Skip to content

Latest commit

 

History

History
16 lines (9 loc) · 1.16 KB

README.md

File metadata and controls

16 lines (9 loc) · 1.16 KB

HS-Architecture-Comparison

Abstract

Given their success, both qualitative and quantitative, Deep Neural Networks have been used to approach classification and segmentation problems for images, especially during these last few years where it has been possible to design computers with sufficient capacity to make quick and efficient experiments. In this work, we will study the use of two Convolutional Neural Networks (CNNs) to segment the ground of a land section of Maspalomas’ area using an image takenby the flight of an airplane. The comparison will be made in terms of computational cost, complexity and results that will be obtained while testing different algorithms, loss functions or optimizers and also while tuning some other parameters. The results will also be compared with a past work done with the same dataset but another methodology (SVM).

Links

  • Link to the thesis

  • Link to presentation

Contact