Faisal Shafait

ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images

Recognition of text in natural scene images is becoming a prominent research area due to the widespread availablity of imaging devices in low-cost consumer products like mobile phones. To evaluate the performance of recent algorithms in detecting and recognizing text from complex images, the ICDAR 2011 Robust Reading Competition was organized. Challenge 2 of the competition dealt specifically with detecting/recognizing text in natural scene images. This paper presents an overview of the approaches that the participants used, the evaluation measure, and the dataset used in the Challenge 2 of the contest. We also report the performance of all participating methods for text localization and word recognition tasks and compare their results using standard methods of area precision/recall and edit distance.

ICDAR 2013 Robust Reading Competition

This report presents the final results of the ICDAR 2013 Robust Reading Competition. The competition is structured in three Challenges addressing text extraction in different application domains, namely born-digital images, real scene images and real-scene videos. The Challenges are organised around specific tasks covering text localisation, text segmentation and word recognition. The competition took place in the first quarter of 2013, and received a total of 42 submissions over the different tasks offered. This report describes the datasets and ground truth specification, details the performance evaluation protocols used and presents the final results along with a brief summary of the participating methods.

Efficient Implementation of Local Adaptive Thresholding Techniques Using Integral Images

Adaptive binarization is an important first step in many document analysis and OCR processes. This paper describes a fast adaptive binarization algorithm that yields the same quality of binarization as the Sauvola method,1 but runs in time close to that of global thresholding methods (like Otsus method2), independent of the window size. The algorithm combines the statistical constraints of Sauvolas method with integral images.3 Testing on the UW-1 dataset demonstrates a 20-fold speedup compared to the original Sauvola algorithm.

Performance Evaluation and Benchmarking of Six-Page Segmentation Algorithms

Informative benchmarks are crucial for optimizing the page segmentation step of an OCR system, frequently the performance limiting step for overall OCR system performance. We show that current evaluation scores are insufficient for diagnosing specific errors in page segmentation and fail to identify some classes of serious segmentation errors altogether. This paper introduces a vectorial score that is sensitive to, and identifies, the most important classes of segmentation errors (over, under, and mis-segmentation) and what page components (lines, blocks, etc.) are affected. Unlike previous schemes, our evaluation method has a canonical representation of ground-truth data and guarantees pixel-accurate evaluation results for arbitrary region shapes. We present the results of evaluating widely used segmentation algorithms (x-y cut, smearing, whitespace analysis, constrained text-line finding, docstrum, and Voronoi) on the UW-III database and demonstrate that the new evaluation scheme permits the identification of several specific flaws in individual segmentation methods.

ICDAR 2015 competition on Robust Reading

Results of the ICDAR 2015 Robust Reading Competition are presented. A new Challenge 4 on Incidental Scene Text has been added to the Challenges on Born-Digital Images, Focused Scene Images and Video Text. Challenge 4 is run on a newly acquired dataset of 1,670 images evaluating Text Localisation, Word Recognition and End-to-End pipelines. In addition, the dataset for Challenge 3 on Video Text has been substantially updated with more video sequences and more accurate ground truth data. Finally, tasks assessing End-to-End system performance have been introduced to all Challenges. The competition took place in the first quarter of 2015, and received a total of 44 submissions. Only the tasks newly introduced in 2015 are reported on. The datasets, the ground truth specification and the evaluation protocols are presented together with the results and a brief summary of the participating methods.

High-Performance OCR for Printed English and Fraktur Using LSTM Networks

Long Short-Term Memory (LSTM) networks have yielded excellent results on handwriting recognition. This paper describes an application of bidirectional LSTM networks to the problem of machine-printed Latin and Fraktur recognition. Latin and Fraktur recognition differs significantly from handwriting recognition in both the statistical properties of the data, as well as in the required, much higher levels of accuracy. Applications of LSTM networks to handwriting recognition use two-dimensional recurrent networks, since the exact position and baseline of handwritten characters is variable. In contrast, for printed OCR, we used a one-dimensional recurrent network combined with a novel algorithm for baseline and x-height normalization. A number of databases were used for training and testing, including the UW3 database, artificially generated and degraded Fraktur text and scanned pages from a book digitization project. The LSTM architecture achieved 0.6% character-level test-set error on English text. When the artificially degraded Fraktur data set is divided into training and test sets, the system achieves an error rate of 1.64%. On specific books printed in Fraktur (not part of the training set), the system achieves error rates of 0.15% (Fontane) and 1.47% (Ersch-Gruber). These recognition accuracies were found without using any language modelling or any other post-processing techniques.

