Hand-designed local image descriptors vs. Off-the-shelf CNN-based features for texture classification: An experimental comparison
View/ Open
Published version
Embargoed until: 5555-01-01
Embargoed until: 5555-01-01
Volume
76
Pagination
1 - 10
ISBN-13
9783319594798
DOI
10.1007/978-3-319-59480-4_1
ISSN
2190-3018
Metadata
Show full item recordAbstract
© Springer International Publishing AG 2018. Convolutional Neural Networks have proved extremely successful in object classification applications; however, their suitability for texture analysis largely remains to be established. We investigate the use of pre-trained CNNs as texture descriptors by tapping the output of the last fully connected layer, an approach that has proved its effectiveness in other domains. Comparison with classical descriptors based on signal processing or statistics over a range of standard databases suggests that CNNs may be more effective where the intra-class variability is large. Conversely, classical approaches may be preferable where classes are well defined and homogeneous.