Advanced search
Start date
Betweenand

Superpixel generation based on Optimum-Path Forest image segmentation

Grant number: 15/01186-6
Support type:Research Grants - Visiting Researcher Grant - International
Duration: June 16, 2015 - July 31, 2015
Field of knowledge:Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
Principal Investigator:Alexandre Xavier Falcão
Grantee:Alexandre Xavier Falcão
Visiting researcher: Ananda Shankar Chowdhury
Visiting researcher institution: Jadavpur University, India
Home Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

Superpixel based research has gained much importance in the field of computer vision over the last decade. Results from algorithms based on superpixels show promise in typical computer vision problems like segmentation, tracking, and, depth estimation. However, generation of superpixels still remains a challenging problem. Many graph-based as well as gradient ascent-based methods are applied in the past for segmentation of superpixels. Lately, SLIC approach for superpixel generation has yielded better performance than the other existing techniques. The main objective of this proposal is to improve the SLIC based segmentation of superpixels by replacing the k-means clustering algorithm with the Optimum Path Forest (OPF) method. Some theoretical improvements of the OPF algorithm will also be investigated, especially for large datasets, to further enhance the quality of the superpixels. Finally, we will show improved segmentation performances on medical images as well as on videos with the newly generated improved superpixels. (AU)

Scientific publications
(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)
VARGAS-MUNOZ, JOHN E.; CHOWDHURY, ANANDA S.; ALEXANDRE, EDUARDO B.; GALVAO, FELIPE L.; VECHIATTO MIRANDA, PAULO A.; FALCAO, ALEXANDRE X. An Iterative Spanning Forest Framework for Superpixel Segmentation. IEEE Transactions on Image Processing, v. 28, n. 7, p. 3477-3489, JUL 2019. Web of Science Citations: 0.

Please report errors in scientific publications list by writing to: cdi@fapesp.br.