In this paper we propose a method for logo recognition based on Convolutional Neural Networks, instead of the commonly used keypoint-based approaches. The method involves the selection of candidate subwindows using an unsupervised segmentation algorithm, and the SVM-based classification of such candidate regions using features computed by a CNN. For training the neural network we augment the training set with artificial transformations, while for classification we exploit a query expansion strategy to increase the recall rate. Experiments were performed on a publicly-available dataset that was also corrupted in order to investigate the robustness of the proposed method with respect to blur, noise and lossy compression.
Bianco, S., Buzzelli, M., Mazzini, D., Schettini, R. (2015). Logo recognition using CNN features. In Image Analysis and Processing — ICIAP 2015 (18th International Conference, Genoa, Italy, September 7-11, 2015), Proceedings, Part II (pp.438-448). Springer Verlag [10.1007/978-3-319-23234-8_41].
Logo recognition using CNN features
BIANCO, SIMONEPrimo
;BUZZELLI, MARCO;MAZZINI, DAVIDE
Penultimo
;SCHETTINI, RAIMONDOUltimo
2015
Abstract
In this paper we propose a method for logo recognition based on Convolutional Neural Networks, instead of the commonly used keypoint-based approaches. The method involves the selection of candidate subwindows using an unsupervised segmentation algorithm, and the SVM-based classification of such candidate regions using features computed by a CNN. For training the neural network we augment the training set with artificial transformations, while for classification we exploit a query expansion strategy to increase the recall rate. Experiments were performed on a publicly-available dataset that was also corrupted in order to investigate the robustness of the proposed method with respect to blur, noise and lossy compression.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
