Image descriptors and their implementation on Android environment

• Grant number: 15/04920-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2015
• End date: April 30, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Léo Pini Magalhães
• Grantee: Marcelo Fernandes de Jesus
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

This activity is part of a Doctoral Project that intends on continuing the implementation of a Content Based Image Retrieval (CBIR) Environment. Once again, a study on Image Descriptors is being performed, this time aiming at the implementation and usage on Android environments. In a previous activity, special focus has been dedicated to the color based descriptor BIC - border/interior pixel classification, which is also going to be a subject in this project, being the previous results used as a source for comparison in regard to effectiveness and efficiency. Here, there will be made a study on color, texture and shape based description techniques/algorithms, aiming to give a comprehensive formation to the activity's protagonist. Likewise, the implementation will be executed on an Android environment as a form of introduction of the student to that technology. Initially, the activities will be centered around the developer environment, then ported to Tablet/Smartphone environment. A number of image databases - e.g. Caltech, Coil-100, Corel, ETH-80, MPEG7, MSRCORID, Pascal, Tattoo-Image-Base - is going to be used for evaluation and comparison of the implementations and results.