Applied Physics Letters, v. 89, n. 17, p. 174101-174101, 2006. (99/12765-2)

COSTA, L. DA F.; COUPEZ, V.; BARBOSA, M. S.. A direct approach to neuronal connectivity. PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, v. 341, n. 1-2, p. 618-628, Oct. 2004. (02/02504-1, 99/12765-2)

COSTA, L. DA F.; BARBOSA, M. S.. An analytical approach to neuronal connectivity. European Physical Journal B, v. 42, n. 4, p. 573-580, Oct. 2004. (99/12765-2)

VIANA, MATHEUS PALHARES; TANCK, ESTHER; BELETTI, MARCELO EMILIO; COSTA, LUCIANO DA FONTOURA. Modularity and robustness of bone networks. MOLECULAR BIOSYSTEMS, v. 5, n. 3, p. 255-261, 2009. (05/00587-5, 07/50882-9, 99/12765-2)