A segmentation-free method for image retrieval and pattern spotting in historical documents using convolutional features

This paper describes a new segmentation-free method for retrieving images and spotting patterns in historical document image collections. The proposed method needs no training on the target domain, characterizing a problem-independent approach. For this purpose, the query and the document image represented by feature maps extracted using intermediate layers of a pre-trained Fully Convolutional Network are submitted to a cross-correlation process. The produced similarity heatmap is used to locate the query occurrences on the document page. A robust experimental protocol using three datasets shows promising results on image retrieval and pattern spotting. The experiments conducted on the public DocExplore dataset demonstrated that the proposed method could improve the mAP by 69.1% for the spotting task and 21% for the image retrieval task compared to the state-of-the-art. Additional experiments on image retrieval using the Horae dataset and logo spotting using the Tobacco800 dataset confirmed the high generalization capability of the proposed method.