Large scale tattoo localization

This paper examines the use of several popular object detection frameworks, namely Fast-RCNN, Faster-RCNN, and the more recent real-time object detection system, YOLO. The data utilized in this paper was collected from Flickr to more accurately represent images that could be found in the electronic...

Full description

Saved in:
Bibliographic Details
Main Author: Ng, Jing Nee
Other Authors: Kong Wai-Kin Adams
Format: Final Year Project
Language:English
Published: 2017
Subjects:
Online Access:http://hdl.handle.net/10356/70231
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-70231
record_format dspace
spelling sg-ntu-dr.10356-702312023-03-03T20:58:14Z Large scale tattoo localization Ng, Jing Nee Kong Wai-Kin Adams School of Computer Science and Engineering DRNTU::Engineering::Computer science and engineering This paper examines the use of several popular object detection frameworks, namely Fast-RCNN, Faster-RCNN, and the more recent real-time object detection system, YOLO. The data utilized in this paper was collected from Flickr to more accurately represent images that could be found in the electronic devices of potential suspects. A total of 90,000 images were used, and split into 4 experiments of 10,000, 20,000, 40,000, and 90,000 images. The VGG_CNN_M_1024 model achieved average precisions (AP)1 of 51.02% and 61.03% for both Fast-RCNN and Faster-RCNN respectively. The PVANet model achieved an AP of 69.15% on Faster-RCNN. Lastly, the YOLO model achieved an AP of 60.60%. All the best APs for each model were attained on the largest dataset, Flickr90k. The trained models were then tested on the NIST database of 2,212 images from the tattoo similarity use case (original, uncropped version), achieving an AP of 97.34% using the PVANet model trained on Flickr90k. Another set of 3,847 images were acquired from NIST’s background tattoo images (original, uncropped version). This set of images achieved an AP of 85.07%. Bachelor of Engineering (Computer Science) 2017-04-17T08:44:09Z 2017-04-17T08:44:09Z 2017 Final Year Project (FYP) http://hdl.handle.net/10356/70231 en Nanyang Technological University 52 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Ng, Jing Nee
Large scale tattoo localization
description This paper examines the use of several popular object detection frameworks, namely Fast-RCNN, Faster-RCNN, and the more recent real-time object detection system, YOLO. The data utilized in this paper was collected from Flickr to more accurately represent images that could be found in the electronic devices of potential suspects. A total of 90,000 images were used, and split into 4 experiments of 10,000, 20,000, 40,000, and 90,000 images. The VGG_CNN_M_1024 model achieved average precisions (AP)1 of 51.02% and 61.03% for both Fast-RCNN and Faster-RCNN respectively. The PVANet model achieved an AP of 69.15% on Faster-RCNN. Lastly, the YOLO model achieved an AP of 60.60%. All the best APs for each model were attained on the largest dataset, Flickr90k. The trained models were then tested on the NIST database of 2,212 images from the tattoo similarity use case (original, uncropped version), achieving an AP of 97.34% using the PVANet model trained on Flickr90k. Another set of 3,847 images were acquired from NIST’s background tattoo images (original, uncropped version). This set of images achieved an AP of 85.07%.
author2 Kong Wai-Kin Adams
author_facet Kong Wai-Kin Adams
Ng, Jing Nee
format Final Year Project
author Ng, Jing Nee
author_sort Ng, Jing Nee
title Large scale tattoo localization
title_short Large scale tattoo localization
title_full Large scale tattoo localization
title_fullStr Large scale tattoo localization
title_full_unstemmed Large scale tattoo localization
title_sort large scale tattoo localization
publishDate 2017
url http://hdl.handle.net/10356/70231
_version_ 1759855278906408960