Ahmed Hamdi, Mickaël Coustaty, Aurélie Joseph, V. P. d'Andecy, A. Doucet, J. Ogier
{"title":"Feature Selection for Document Flow Segmentation","authors":"Ahmed Hamdi, Mickaël Coustaty, Aurélie Joseph, V. P. d'Andecy, A. Doucet, J. Ogier","doi":"10.1109/DAS.2018.66","DOIUrl":"https://doi.org/10.1109/DAS.2018.66","url":null,"abstract":"In this paper, we describe a method to restore a flow of continuous documents. The flow is a collection of consecutive scanned pages without explicit separation marks between documents. Our method is based on contextual and layout descriptors meant to specify the relationship between each pair of consecutive pages. The relationships are represented using vectors of features with boolean values indicating the presence or the absence of descriptors on concerned pages. The segmentation task therefore consists in classifying such vectors into continuities or breaks. The continuity class indicates that pages belong to the same document while the break class ends the ongoing document and starts a new one. The experimental part is based on a large collection of real administrative documents.","PeriodicalId":243741,"journal":{"name":"2018 13th IAPR International Workshop on Document Analysis Systems (DAS)","volume":"55 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120859780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kartik Dutta, Praveen Krishnan, Minesh Mathew, C. V. Jawahar
{"title":"Offline Handwriting Recognition on Devanagari Using a New Benchmark Dataset","authors":"Kartik Dutta, Praveen Krishnan, Minesh Mathew, C. V. Jawahar","doi":"10.1109/DAS.2018.69","DOIUrl":"https://doi.org/10.1109/DAS.2018.69","url":null,"abstract":"Handwriting recognition (HWR) in Indic scripts, like Devanagari is very challenging due to the subtleties in the scripts, variations in rendering and the cursive nature of the handwriting. Lack of public handwriting datasets in Indic scripts has long stymied the development of offline handwritten word recognizers and made comparison across different methods a tedious task in the field. In this paper, we release a new handwritten word dataset for Devanagari, IIIT-HW-Dev to alleviate some of these issues. We benchmark the IIIT-HW-Dev dataset using a CNN-RNN hybrid architecture. Furthermore, using this architecture, we empirically show that usage of synthetic data and cross lingual transfer learning helps alleviate the issue of lack of training data. We use this proposed pipeline on a public dataset, RoyDB and achieve state of the art results.","PeriodicalId":243741,"journal":{"name":"2018 13th IAPR International Workshop on Document Analysis Systems (DAS)","volume":"243 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116891999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rathin Radhakrishnan Nair, Nishant Sankaran, B. Kota, S. Tulyakov, S. Setlur, V. Govindaraju
{"title":"Knowledge Transfer Using Neural Network Based Approach for Handwritten Text Recognition","authors":"Rathin Radhakrishnan Nair, Nishant Sankaran, B. Kota, S. Tulyakov, S. Setlur, V. Govindaraju","doi":"10.1109/DAS.2018.75","DOIUrl":"https://doi.org/10.1109/DAS.2018.75","url":null,"abstract":"The goal of a writer adaptive handwriting recognition system is to build a model that improves the recognition of a generic recognition model for a specific author. In this work, we show how structural representation learned from a generic writer-independent handwriting recognition model can be customized to individual authors. Convolutional Neural Network has shown outstanding performance in learning image-based representation that was used for classification. Additionally, they have been used along with Recurrent Neural Network (RNN) or its variations like, LSTM and GRU layers to analyze and understand sequences in handwriting recognition, sentence analysis, voice recognition etc. In most cases, the CNNs serve as a feature extractor instead of low-level hand-designed features that were used previously for the above-mentioned classification tasks. We design a method to reuse weights from layers trained on the IAM offline handwritten dataset to compute mid-level image representation for text in the Washington and Moore dataset. We show that despite differences in the writing style, fonts across these datasets, the transferred representation is able to capture a spatio-temporal representation leading to significantly improved recognition results. We hypothesize that the performance is solely not dependent on the number of samples and the model is evaluated with varying amount of fine-tuning samples showing promising results backing the hypothesis.","PeriodicalId":243741,"journal":{"name":"2018 13th IAPR International Workshop on Document Analysis Systems (DAS)","volume":"73 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134162552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A New Descriptor for Pattern Matching: Application to Identity Document Verification","authors":"N. Ghanmi, Ahmad Montaser Awal","doi":"10.1109/DAS.2018.74","DOIUrl":"https://doi.org/10.1109/DAS.2018.74","url":null,"abstract":"Identity document verification consists on checking its conformity to one or eventually a set of authentic documents. This verification is usually performed through visible patterns