Rolf Ingold

Optical font recognition using typographical features

A new statistical approach based on global typographical features is proposed to the widely neglected problem of font recognition. It aims at the identification of the typeface, weight, slope and size of the text from an image block without any knowledge of the content of that text. The recognition is based on a multivariate Bayesian classifier and operates on a given set of known fonts. The effectiveness of the adopted approach has been experimented on a set of 280 fonts. Font recognition accuracies of about 97 percent were reached on high-quality images. In addition, rates higher than 99.9 percent were obtained for weight and slope detection. Experiments have also shown the system robustness to document language and text content and its sensitivity to text length.

A New Arabic Printed Text Image Database and Evaluation Protocols

We report on the creation of a database composed of images of Arabic Printed words. The purpose of this database is the large-scale benchmarking of open-vocabulary, multi-font, multi-size and multi-style text recognition systems in Arabic. The challenges that are addressed by the database are in the variability of the sizes, fonts and style used to generate the images. A focus is also given on low-resolution images where anti-aliasing is generating noise on the characters to recognize. The database is synthetically generated using a lexicon of 113’284 words, 10 Arabic fonts, 10 font sizes and 4 font styles. The database contains 45’313’600 single word images totaling to more than 250 million characters. Ground truth annotation is provided for each image. The database is called APTI for Arabic Printed Text Images.

A study on font-family and font-size recognition applied to Arabic word images at ultra-low resolution

In this paper, we propose a new font and size identification method for ultra-low resolution Arabic word images using a stochastic approach. The literature has proved the difficulty for Arabic text recognition systems to treat multi-font and multi-size word images. This is due to the variability induced by some font family, in addition to the inherent difficulties of Arabic writing including cursive representation, overlaps and ligatures. This research work proposes an efficient stochastic approach to tackle the problem of font and size recognition. Our method treats a word image with a fixed-length, overlapping sliding window. Each window is represented with a 102 features whose distribution is captured by Gaussian Mixture Models (GMMs). We present three systems: (1) a font recognition system, (2) a size recognition system and (3) a font and size recognition system. We demonstrate the importance of font identification before recognizing the word images with two multi-font Arabic OCRs (cascading and global). The cascading system is about 23% better than the global multi-font system in terms of word recognition rate on the Arabic Printed Text Image (APTI) database which is freely available to the scientific community.

Arabic newspaper page segmentation

The aim of layout analysis is to extract the geometricstructure from a document image. It consists of labelinghomogenous regions of a document image. This paperdescribes the performance of segmentation algorithmsand their adaptation in order to treat complex structuredArabic documents such as newspapers. Experimentaltests have been carried out on four different phases ofnewspaper image analysis: thread recognition, framerecognition, image text separation, text line recognition,and line merging into blocks. Some promisingexperimental results are reported.

Description languages for multimodal interaction: a set of guidelines and its illustration with SMUIML

This article introduces the problem of modeling multimodal interaction, in the form of markup languages. After an analysis of the current state of the art in multimodal interaction description languages, nine guidelines for languages dedicated at multimodal interaction description are introduced, as well as four different roles that such language should target: communication, configuration, teaching and modeling. The article further presents the SMUIML language, our proposed solution to improve the time synchronicity aspect while still fulfilling other guidelines. SMUIML is finally mapped to these guidelines as a way to evaluate their spectrum and to sketch future works.

Combined Handwriting and Speech Modalities for User Authentication

In this paper, we report on the development of an efficient user authentication system based on a combined acquisition of online pen and speech signals. The novelty of our approach is in the simultaneous recording of these two modalities, simply asking the user to utter what she/he is writing. The main benefit of this multimodal approach is a better accuracy at no extra costs in terms of access time or inconvenience. Another benefit comes from an increased difficulty for forgers willing to perform imitation attacks as two signals need to be reproduced. We are comparing here two potential scenarios of use. The first one is called spoken signatures where the user signs and says the content of the signature. The second scenario is based on spoken handwriting where the user is prompted to write and read the content of sentences randomly extracted from a text. Data according to these two scenarios have been recorded from a set of 70 users. In the first part of this paper, we describe the acquisition procedure, and we comment on the viability and usability of such simultaneous recordings. Our conclusions are supported by a short survey performed with the users. In the second part, we present the authentication systems that we have developed for both scenarios. More specifically, our strategy was to model independently both streams of data and to perform a fusion at the score level. Starting from a state-of-the-art-modeling algorithm based on Gaussian Mixture Models trained with an Expectation-Maximization procedure, we report on several significant improvements that are brought. As a general observation, the use of both modalities outperforms significantly the modalities used alone.

A self-paced BCI system to control an electric wheelchair: Evaluation of a commercial, low-cost EEG device

The electrical cerebral activity has been already used in several applications aiming at improving the daily life of impaired people with strong motor disabilities. In particular the Electroencephalogram signals (EEG) have been used to provide new ways for communication and control. However, such kind of technology presents some important drawbacks such as the price and the difficulty to prepare the system without an experts support. This work intends to build a user-friendly, self-paced Brain-Computer Interface (BCI) system that allows using commercial EEG headsets in order to drive an electrical wheelchair with a motor imagery approach. Furthermore, the conceived system has been used for a first evaluation of a commercial, low-cost, EEG device compared with data coming from a professional device. The result shows that the low cost EEG device, at the actual state of the art, provide interesting results but can hardly be used for self-paced systems in error sensitive context.

Newspaper page decomposition using a split and merge approach

Indexing large newspaper archives requires automatic page decomposition algorithms with high accuracy. In this paper, we present our approach to an automatic page decomposition algorithm developed for the First International Newspaper Segmentation Contest. Our approach decomposes the newspaper image into image regions, horizontal and vertical lines, text regions and title areas. Experimental results are obtained from the data set of the contest.

Modeling documents for structure recognition using generalized N-grams

We present and discuss a novel approach to modeling logical structures of documents, based on a statistical representation of patterns in a document class. An efficient and error tolerant recognition heuristics adapted to the model is proposed. The statistical approach permits easily automated and incremental learning of the model. The approach has been partially evaluated on a prototype. A discussion of the results achieved by the prototype is finally made.

Page segmentation of historical document images with convolutional autoencoders

In this paper, we present an unsupervised feature learning method for page segmentation of historical handwritten documents available as color images. We consider page segmentation as a pixel labeling problem, i.e., each pixel is classified as either periphery, background, text block, or decoration. Traditional methods in this area rely on carefully hand-crafted features or large amounts of prior knowledge. In contrast, we apply convolutional autoencoders to learn features directly from pixel intensity values. Then, using these features to train an SVM, we achieve high quality segmentation without any assumption of specific topologies and shapes. Experiments on three public datasets demonstrate the effectiveness and superiority of the proposed approach.