
Training CNNs with image patches for object localisation
Author(s) -
Orhan S.,
Bastanlar Y.
Publication year - 2018
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2017.4725
Subject(s) - artificial intelligence , training (meteorology) , computer vision , computer science , object (grammar) , image (mathematics) , computer graphics (images) , pattern recognition (psychology) , geography , meteorology
Recently, convolutional neural networks (CNNs) have shown great performance in different problems of computer vision including object detection and localisation. A novel training approach is proposed for CNNs to localise some animal species whose bodies have distinctive patterns such as leopards and zebras. To learn characteristic patterns, small patches which are taken from different body parts of animals are used to train models. To find object location, in a test image, all locations are visited in a sliding window fashion. Crops are fed into trained CNN and their classification scores are combined into a heat map. Later on, heat maps are converted to bounding box estimates for varying confidence scores. The localisation performance of the patch‐based training approach is compared with Faster R‐CNN – a state‐of‐the‐art CNN‐based object detection and localisation method. Experimental results reveal that the patch‐based training outperforms Faster R‐CNN, especially for classes with distinctive patterns.