matching. In this paper, we propose a new efficient visual descriptor for pattern comparison. As most of existing descriptors incorporate either color or spatial information; the proposed descriptor, called Grid-3CD, includes both information. This descriptor is based on color connected components (CC) extracted from a quantified image. It consists of a set of 6-tuples computed on a grid of pixels sampled from the color-quantified image. The 6-tuple of a given pixel describes the density, the mass center, the bounding box and the color of the CC that contains this pixel. The efficiency of this descriptor for identity document verification is shown using two strategies of pattern comparison. The first one is unsupervised and based on a distance measure whereas the second is supervised and based on one-class Support Vector Machine (SVM). The experimentation of the new descriptor on four datasets of identity documents totaling 3250 documents shows an average accuracy of about 90%, outperforming state-of-the-art descriptors.","PeriodicalId":243741,"journal":{"name":"2018 13th IAPR International Workshop on Document Analysis Systems (DAS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122063507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Synthetically Generated Semantic Codebook for Bag-of-Visual-Words Based Word Spotting","authors":"David Aldavert, Marçal Rusiñol","doi":"10.1109/DAS.2018.25","DOIUrl":"https://doi.org/10.1109/DAS.2018.25","url":null,"abstract":"Word-spotting methods based on the Bag-of-Visual-Words framework have demonstrated a good retrieval performance even when used in a completely unsupervised manner. Although unsupervised approaches are suitable for large document collections due to the cost of acquiring labeled data, these methods also present some drawbacks. For instance, having to train a suitable \"codebook\" for a certain dataset has a high computational cost. Therefore, in this paper we present a database agnostic codebook which is trained from synthetic data. The aim of the proposed approach is to generate a codebook where the only information required is the type of script used in the document. The use of synthetic data also allows to easily incorporate semantic information in the codebook generation. So, the proposed method is able to determine which set of codewords have a semantic representation of the descriptor feature space. Experimental results show that the resulting codebook attains a state-of-the-art performance while having a more compact representation.","PeriodicalId":243741,"journal":{"name":"2018 13th IAPR International Workshop on Document Analysis Systems (DAS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124133184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Handwriting Recognition of Historical Documents with Few Labeled Data","authors":"E. Chammas, C. Mokbel, Laurence Likforman-Sulem","doi":"10.1109/DAS.2018.15","DOIUrl":"https://doi.org/10.1109/DAS.2018.15","url":null,"abstract":"Historical documents present many challenges for offline handwriting recognition systems, among them, the segmentation and labeling steps. Carefully annotated text lines are needed to train an HTR system. In some scenarios, transcripts are only available at the paragraph level with no text-line information. In this work, we demonstrate how to train an HTR system with few labeled data. Specifically, we train a deep convolutional recurrent neural network (CRNN) system on only 10% of manually labeled text-line data from a dataset and propose an incremental training procedure that covers the rest of the data. Performance is further increased by augmenting the training set with specially crafted multi scale data. We also propose a model-based normalization scheme which considers the variability in the writing scale at the recognition phase. We apply this approach to the publicly available READ dataset. Our system achieved the second best result during the ICDAR2017 competition [1].","PeriodicalId":243741,"journal":{"name":"2018 13th IAPR International Workshop on Document Analysis Systems (DAS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115836990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Word Spotting and Recognition Using Deep Embedding","authors":"Praveen Krishnan, Kartik Dutta, C. V. Jawahar","doi":"10.1109/DAS.2018.70","DOIUrl":"https://doi.org/10.1109/DAS.2018.70","url":null,"abstract":"Deep convolutional features for word images and textual embedding schemes have shown great success in word spotting. In this work, we follow these motivations to propose an End2End embedding framework which jointly learns both the text and image embeddings using state of the art deep convolutional architectures. The three major contributions of this work are: (i) an End2End embedding scheme to learn a common representation for word images and its labels, (ii) building a state of art word image descriptor and demonstrating its utility as off-the-shelf features for word spotting, and (iii) use of synthetic data as a complementary modality to further enhance word spotting and recognition. On the challenging IAM handwritten dataset, we report a mAP of 0.9509 for query-by-string based retrieval task. Under lexicon based word recognition, our proposed method report a 2.66 and 5.10 CER