|
|
Mohamed Ali Souibgui and 6 others. 2022. DocEnTr: An End-to-End Document Image Enhancement Transformer. 26th International Conference on Pattern Recognition.1699–1705.
Abstract: Document images can be affected by many degradation scenarios, which cause recognition and processing difficulties. In this age of digitization, it is important to denoise them for proper usage. To address this challenge, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion. The encoder operates directly on the pixel patches with their positional information without the use of any convolutional layers, while the decoder reconstructs a clean image from the encoded patches. Conducted experiments show a superiority of the proposed model compared to the state-of the-art methods on several DIBCO benchmarks. Code and models will be publicly available at: https://github.com/dali92002/DocEnTR
Keywords: Degradation; Head; Optical character recognition; Self-supervised learning; Benchmark testing; Transformers; Magnetic heads
|
|
|
|
Minesh Mathew, Viraj Bagal, Ruben Tito, Dimosthenis Karatzas, Ernest Valveny and C.V. Jawahar. 2022. InfographicVQA. Winter Conference on Applications of Computer Vision.1697–1706.
Abstract: Infographics communicate information using a combination of textual, graphical and visual elements. This work explores the automatic understanding of infographic images by using a Visual Question Answering technique. To this end, we present InfographicVQA, a new dataset comprising a diverse collection of infographics and question-answer annotations. The questions require methods that jointly reason over the document layout, textual content, graphical elements, and data visualizations. We curate the dataset with an emphasis on questions that require elementary reasoning and basic arithmetic skills. For VQA on the dataset, we evaluate two Transformer-based strong baselines. Both the baselines yield unsatisfactory results compared to near perfect human performance on the dataset. The results suggest that VQA on infographics--images that are designed to communicate information quickly and clearly to human brain--is ideal for benchmarking machine understanding of complex document images. The dataset is available for download at docvqa. org
Keywords: Document Analysis Datasets; Evaluation and Comparison of Vision Algorithms; Vision and Languages
|
|
|
|
Palaiahnakote Shivakumara, Anjan Dutta, Trung Quy Phan, Chew Lim Tan and Umapada Pal. 2011. A Novel Mutual Nearest Neighbor based Symmetry for Text Frame Classification in Video. PR, 44(8), 1671–1683.
Abstract: In the field of multimedia retrieval in video, text frame classification is essential for text detection, event detection, event boundary detection, etc. We propose a new text frame classification method that introduces a combination of wavelet and median moment with k-means clustering to select probable text blocks among 16 equally sized blocks of a video frame. The same feature combination is used with a new Max–Min clustering at the pixel level to choose probable dominant text pixels in the selected probable text blocks. For the probable text pixels, a so-called mutual nearest neighbor based symmetry is explored with a four-quadrant formation centered at the centroid of the probable dominant text pixels to know whether a block is a true text block or not. If a frame produces at least one true text block then it is considered as a text frame otherwise it is a non-text frame. Experimental results on different text and non-text datasets including two public datasets and our own created data show that the proposed method gives promising results in terms of recall and precision at the block and frame levels. Further, we also show how existing text detection methods tend to misclassify non-text frames as text frames in term of recall and precision at both the block and frame levels.
|
|
|
|
Anjan Dutta, Jaume Gibert, Josep Llados, Horst Bunke and Umapada Pal. 2012. Combination of Product Graph and Random Walk Kernel for Symbol Spotting in Graphical Documents. 21st International Conference on Pattern Recognition.1663–1666.
Abstract: This paper explores the utilization of product graph for spotting symbols on graphical documents. Product graph is intended to find the candidate subgraphs or components in the input graph containing the paths similar to the query graph. The acute angle between two edges and their length ratio are considered as the node labels. In a second step, each of the candidate subgraphs in the input graph is assigned with a distance measure computed by a random walk kernel. Actually it is the minimum of the distances of the component to all the components of the model graph. This distance measure is then used to eliminate dissimilar components. The remaining neighboring components are grouped and the grouped zone is considered as a retrieval zone of a symbol similar to the queried one. The entire method works online, i.e., it doesn't need any preprocessing step. The present paper reports the initial results of the method, which are very encouraging.
|
|
|
|
Veronica Romero and 7 others. 2013. The ESPOSALLES database: An ancient marriage license corpus for off-line handwriting recognition. PR, 46(6), 1658–1669.
