User Tools

Site Tools


projects:year4:15.9

15.9 - Learn to Segment by Operational Object Segmentation Networks

Project - Summary

Objectives:

  • To develop novel methods for supervised salient object segmentation task that provides many industrial applications such as camera auto-focusing, advertisement assessment, etc.
  • To provide general trainable segmentation systems to the industrial partners such that each partner can train its own network in accordance with their application of interest.
  • To research novel Neural Network structures and to investigate the feasibility and effectiveness of the proposed models for salient object segmentation task.

Project - Team

Team Member Role Email Phone Number Academic Site/IAB
Moncef Gabbouj PI moncef.gabbouj@tuni.fi +358 400 736613 Tampere University
Serkan Kiranyaz PI serkan.kiranyaz@tuni.fi 97 43 063 5600 Tampere University
Caglar Aytekin PhD Student Not available Not available Tampere University

Project - Impact and Uses/Benefits

The Convolutional Segmentation Networks and Convolutional Kernel Networks combined with Quantum Cuts provide two trainable segmentation networks that have the capacity to achieve state-of-the-art performance in salient object segmentation. The impact of such a generalized segmentation network is the fact that, given the ground truths, an industrial partner can train this system for any segmentation task that it desires. Such systems can serve the companies that are dealing with computer vision problems such as camera auto-focusing, advertisement assessment, face segmentation and many other applications basically including any object/region segmentation task.

Project - Deep Dive

Project - Documents

FilenameFilesizeLast modified
15.9_year_4_ip_letter_combined.pdf371.0 KiB2019/08/22 11:50
15.9_year_4_executive_summary.pdf287.8 KiB2019/08/22 11:50
15.9_year_4_final_report.pdf1.0 MiB2019/08/22 10:33
projects/year4/15.9.txt · Last modified: 2021/06/02 14:40 by sally.johnson