and WER respectively.","PeriodicalId":243741,"journal":{"name":"2018 13th IAPR International Workshop on Document Analysis Systems (DAS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125341496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Feature Fusion for Scene Text Detection","authors":"Zhen Zhu, Minghui Liao, Baoguang Shi, X. Bai","doi":"10.1109/DAS.2018.60","DOIUrl":"https://doi.org/10.1109/DAS.2018.60","url":null,"abstract":"A significant challenge in scene text detection is the large variation in text sizes. In particular, small text are usually hard to detect. This paper presents an accurate oriented text detector based on Faster R-CNN. We observe that Faster R-CNN is suitable for general object detection but inadequate for scene text detection due to the large variation in text size. We apply feature fusion both in RPN and Fast R-CNN to alleviate this problem and furthermore, enhance model's ability to detect relatively small text. Our text detector achieves comparable results to those state of the art methods on ICDAR 2015 and MSRA-TD500, showing its advantage and applicability.","PeriodicalId":243741,"journal":{"name":"2018 13th IAPR International Workshop on Document Analysis Systems (DAS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125562177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maximilian Klockmann, Marco Filax, F. Ortmeier, Martin ReiB
{"title":"On the Similarities of Fingerprints and Railroad Tracks: Using Minutiae Detection Algorithms to Digitize Track Plans","authors":"Maximilian Klockmann, Marco Filax, F. Ortmeier, Martin ReiB","doi":"10.1109/DAS.2018.47","DOIUrl":"https://doi.org/10.1109/DAS.2018.47","url":null,"abstract":"The complete track system of Germany covers more than 42.000 kilometers - some built before 1970. As a consequence, technical drawings are typically of manual origin. Newer plans are generated in a computer-aided way but remain drawings in the sense that semantics are not captured in the electronic files themselves. The engineer decides the meaning of a symbol while viewing the document. For project realization (e.g., engineering of some interlocking system), these plans are digitized manually into some machine interpretable format. In this paper, we propose an approach to digitize track layouts (semi-)automatically. We use fingerprint recognition techniques to digitize manually created track plans efficiently. At first, we detect tracks by detecting line endings and bifurcations. Secondly, we eliminate false candidates and irregularities. Finally, we translate the resulting graph into an interchangeable format: RailML. We evaluate our method by comparing our results with different track plans. Our results indicate that the proposed method is a promising candidate to reduce the effort of digitization.","PeriodicalId":243741,"journal":{"name":"2018 13th IAPR International Workshop on Document Analysis Systems (DAS)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117033854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Chanda, Emmanuel Okafor, Sébastien Hamel, D. Stutzmann, Lambert Schomaker
{"title":"Deep Learning for Classification and as Tapped-Feature Generator in Medieval Word-Image Recognition","authors":"S. Chanda, Emmanuel Okafor, Sébastien Hamel, D. Stutzmann, Lambert Schomaker","doi":"10.1109/DAS.2018.82","DOIUrl":"https://doi.org/10.1109/DAS.2018.82","url":null,"abstract":"Historical manuscripts are the main source of information about past. In recent years, digitization of large quantities of historical handwritten documents is in vogue. This trend gives access to a plethora of information about our medieval past. Such digital archives can be more useful if automatic indexing and retrieval of document images can be provided to the end users of a digital library. An automatic transcription of the full digital archive using traditional Optical Character Recognition (OCR) is still not possible with sufficient accuracy. If full transcription is not available, the end users are interested in indexing and retrieving of particular document pages of their interest. Hence recognition of certain keywords from within the corpus will be sufficient to meet the end users needs. Recently, deep-learning based methods have shown competence in image classification problems. However, one bottleneck with deep-learning based techniques is that it requires a huge amount of training samples per class. Since the number of samples per word class is scarce for collections that are freshly scanned, this is a serious hindrance for direct usage of the deep-learning technique for the purpose of word image recognition in historical document images. This paper aims to investigate the problem of recognizing words from historical document images using a deep-learning based framework for feature extraction and classification while countering the problem of the low amount of image samples using off-line data augmentation techniques. Encouraging results (highest accuracy of 90.03%) were obtained while dealing with 365 different word classes.","PeriodicalId":243741,"journal":{"name":"2018 13th IAPR International Workshop on Document Analysis Systems (DAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129324045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}