Abstract: Historical records of daily activities provide intriguing insights into the life of our ancestors, useful for demography studies and genealogical research. Automatic processing of historical documents, however, has mostly been focused on single works of literature and less on social records, which tend to have a distinct layout, structure, and vocabulary. Such information is usually collected by expert demographers that devote a lot of time to manually transcribe them. This paper presents a new database, compiled from a marriage license books collection, to support research in automatic handwriting recognition for historical documents containing social records. Marriage license books are documents that were used for centuries by ecclesiastical institutions to register marriage licenses. Books from this collection are handwritten and span nearly half a millennium until the beginning of the 20th century. In addition, a study is presented about the capability of state-of-the-art handwritten text recognition systems, when applied to the presented database. Baseline results are reported for reference in future studies.
|
|
|
|
Miquel Ferrer, Ernest Valveny, F. Serratosa, K. Riesen and Horst Bunke. 2010. Generalized Median Graph Computation by Means of Graph Embedding in Vector Spaces. PR, 43(4), 1642–1655.
Abstract: The median graph has been presented as a useful tool to represent a set of graphs. Nevertheless its computation is very complex and the existing algorithms are restricted to use limited amount of data. In this paper we propose a new approach for the computation of the median graph based on graph embedding. Graphs are embedded into a vector space and the median is computed in the vector domain. We have designed a procedure based on the weighted mean of a pair of graphs to go from the vector domain back to the graph domain in order to obtain a final approximation of the median graph. Experiments on three different databases containing large graphs show that we succeed to compute good approximations of the median graph. We have also applied the median graph to perform some basic classification tasks achieving reasonable good results. These experiments on real data open the door to the application of the median graph to a number of more complex machine learning algorithms where a representative of a set of graphs is needed.
Keywords: Graph matching; Weighted mean of graphs; Median graph; Graph embedding; Vector spaces
|
|
|
|
Oriol Ramos Terrades, Ernest Valveny and Salvatore Tabbone. 2009. Optimal Classifier Fusion in a Non-Bayesian Probabilistic Framework. TPAMI, 31(9), 1630–1644.
Abstract: The combination of the output of classifiers has been one of the strategies used to improve classification rates in general purpose classification systems. Some of the most common approaches can be explained using the Bayes' formula. In this paper, we tackle the problem of the combination of classifiers using a non-Bayesian probabilistic framework. This approach permits us to derive two linear combination rules that minimize misclassification rates under some constraints on the distribution of classifiers. In order to show the validity of this approach we have compared it with other popular combination rules from a theoretical viewpoint using a synthetic data set, and experimentally using two standard databases: the MNIST handwritten digit database and the GREC symbol database. Results on the synthetic data set show the validity of the theoretical approach. Indeed, results on real data show that the proposed methods outperform other common combination schemes.
|
|
|
|
Marçal Rusiñol, Farshad Nourbakhsh, Dimosthenis Karatzas, Ernest Valveny and Josep Llados. 2010. Perceptual Image Retrieval by Adding Color Information to the Shape Context Descriptor. 20th International Conference on Pattern Recognition.1594–1597.
Abstract: In this paper we present a method for the retrieval of images in terms of perceptual similarity. Local color information is added to the shape context descriptor in order to obtain an object description integrating both shape and color as visual cues. We use a color naming algorithm in order to represent the color information from a perceptual point of view. The proposed method has been tested in two different applications, an object retrieval scenario based on color sketch queries and a color trademark retrieval problem. Experimental results show that the addition of the color information significantly outperforms the sole use of the shape context descriptor.
|
|
|
|
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.
|
|
|
|
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.
|
|
