Multimodal deep networks for text and image-based document classification
This addresses the need for more accurate document classification in archival and administrative settings, though it is incremental by building on existing deep learning approaches.
The paper tackles the problem of fine-grained document classification by combining visual and textual information, achieving a 3% accuracy improvement over image-only methods on Tobacco3482 and RVL-CDIP datasets using a new multimodal neural network.
Classification of document images is a critical step for archival of old manuscripts, online subscription and administrative procedures. Computer vision and deep learning have been suggested as a first solution to classify documents based on their visual appearance. However, achieving the fine-grained classification that is required in real-world setting cannot be achieved by visual analysis alone. Often, the relevant information is in the actual text content of the document. We design a multimodal neural network that is able to learn from word embeddings, computed on text extracted by OCR, and from the image. We show that this approach boosts pure image accuracy by 3% on Tobacco3482 and RVL-CDIP augmented by our new QS-OCR text dataset (https://github.com/Quicksign/ocrized-text-dataset), even without clean text information.