Home News About Us Contact Contributors Disclaimer Privacy Policy Help FAQ

Home
Search
Quick Search
Advanced
Fulltext
Browse
Collections
Persons
My eDoc
Session History
Login
Name:
Password:
Documentation
Help
Support Wiki
Direct access to
document ID:


          Institute: MPI für medizinische Forschung     Collection: Abteilung Biomedizinische Optik     Display Documents



ID: 546034.0, MPI für medizinische Forschung / Abteilung Biomedizinische Optik
Convolutional networks can learn to generate affinity graphs for image segmentation
Translation of Title:Convolutional networks can learn to generate affinity graphs for image segmentation
Authors:Turaga, Srinivas C.; Murray, Joseph F.; Jain, VViren; Roth, Fabian; Helmstaedter, Moritz; Briggman, Kevin; Denk, Winfried; Seung, H. Sebastian
Language:English
Date of Publication (YYYY-MM-DD):2010-02-01
Title of Journal:Neural Comput
Journal Abbrev.:Neural Comput
Volume:22
Issue / Number:2
Start Page:511
End Page:538
Review Status:Peer-review
Audience:Experts Only
Intended Educational Use:No
Abstract / Description:Many image segmentation algorithms first generate an affinity graph and then partition it. We present a machine learning approach to computing an affinity graph using a convolutional network (CN) trained using ground truth provided by human experts. The CN affinity graph can be paired with any standard partitioning algorithm and improves segmentation accuracy significantly compared to standard hand−designed affinity functions.

We apply our algorithm to the challenging 3D segmentation problem of reconstructing neuronal processes from volumetric electron microscopy (EM) and show that we are able to learn a good affinity graph directly from the raw EM images. Further, we show that our affinity graph improves the segmentation accuracy of both simple and sophisticated graph partitioning algorithms.

In contrast to previous work, we do not rely on prior knowledge in the form of hand−designed image features or image preprocessing. Thus, we expect our algorithm to generalize effectively to arbitrary image types.
Last Change of the Resource (YYYY-MM-DD):--
External Publication Status:published
Document Type:Article
Communicated by:Wulf Kaiser
Affiliations:MPI für medizinische Forschung/Abteilung Biomedizinische Optik
Identifiers:LOCALID:7561
URI:http%3A%2F%2Fwww.mitpressjournals.org%2Fdoi%2Fpdf%...
URI:http%3A%2F%2Fwww.mitpressjournals.org%2Fdoi%2Ffull...
URI:http%3A%2F%2Fwww.mitpressjournals.org%2Fdoi%2Fabs%...
Full Text:
Sorry, no privileges
The scope and number of records on eDoc is subject to the collection policies defined by each institute - see "info" button in the collection browse view.