Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Enlarging the discriminability of bag-of-words representations with deep convolutional features

: Manger, Daniel; Willersinn, Dieter

Volltext urn:nbn:de:0011-n-4873657 (901 KByte PDF)
MD5 Fingerprint: 79575f3ed2fce6d73e867eb33ad1c960
© IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Erstellt am: 27.3.2018

7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017 : Montreal, Canada November 28 - December 1
Piscataway, NJ: IEEE, 2017
ISBN: 978-1-5386-1841-7
ISBN: 978-1-5386-1842-4
ISBN: 978-1-5386-1843-1
6 S.
International Conference on Image Processing Theory, Tools and Applications (IPTA) <7, 2017, Montreal>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()
Content-based Image Retrieval; Bag-of-Words; Spatial Context of local Features; CNN features; 2D index

In this work, we propose an extension of established image retrieval models which are based on the bag-of-words representation, i.e. on models which quantize local features such as SIFT to leverage an inverted file indexing scheme for speedup. Since the quantization of local features impairs their discriminability, the ability to retrieve those database images which show the same object or scene to a given query image is decreasing with the growing number of images in the database. We address this issue by extending a quantized local feature with information from its local spatial neighborhood incorporating a representation based on pooling features from deep convolutional neural network layer outputs. Using four public datasets, we evaluate both the discriminability of the representation and its overall performance in a large-scale image retrieval setup.