|
Minesh Mathew, Ruben Tito, Dimosthenis Karatzas, R.Manmatha and C.V. Jawahar. 2020. Document Visual Question Answering Challenge 2020. 33rd IEEE Conference on Computer Vision and Pattern Recognition – Short paper.
Abstract: This paper presents results of Document Visual Question Answering Challenge organized as part of “Text and Documents in the Deep Learning Era” workshop, in CVPR 2020. The challenge introduces a new problem – Visual Question Answering on document images. The challenge comprised two tasks. The first task concerns with asking questions on a single document image. On the other hand, the second task is set as a retrieval task where the question is posed over a collection of images. For the task 1 a new dataset is introduced comprising 50,000 questions-answer(s) pairs defined over 12,767 document images. For task 2 another dataset has been created comprising 20 questions over 14,362 document images which share the same document template.
|
|
|
Minesh Mathew, Dimosthenis Karatzas and C.V. Jawahar. 2021. DocVQA: A Dataset for VQA on Document Images. IEEE Winter Conference on Applications of Computer Vision.2200–2209.
Abstract: We present a new dataset for Visual Question Answering (VQA) on document images called DocVQA. The dataset consists of 50,000 questions defined on 12,000+ document images. Detailed analysis of the dataset in comparison with similar datasets for VQA and reading comprehension is presented. We report several baseline results by adopting existing VQA and reading comprehension models. Although the existing models perform reasonably well on certain types of questions, there is large performance gap compared to human performance (94.36% accuracy). The models need to improve specifically on questions where understanding structure of the document is crucial. The dataset, code and leaderboard are available at docvqa. org
|
|
|
Arka Ujjal Dey, Suman Ghosh and Ernest Valveny. 2018. Don't only Feel Read: Using Scene text to understand advertisements. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.
Abstract: We propose a framework for automated classification of Advertisement Images, using not just Visual features but also Textual cues extracted from embedded text. Our approach takes inspiration from the assumption that Ad images contain meaningful textual content, that can provide discriminative semantic interpretetion, and can thus aid in classifcation tasks. To this end, we develop a framework using off-the-shelf components, and demonstrate the effectiveness of Textual cues in semantic Classfication tasks.
|
|
|
Sounak Dey, Pau Riba, Anjan Dutta, Josep Llados and Yi-Zhe Song. 2019. Doodle to Search: Practical Zero-Shot Sketch-Based Image Retrieval. IEEE Conference on Computer Vision and Pattern Recognition.2179–2188.
Abstract: In this paper, we investigate the problem of zero-shot sketch-based image retrieval (ZS-SBIR), where human sketches are used as queries to conduct retrieval of photos from unseen categories. We importantly advance prior arts by proposing a novel ZS-SBIR scenario that represents a firm step forward in its practical application. The new setting uniquely recognizes two important yet often neglected challenges of practical ZS-SBIR, (i) the large domain gap between amateur sketch and photo, and (ii) the necessity for moving towards large-scale retrieval. We first contribute to the community a novel ZS-SBIR dataset, QuickDraw-Extended, that consists of 330,000 sketches and 204,000 photos spanning across 110 categories. Highly abstract amateur human sketches are purposefully sourced to maximize the domain gap, instead of ones included in existing datasets that can often be semi-photorealistic. We then formulate a ZS-SBIR framework to jointly model sketches and photos into a common embedding space. A novel strategy to mine the mutual information among domains is specifically engineered to alleviate the domain gap. External semantic knowledge is further embedded to aid semantic transfer. We show that, rather surprisingly, retrieval performance significantly outperforms that of state-of-the-art on existing datasets that can already be achieved using a reduced version of our model. We further demonstrate the superior performance of our full model by comparing with a number of alternatives on the newly proposed dataset. The new dataset, plus all training and testing code of our model, will be publicly released to facilitate future research.
|
|
|
Thanh Ha Do, Oriol Ramos Terrades and Salvatore Tabbone. 2019. DSD: document sparse-based denoising algorithm. PAA, 22(1), 177–186.
Abstract: In this paper, we present a sparse-based denoising algorithm for scanned documents. This method can be applied to any kind of scanned documents with satisfactory results. Unlike other approaches, the proposed approach encodes noise documents through sparse representation and visual dictionary learning techniques without any prior noise model. Moreover, we propose a precision parameter estimator. Experiments on several datasets demonstrate the robustness of the proposed approach compared to the state-of-the-art methods on document denoising.
Keywords: Document denoising; Sparse representations; Sparse dictionary learning; Document degradation models
|
|
|
Y. Patel, Lluis Gomez, Marçal Rusiñol and Dimosthenis Karatzas. 2016. Dynamic Lexicon Generation for Natural Scene Images. 14th European Conference on Computer Vision Workshops.395–410.
Abstract: Many scene text understanding methods approach the endtoend recognition problem from a word-spotting perspective and take huge benet from using small per-image lexicons. Such customized lexicons are normally assumed as given and their source is rarely discussed.
In this paper we propose a method that generates contextualized lexicons
for scene images using only visual information. For this, we exploit
the correlation between visual and textual information in a dataset consisting
of images and textual content associated with them. Using the topic modeling framework to discover a set of latent topics in such a dataset allows us to re-rank a xed dictionary in a way that prioritizes the words that are more likely to appear in a given image. Moreover, we train a CNN that is able to reproduce those word rankings but using only the image raw pixels as input. We demonstrate that the quality of the automatically obtained custom lexicons is superior to a generic frequency-based baseline.
Keywords: scene text; photo OCR; scene understanding; lexicon generation; topic modeling; CNN
|
|
|
Albert Berenguel, Oriol Ramos Terrades, Josep Llados and Cristina Cañero. 2017. e-Counterfeit: a mobile-server platform for document counterfeit detection. 14th IAPR International Conference on Document Analysis and Recognition.
