2019 |
|
Manuel Carbonell, Joan Mas, Mauricio Villegas, Alicia Fornes and Josep Llados. 2019. End-to-End Handwritten Text Detection and Transcription in Full Pages. 2nd International Workshop on Machine Learning.29–34.
Abstract: When transcribing handwritten document images, inaccuracies in the text segmentation step often cause errors in the subsequent transcription step. For this reason, some recent methods propose to perform the recognition at paragraph level. But still, errors in the segmentation of paragraphs can affect
the transcription performance. In this work, we propose an end-to-end framework to transcribe full pages. The joint text detection and transcription allows to remove the layout analysis requirement at test time. The experimental results show that our approach can achieve comparable results to models that assume
segmented paragraphs, and suggest that joining the two tasks brings an improvement over doing the two tasks separately.
Keywords: Handwritten Text Recognition; Layout Analysis; Text segmentation; Deep Neural Networks; Multi-task learning
|
|
|
Marçal Rusiñol. 2019. Classificació semàntica i visual de documents digitals.
Abstract: Se analizan los sistemas de procesamiento automático que trabajan sobre documentos digitalizados con el objetivo de describir los contenidos. De esta forma contribuyen a facilitar el acceso, permitir la indización automática y hacer accesibles los documentos a los motores de búsqueda. El objetivo de estas tecnologías es poder entrenar modelos computacionales que sean capaces de clasificar, agrupar o realizar búsquedas sobre documentos digitales. Así, se describen las tareas de clasificación, agrupamiento y búsqueda. Cuando utilizamos tecnologías de inteligencia artificial en los sistemas de
clasificación esperamos que la herramienta nos devuelva etiquetas semánticas; en sistemas de agrupamiento que nos devuelva documentos agrupados en clusters significativos; y en sistemas de búsqueda esperamos que dada una consulta, nos devuelva una lista ordenada de documentos en función de la relevancia. A continuación se da una visión de conjunto de los métodos que nos permiten describir los documentos digitales, tanto de manera visual (cuál es su apariencia), como a partir de sus contenidos semánticos (de qué hablan). En cuanto a la descripción visual de documentos se aborda el estado de la cuestión de las representaciones numéricas de documentos digitalizados
tanto por métodos clásicos como por métodos basados en el aprendizaje profundo (deep learning). Respecto de la descripción semántica de los contenidos se analizan técnicas como el reconocimiento óptico de caracteres (OCR); el cálculo de estadísticas básicas sobre la aparición de las diferentes palabras en un texto (bag-of-words model); y los métodos basados en aprendizaje profundo como el método word2vec, basado en una red neuronal que, dadas unas cuantas palabras de un texto, debe predecir cuál será la
siguiente palabra. Desde el campo de las ingenierías se están transfiriendo conocimientos que se han integrado en productos o servicios en los ámbitos de la archivística, la biblioteconomía, la documentación y las plataformas de gran consumo, sin embargo los algoritmos deben ser lo suficientemente eficientes no sólo para el reconocimiento y transcripción literal sino también para la capacidad de interpretación de los contenidos.
|
|
|
Marçal Rusiñol, Lluis Gomez, A. Landman, M. Silva Constenla and Dimosthenis Karatzas. 2019. Automatic Structured Text Reading for License Plates and Utility Meters. BMVC Workshop on Visual Artificial Intelligence and Entrepreneurship.
Abstract: Reading text in images has attracted interest from computer vision researchers for
many years. Our technology focuses on the extraction of structured text – such as serial
numbers, machine readings, product codes, etc. – so that it is able to center its attention just on the relevant textual elements. It is conceived to work in an end-to-end fashion, bypassing any explicit text segmentation stage. In this paper we present two different industrial use cases where we have applied our automatic structured text reading technology. In the first one, we demonstrate an outstanding performance when reading license plates compared to the current state of the art. In the second one, we present results on our solution for reading utility meters. The technology is commercialized by a recently created spin-off company, and both solutions are at different stages of integration with final clients.
|
|
|
Mohammed Al Rawi and Ernest Valveny. 2019. Compact and Efficient Multitask Learning in Vision, Language and Speech. IEEE International Conference on Computer Vision Workshops.2933–2942.
Abstract: Across-domain multitask learning is a challenging area of computer vision and machine learning due to the intra-similarities among class distributions. Addressing this problem to cope with the human cognition system by considering inter and intra-class categorization and recognition complicates the problem even further. We propose in this work an effective holistic and hierarchical learning by using a text embedding layer on top of a deep learning model. We also propose a novel sensory discriminator approach to resolve the collisions between different tasks and domains. We then train the model concurrently on textual sentiment analysis, speech recognition, image classification, action recognition from video, and handwriting word spotting of two different scripts (Arabic and English). The model we propose successfully learned different tasks across multiple domains.
|
|
|
Mohammed Al Rawi, Ernest Valveny and Dimosthenis Karatzas. 2019. Can One Deep Learning Model Learn Script-Independent Multilingual Word-Spotting? 15th International Conference on Document Analysis and Recognition.260–267.
Abstract: Word spotting has gained increased attention lately as it can be used to extract textual information from handwritten documents and scene-text images. Current word spotting approaches are designed to work on a single language and/or script. Building intelligent models that learn script-independent multilingual word-spotting is challenging due to the large variability of multilingual alphabets and symbols. We used ResNet-152 and the Pyramidal Histogram of Characters (PHOC) embedding to build a one-model script-independent multilingual word-spotting and we tested it on Latin, Arabic, and Bangla (Indian) languages. The one-model we propose performs on par with the multi-model language-specific word-spotting system, and thus, reduces the number of models needed for each script and/or language.
|
|
|
Nibal Nayef and 10 others. 2019. ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition — RRC-MLT-2019. 15th International Conference on Document Analysis and Recognition.1582–1587.
