With the development of hand-held photographic devices, document images in unconstrained environments can be captured in high-speed and high-resolution. It will be more efficient to process the text information of multiple documents simultaneously. In this paper, we propose a multi-document detection approach. It can estimate the amount of documents and also detect their accurate locations via iteratively searching the four corners and their direction maps from individual document in the image. Even for slightly occluded documents, the proposed method can infer the hidden corner positions. The model is designed to jointly learn the corner categories, locations and their directions in attentional regions via two branches of the same sequential prediction process. The association score is calculated based on the them between two corner connections. The graph theory, considering corners as nodes and association scores as edges, is applied to get the quadrangle for each document in image. For evaluation, we collect a Multi-Doc data set which contains 2,200 document images in various natural scenes. We show that the baseline model trained on this collected data and bench-mark SmartDoc 2015 can detect both single and multiple documents accurately and effectively. (c) 2021 Elsevier B.V. All rights reserved.
展开▼