Abstract: This paper presents a novel application to detect counterfeit identity documents forged by a scan-printing operation. Texture analysis approaches are proposed to extract validation features from security background that is usually printed in documents as IDs or banknotes. The main contribution of this work is the end-to-end mobile-server architecture, which provides a service for non-expert users and therefore can be used in several scenarios. The system also provides a crowdsourcing mode so labeled images can be gathered, generating databases for incremental training of the algorithms.
|
|
|
Pau Riba, Jon Almazan, Alicia Fornes, David Fernandez, Ernest Valveny and Josep Llados. 2014. e-Crowds: a mobile platform for browsing and searching in historical demographyrelated manuscripts. 14th International Conference on Frontiers in Handwriting Recognition.228–233.
Abstract: This paper presents a prototype system running on portable devices for browsing and word searching through historical handwritten document collections. The platform adapts the paradigm of eBook reading, where the narrative is not necessarily sequential, but centered on the user actions. The novelty is to replace digitally born books by digitized historical manuscripts of marriage licenses, so document analysis tasks are required in the browser. With an active reading paradigm, the user can cast queries of people names, so he/she can implicitly follow genealogical links. In addition, the system allows combined searches: the user can refine a search by adding more words to search. As a second contribution, the retrieval functionality involves as a core technology a word spotting module with an unified approach, which allows combined query searches, and also two input modalities: query-by-example, and query-by-string.
|
|
|
Asma Bensalah, Alicia Fornes, Cristina Carmona_Duarte and Josep Llados. 2022. Easing Automatic Neurorehabilitation via Classification and Smoothness Analysis. Intertwining Graphonomics with Human Movements. 20th International Conference of the International Graphonomics Society, IGS 2022.336–348. (LNCS.)
Abstract: Assessing the quality of movements for post-stroke patients during the rehabilitation phase is vital given that there is no standard stroke rehabilitation plan for all the patients. In fact, it depends basically on the patient’s functional independence and its progress along the rehabilitation sessions. To tackle this challenge and make neurorehabilitation more agile, we propose an automatic assessment pipeline that starts by recognising patients’ movements by means of a shallow deep learning architecture, then measuring the movement quality using jerk measure and related measures. A particularity of this work is that the dataset used is clinically relevant, since it represents movements inspired from Fugl-Meyer a well common upper-limb clinical stroke assessment scale for stroke patients. We show that it is possible to detect the contrast between healthy and patients movements in terms of smoothness, besides achieving conclusions about the patients’ progress during the rehabilitation sessions that correspond to the clinicians’ findings about each case.
Keywords: Neurorehabilitation; Upper-lim; Movement classification; Movement smoothness; Deep learning; Jerk
|
|
|
David Aldavert. 2021. Efficient and Scalable Handwritten Word Spotting on Historical Documents using Bag of Visual Words. (Ph.D. thesis, Ediciones Graficas Rey.)
Abstract: Word spotting can be defined as the pattern recognition tasked aimed at locating and retrieving a specific keyword within a document image collection without explicitly transcribing the whole corpus. Its use is particularly interesting when applied in scenarios where Optical Character Recognition performs poorly or can not be used at all. This thesis focuses on such a scenario, word spotting on historical handwritten documents that have been written by a single author or by multiple authors with a similar calligraphy.
This problem requires a visual signature that is robust to image artifacts, flexible to accommodate script variations and efficient to retrieve information in a rapid manner. For this, we have developed a set of word spotting methods that on their foundation use the well known Bag-of-Visual-Words (BoVW) representation. This representation has gained popularity among the document image analysis community to characterize handwritten words
in an unsupervised manner. However, most approaches on this field rely on a basic BoVW configuration and disregard complex encoding and spatial representations. We determine which BoVW configurations provide the best performance boost to a spotting system.
Then, we extend the segmentation-based word spotting, where word candidates are given a priori, to segmentation-free spotting. The proposed approach seeds the document images with overlapping word location candidates and characterizes them with a BoVW signature. Retrieval is achieved comparing the query and candidate signatures and returning the locations that provide a higher consensus. This is a simple but powerful approach that requires a more compact signature than in a segmentation-based scenario. We first
project the BoVW signature into a reduced semantic topics space and then compress it further using Product Quantizers. The resulting signature only requires a few dozen bytes, allowing us to index thousands of pages on a common desktop computer. The final system still yields a performance comparable to the state-of-the-art despite all the information loss during the compression phases.
Afterwards, we also study how to combine different modalities of information in order to create a query-by-X spotting system where, words are indexed using an information modality and queries are retrieved using another. We consider three different information modalities: visual, textual and audio. Our proposal is to create a latent feature space where features which are semantically related are projected onto the same topics. Creating thus a new feature space where information from different modalities can be compared. Later, we consider the codebook generation and descriptor encoding problem. The codebooks used to encode the BoVW signatures are usually created using an unsupervised clustering algorithm and, they require to test multiple parameters to determine which configuration is best for a certain document collection. We propose a semantic clustering algorithm which allows to estimate the best parameter from data. Since gather annotated data is costly, we use synthetically generated word images. The resulting codebook is database agnostic, i. e. a codebook that yields a good performance on document collections that use the same script. We also propose the use of an additional codebook to approximate descriptors and reduce the descriptor encoding
complexity to sub-linear.
Finally, we focus on the problem of signatures dimensionality. We propose a new symbol probability signature where each bin represents the probability that a certain symbol is present a certain location of the word image. This signature is extremely compact and combined with compression techniques can represent word images with just a few bytes per signature.
|
|