Sorry, you need to enable JavaScript to visit this website.

Machine-Assisted Annotation of Forensic Imagery

Citation Author(s):
Sara Mousavi, Ramin Nabati, Megan Kleeschulte, Dawnie Steadman, Audris Mockus
Submitted by:
Sara Mousavi
Last updated:
16 September 2019 - 10:28am
Document Type:
Poster
Document Year:
2019
Event:
Presenters:
Audris Mockus
Paper Code:
3417

Abstract

Image collections, if critical aspects of image content are exposed, can spur research and practical applications in many domains. Supervised machine learning may be the only feasible way to annotate very large collections. However, leading approaches rely on large samples of completely and accurately annotated images. In the case of a large forensic collection that we are aiming to annotate, neither the complete annotation nor the large training samples can be feasibly produced. We, therefore, investigate ways to assist manual annotation efforts done by forensic experts. We present a method that can propose both images and areas within an image likely to contain desired classes. Evaluation of the method with human annotators showed highly accurate classification and reasonable segmentation accuracy that was strongly affected by transfer learning.
We hope this effort can be helpful in other domains that require weak segmentation and have limited availability of qualified annotators.

up
0 users have voted:

Comments

The rest of the authors are: Ramin Nabati, Megan Kleeschulte, Dawnie Steadman, Audris Mockus

Files

SaraMousaviICIP19Poster.pdf

(288)