Document cleanup using page frame detection

AbstractWhen a page of a book is scanned or photocopied, textual noise (extraneous symbols from the neighboring page) and/or non-textual noise (black borders, speckles, ...) appear along the border of the document. Existing document analysis methods can handle non-textual noise reasonably well, whereas textual noise still presents a major issue for document analysis systems. Textual noise may result in undesired text in optical character recognition (OCR) output that needs to be removed afterwards. Existing document cleanup methods try to explicitly detect and remove marginal noise. This paper presents a new perspective for document image cleanup by detecting the page frame of the document. The goal of page frame detection is to find the actual page contents area, ignoring marginal noise along the page border. We use a geometric matching algorithm to find the optimal page frame of structured documents (journal articles, books, magazines) by exploiting their text alignment property. We evaluate the algorithm on the UW-III database. The results show that the error rates are below 4% each of the performance measures used. Further tests were run on a dataset of magazine pages and on a set of camera captured document images. To demonstrate the benefits of using page frame detection in practical applications, we choose OCR and layout-based document image retrieval as sample applications. Experiments using a commercial OCR system show that by removing characters outside the computed page frame, the OCR error rate is reduced from 4.3 to 1.7% on the UW-III dataset. The use of page frame detection in layout-based document image retrieval application decreases the retrieval error rates by 30%.

Performance comparison of six algorithms for page segmentation

This paper presents a quantitative comparison of six algorithms for page segmentation: X-Y cut, smearing, whitespace analysis, constrained text-line finding, Docstrum, and Voronoi-diagram-based. The evaluation is performed using a subset of the UW-III collection commonly used for evaluation, with a separate training set for parameter optimization. We compare the results using both default parameters and optimized parameters. In the course of the evaluation, the strengths and weaknesses of each algorithm are analyzed, and it is shown that no single algorithm outperforms all other algorithms. However, we observe that the three best-performing algorithms are those based on constrained text-line finding, Docstrum, and the Voronoi-diagram.

Sparse Spatio-spectral Representation for Hyperspectral Image Super-resolution

Existing hyperspectral imaging systems produce low spatial resolution images due to hardware constraints. We propose a sparse representation based approach for hyperspectral image super-resolution. The proposed approach first extracts distinct reflectance spectra of the scene from the available hyperspectral image. Then, the signal sparsity, non-negativity and the spatial structure in the scene are exploited to explain a high-spatial but low-spectral resolution image of the same scene in terms of the extracted spectra. This is done by learning a sparse code with an algorithm G-SOMP+. Finally, the learned sparse code is used with the extracted scene spectra to estimate the super-resolution hyperspectral image. Comparison of the proposed approach with the state-of-the-art methods on both ground-based and remotely-sensed public hyperspectral image databases shows that the presented method achieves the lowest error rate on all test images in the three datasets.

Automatic classifier selection for non-experts

Choosing a suitable classifier for a given dataset is an important part of developing a pattern recognition system. Since a large variety of classification algorithms are proposed in literature, non-experts do not know which method should be used in order to obtain good classification results on their data. Meta-learning tries to address this problem by recommending promising classifiers based on meta-features computed from a given dataset. In this paper, we empirically evaluate five different categories of state-of-the-art meta-features for their suitability in predicting classification accuracies of several widely used classifiers (including Support Vector Machines, Neural Networks, Random Forests, Decision Trees, and Logistic Regression). Based on the evaluation results, we have developed the first open source meta-learning system that is capable of accurately predicting accuracies of target classifiers. The user provides a dataset as input and gets an automatically created high-performance ready-to-use pattern recognition system in a few simple steps. A user study of the system with non-experts showed that the users were able to develop more accurate pattern recognition systems in significantly less development time when using our system as compared to using a state-of-the-art data mining software.