This paper presents a novel approach for image retrieval and pattern spotting in document image collections. The manual feature engineering is avoided by learning a similarity-based representation using a Siamese Neural Network trained on a previously prepared subset of image pairs from the ImageNet dataset. The learned representation is used to provide the similarity-based feature maps used to find relevant image candidates in the data collection given an image query. A robust experimental protocol based on the public Tobacco800 document image collection shows that the proposed method compares favorably against state-of-the-art document image retrieval methods, reaching 0.94 and 0.83 of mean average precision (mAP) for retrieval and pattern spotting (IoU=0.7), respectively. Besides, we have evaluated the proposed method considering feature maps of different sizes, showing the impact of reducing the number of features in the retrieval performance and time-consuming.
@article{arxiv.1906.09513,
title = {Image Retrieval and Pattern Spotting using Siamese Neural Network},
author = {Kelly L. Wiggers and Alceu S. Britto and Laurent Heutte and Alessandro L. Koerich and Luiz S. Oliveira},
journal= {arXiv preprint arXiv:1906.09513},
year = {2019}
}