Format

Send to

Choose Destination
Sensors (Basel). 2018 Apr 25;18(5). pii: E1329. doi: 10.3390/s18051329.

Textile Retrieval Based on Image Content from CDC and Webcam Cameras in Indoor Environments.

Author information

1
Department of Electrical, Systems and Automation, Universidad de León, 24071 León, Spain. ogaro@unileon.es.
2
Department of Electrical, Systems and Automation, Universidad de León, 24071 León, Spain. ealeg@unileon.es.
3
Researcher at INCIBE (Spanish National Cybersecurity Institute), 24005 León, Spain. ealeg@unileon.es.
4
Department of Mechanical, Computer Science and Aerospace Engineering, Universidad de León, 24071 León, Spain. l.fernandez@unileon.es.
5
Researcher at INCIBE (Spanish National Cybersecurity Institute), 24005 León, Spain. l.fernandez@unileon.es.
6
Department of Electrical, Systems and Automation, Universidad de León, 24071 León, Spain. efidf@unileon.es.
7
Researcher at INCIBE (Spanish National Cybersecurity Institute), 24005 León, Spain. efidf@unileon.es.
8
Department of Electrical, Systems and Automation, Universidad de León, 24071 León, Spain. ssai@unileon.es.
9
Researcher at INCIBE (Spanish National Cybersecurity Institute), 24005 León, Spain. ssai@unileon.es.

Abstract

Textile based image retrieval for indoor environments can be used to retrieve images that contain the same textile, which may indicate that scenes are related. This makes up a useful approach for law enforcement agencies who want to find evidence based on matching between textiles. In this paper, we propose a novel pipeline that allows searching and retrieving textiles that appear in pictures of real scenes. Our approach is based on first obtaining regions containing textiles by using MSER on high pass filtered images of the RGB, HSV and Hue channels of the original photo. To describe the textile regions, we demonstrated that the combination of HOG and HCLOSIB is the best option for our proposal when using the correlation distance to match the query textile patch with the candidate regions. Furthermore, we introduce a new dataset, TextilTube, which comprises a total of 1913 textile regions labelled within 67 classes. We yielded 84.94% of success in the 40 nearest coincidences and 37.44% of precision taking into account just the first coincidence, which outperforms the current deep learning methods evaluated. Experimental results show that this pipeline can be used to set up an effective textile based image retrieval system in indoor environments.

KEYWORDS:

content-based image retrieval; textile localization; textile retrieval; texture description; texture retrieval; visual sensors

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center