Abstract: With the growing cosmopolitan culture of modern cities, the need of robust Multi-Lingual scene Text (MLT) detection and recognition systems has never been more immense. With the goal to systematically benchmark and push the state-of-the-art forward, the proposed competition builds on top of the RRC-MLT-2017 with an additional end-to-end task, an additional language in the real images dataset, a large scale multi-lingual synthetic dataset to assist the training, and a baseline End-to-End recognition method. The real dataset consists of 20,000 images containing text from 10 languages. The challenge has 4 tasks covering various aspects of multi-lingual scene text: (a) text detection, (b) cropped word script classification, (c) joint text detection and script classification and (d) end-to-end detection and recognition. In total, the competition received 60 submissions from the research and industrial communities. This paper presents the dataset, the tasks and the findings of the presented RRC-MLT-2019 challenge.
|
|
|
Pau Riba, Anjan Dutta, Lutz Goldmann, Alicia Fornes, Oriol Ramos Terrades and Josep Llados. 2019. Table Detection in Invoice Documents by Graph Neural Networks. 15th International Conference on Document Analysis and Recognition.122–127.
Abstract: Tabular structures in documents offer a complementary dimension to the raw textual data, representing logical or quantitative relationships among pieces of information. In digital mail room applications, where a large amount of
administrative documents must be processed with reasonable accuracy, the detection and interpretation of tables is crucial. Table recognition has gained interest in document image analysis, in particular in unconstrained formats (absence of rule lines, unknown information of rows and columns). In this work, we propose a graph-based approach for detecting tables in document images. Instead of using the raw content (recognized text), we make use of the location, context and content type, thus it is purely a structure perception approach, not dependent on the language and the quality of the text
reading. Our framework makes use of Graph Neural Networks (GNNs) in order to describe the local repetitive structural information of tables in invoice documents. Our proposed model has been experimentally validated in two invoice datasets and achieved encouraging results. Additionally, due to the scarcity
of benchmark datasets for this task, we have contributed to the community a novel dataset derived from the RVL-CDIP invoice data. It will be publicly released to facilitate future research.
|
|
|
Raul Gomez, Ali Furkan Biten, Lluis Gomez, Jaume Gibert, Marçal Rusiñol and Dimosthenis Karatzas. 2019. Selective Style Transfer for Text. 15th International Conference on Document Analysis and Recognition.805–812.
Abstract: This paper explores the possibilities of image style transfer applied to text maintaining the original transcriptions. Results on different text domains (scene text, machine printed text and handwritten text) and cross-modal results demonstrate that this is feasible, and open different research lines. Furthermore, two architectures for selective style transfer, which means
transferring style to only desired image pixels, are proposed. Finally, scene text selective style transfer is evaluated as a data augmentation technique to expand scene text detection datasets, resulting in a boost of text detectors performance. Our implementation of the described models is publicly available.
Keywords: transfer; text style transfer; data augmentation; scene text detection
|
|
|
Raul Gomez, Lluis Gomez, Jaume Gibert and Dimosthenis Karatzas. 2019. Self-Supervised Learning from Web Data for Multimodal Retrieval. Multi-Modal Scene Understanding Book.279–306.
Abstract: Self-Supervised learning from multimodal image and text data allows deep neural networks to learn powerful features with no need of human annotated data. Web and Social Media platforms provide a virtually unlimited amount of this multimodal data. In this work we propose to exploit this free available data to learn a multimodal image and text embedding, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the proposed pipeline can learn from images with associated text without supervision and analyze the semantic structure of the learnt joint image and text embeddingspace. Weperformathoroughanalysisandperformancecomparisonoffivedifferentstateof the art text embeddings in three different benchmarks. We show that the embeddings learnt with Web and Social Media data have competitive performances over supervised methods in the text basedimageretrievaltask,andweclearlyoutperformstateoftheartintheMIRFlickrdatasetwhen training in the target data. Further, we demonstrate how semantic multimodal image retrieval can be performed using the learnt embeddings, going beyond classical instance-level retrieval problems. Finally, we present a new dataset, InstaCities1M, composed by Instagram images and their associated texts that can be used for fair comparison of image-text embeddings.
Keywords: self-supervised learning; webly supervised learning; text embeddings; multimodal retrieval; multimodal embedding
|
|
|
Rui Zhang and 14 others. 2019. ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard. 15th International Conference on Document Analysis and Recognition.1577–1581.
Abstract: Chinese scene text reading is one of the most challenging problems in computer vision and has attracted great interest. Different from English text, Chinese has more than 6000 commonly used characters and Chinesecharacters can be arranged in various layouts with numerous fonts. The Chinese signboards in street view are a good choice for Chinese scene text images since they have different backgrounds, fonts and layouts. We organized a competition called ICDAR2019-ReCTS, which mainly focuses on reading Chinese text on signboard. This report presents the final results of the competition. A large-scale dataset of 25,000 annotated signboard images, in which all the text lines and characters are annotated with locations and transcriptions, were released. Four tasks, namely character recognition, text line recognition, text line detection and end-to-end recognition were set up. Besides, considering the Chinese text ambiguity issue, we proposed a multi ground truth (multi-GT) evaluation method to make evaluation fairer. The competition started on March 1, 2019 and ended on April 30, 2019. 262 submissions from 46 teams are received. Most of the participants come from universities, research institutes, and tech companies in China. There are also some participants from the United States, Australia, Singapore, and Korea. 21 teams submit results for Task 1, 23 teams submit results for Task 2, 24 teams submit results for Task 3, and 13 teams submit results for Task 4.
|
|