RT Journal Article
T1 Place and Object Recognition by CNN-Based COSFIRE Filters
A1 Lopez-Antequera, Manuel
A1 Vallina, Maria Leyva
A1 Strisciuglio, Nicola
A1 Petkov, Nicolai
K1 COSFIRE filter
K1 CNN
K1 object recognition
K1 place recognition
K1 Vessel delineation
AB COSFIRE filters are an effective means for detecting and localizing visual patterns. In contrast to a convolutional neural network (CNN), such a filter can be configured by presenting a single training example and it can be applied on images of any size. The main limitation of COSFIRE filters so far was the use of only Gabor and DoGs contributing filters for the configuration of a COSFIRE filter. In this paper, we propose to use a much broader class of contributing filters, namely filters defined by intermediate CNN representations. We apply our proposed method on the MNIST data set, on the butterfly data set, and on a garden data set for place recognition, obtaining accuracies of 99.49%, 96.57%, and 89.84%, respectively. Our method outperforms a CNN-baseline method in which the full CNN representation at a certain layer is used as input to an SVM classifier. It also outperforms traditional non-CNN methods for the studied applications. In the case of place recognition, our method outperforms NetVLAD when only one reference image is used per scene and the two methods perform similarly when many reference images are used.
PB Ieee-inst electrical electronics engineers inc
SN 2169-3536
YR 2019
FD 2019-01-01
LK http://hdl.handle.net/10668/18969
UL http://hdl.handle.net/10668/18969
LA en
DS RISalud
RD Apr 18, 2025