Abstract: Handwritten document images can be highly affected by degradation for different reasons: Paper ageing, daily-life scenarios (wrinkles, dust, etc.), bad scanning process and so on. These artifacts raise many readability issues for current Handwritten Text Recognition (HTR) algorithms and severely devalue their efficiency. In this paper, we propose an end to end architecture based on Generative Adversarial Networks (GANs) to recover the degraded documents into a and form. Unlike the most well-known document binarization methods, which try to improve the visual quality of the degraded document, the proposed architecture integrates a handwritten text recognizer that promotes the generated document image to be more readable. To the best of our knowledge, this is the first work to use the text information while binarizing handwritten documents. Extensive experiments conducted on degraded Arabic and Latin handwritten documents demonstrate the usefulness of integrating the recognizer within the GAN architecture, which improves both the visual quality and the readability of the degraded document images. Moreover, we outperform the state of the art in H-DIBCO challenges, after fine tuning our pre-trained model with synthetically degraded Latin handwritten images, on this task.

Abstract: Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream approach. In this paper, we approach the document classification problem by learning cross-modal representations through language and vision cues, considering intra- and inter-modality relationships. Instead of merging features from different modalities into a common representation space, the proposed method exploits high-level interactions and learns relevant semantic information from effective attention flows within and across modalities. The proposed learning objective is devised between intra- and inter-modality alignment tasks, where the similarity distribution per task is computed by contracting positive sample pairs while simultaneously contrasting negative ones in the common feature representation space}. Extensive experiments on public document classification datasets demonstrate the effectiveness and the generalization capacity of our model on both low-scale and large-scale datasets.

Abstract: This paper presents an image retrieval system based on 2D shape information. Query shape objects and database images are repre- sented by polygonal approximations of their contours. Afterwards they are encoded, using geometric features, in terms of predefined structures. Shapes are then located in database images by a voting procedure on the spatial domain. Then an alignment matching provides a probability value to rank de database image in the retrieval result. The method al- lows to detect a query object in database images even when they contain complex scenes. Also the shape matching tolerates partial occlusions and affine transformations as translation, rotation or scaling.

Abstract: In this paper we propose a segmentation-free approach to word spotting. Word images are first encoded into feature vectors using Fisher Vector. Then, these feature vectors are used together with pyramidal histogram of characters labels (PHOC) to learn SVM-based attribute models. Documents are represented by these PHOC based word attributes. To efficiently compute the word attributes over a sliding window, we propose to use an integral image representation of the document using a simplified version of the attribute model. Finally we re-rank the top word candidates using the more discriminative full version of the word attributes. We show state-of-the-art results for segmentation-free query-by-example word spotting in single-writer and multi-writer standard datasets.