This paper studies the problem of document image classification. More specifically, we address the classification of documents composed of few textual information and complex background (such as identity documents). Unlike most existing systems, the proposed approach simultaneously locates the document and recognizes its class. The latter is defined by the document nature (passport, ID, etc.), emission country, version, and the visible side (main or back). This task is very challenging due to unconstrained capturing conditions, sparse textual information, and varying components that are irrelevant to the classification, e.g. photo, names, address, etc.First, a base of document models is created from reference images. We show that training images are not necessary and only one reference image is enough to create a document model. Then, the query image is matched against all models in the base. Unknown documents are rejected using an estimated quality based on the extracted document. The matching process is optimized to guarantee an execution time independent from the number of document models. Once the document model is found, a more accurate matching is performed to locate the document and facilitate information extraction. Our system is evaluated on several datasets with up to 3042 real documents (representing 64 classes) achieving an accuracy of 96.6%.
This paper presents an approach for spotting and accurately localizing identity documents in the wild. Contrary to blind solutions that often rely on borders and corners detection, the proposed approach requires a classification a priori along with a list of predefined models. The matching and accurate localization are performed using specific ID document features. This process is especially difficult due to the intrinsic variable nature of ID models (text fields, multi-pass printing with offset, unstable layouts, added artifacts, blinking security elements, nonrigid materials). We tackle the problem by putting different combinations of features in competition within a multi-hypothesis exploration where only the best document quadrilateral candidate is retained thanks to a custom visual similarity metric. The idea is to find, in a given context, at least one feature able to correctly crop the document. The proposed solution has been tested and has shown its benefits on both the MIDV-500 academic dataset and an industrial one supposedly more representative of a real-life application.Best selected hypothesis repatriation in docs % (-are ablated hypothesis)Accepted crops >0.9 Jaccard dist Keypoints 3D trans.
In this paper, we present a new approach using conditional random fields (CRFs) to localize tabular components in an unconstrained handwritten compound document. Given a line-segmented document, the extraction of table is considered as a labeling task that consists in assigning a label to each line: TableRow label for a line which belongs to a table and LineText label for a line which belongs to a text block. To perform the labeling task, we use a CRF model to combine two classifiers: a local classifier which assigns a label to the line based on local features and a contextual classifier which uses features taking into account the neighborhood. The CRF model gives the global conditional probability of a given labeling of the line considering the outputs of the two classifiers. A set of chemistry documents is used for the evaluation of this approach. The obtained results are around 88% of table lines correctly detected.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.