Search

P300 is a positive event-related potential used by P300-brain computer interfaces (BCIs) as a means of communication with external devices. One of the main requirements of any P300-based BCI is accuracy and time efficiency for P300 extraction and detection. Among many attempted techniques, independent component analysis (ICA) is currently the most popular P300 extraction technique. However, since ICA extracts multiple independent components (ICs), its use requires careful selection of ICs containing P300 responses, which limits the number of channels available for computational efficiency. Here, we propose a novel procedure for P300 extraction and detection using constrained independent component analysis (cICA) through which we can directly extract only P300-relevant ICs. We tested our procedure on two standard datasets collected from healthy and disabled subjects. We tested our procedure on these datasets and compared their respective performances with a conventional ICA-based procedure. Our results demonstrate that the cICA-based method was more reliable and less computationally expensive, and was able to achieve 97 and 91.6% accuracy in P300 detection from healthy and disabled subjects, respectively. In recognizing target characters and images, our approach achieved 95 and 90.25% success in healthy and disabled individuals, whereas use of ICA only achieved 83 and 72.25%, respectively. In terms of information transfer rate, our results indicate that the ICA-based procedure optimally performs with a limited number of channels (typically three), but with a higher number of available channels (>3), its performance deteriorates and the cICA-based one performs better.

We propose a method for increasing word recognition accuracies by correcting the output of a handwriting recognition system. We treat the handwriting recognizer as a black box, such that there is no access to its internals. This enables us to keep our algorithm general and independent of any particular system. We use a novel method for correcting the output based on a ''phrase-based'' system in contrast to traditional source-channel models. We report the accuracies of two in-house handwritten word recognizers before and after the correction. We achieve highly encouraging results for a large synthetically generated dataset. We also report results for a commercially available OCR on real data.

Despite several decades of research in document analysis, recognition of unconstrained handwritten documents is still considered a challenging task. Previous research in this area has shown that word recognizers perform adequately on constrained handwritten documents which typically use a restricted vocabulary (lexicon). But in the case of unconstrained handwritten documents, state-of-the-art word recognition accuracy is still below the acceptable limits. The objective of this research is to improve word recognition accuracy on unconstrained handwritten documents by applying a post-processing or OCR correction technique to the word recognition output. In this paper, we present two different methods for this purpose. First, we describe a lexicon reduction-based method by topic categorization of handwritten documents which is used to generate smaller topic-specific lexicons for improving the recognition accuracy. Second, we describe a method which uses topic-specific language models and a maximum-entropy based topic categorization model to refine the recognition output. We present the relative merits of each of these methods and report results on the publicly available IAM database.

The translation of non-invasive Brain-Computer Interfaces (BCI) from the only possible communication pathway for paralyzed patients into more widespread applications is limited by: the lack of effective, user-friendly and robust paradigms, low information transfer rates (ITR), and lack of suitable electroencephalography (EEG) recording platforms. This study addresses the last point by exploring the extent to which the recently introduced EarEEG technology, which provides an unobtrusive, discreet and user-friendly way of recording EEG, can be used in BCI applications. This was approached by comparing conventional on-scalp EEG and EarEEG recordings in a well-established visual P300 BCI setup. The two recording methods were compared qualitatively by comparing Event-Related Potential (ERP) waveforms, and quantitatively in terms of P300 signal-to-noise ratios (SNR) and ITRs of the BCI paradigm. The study showed similar ERP waveforms and on par P300 SNRs from both on-scalp and ear electrodes, and only a 6.5% decrease in single channel ITR for ear electrodes compared to on-scalp electrodes. This demonstrates that the EarEEG platform is a feasible technology for P300-based BCIs.

Feature extraction is one of the most important modules for Facial Expression Recognition (FER) systems, which deals with getting the distinguishable features each expression and quantizing it as a discrete symbol. In this paper, we have proposed the novel robust feature extraction technique for the FER systems called Stepwise Linear Discriminant Analysis (SWLDA). This technique focuses on the selection of localized features from the facial expression images and discriminate their classes on the basis of regression values i.e. partial F-test. The proposed technique is then compared with conventional techniques such as LDA in combination with ICA. The results shows that SWLDA better than conventional techniques in terms of robustness in suitable feature selection and classification.

Despite several decades of research in handwriting recognition, the goal of having computers access handwritten information from unconstrained document images is still elusive. Current handwriting recognition systems are only capable of recognizing words that are present in a restricted lexicon typically comprised of 10 to 1000 words. As the size of the lexicon grows, the recognition accuracy falls sharply and is reported to be around 30% for a10K word lexicon. The objective of this research is to raise the accuracy levels on unconstrained handwritten documents by reducing the size of lexicons. We present an innovative method of lexicon reduction by topic categorization of handwritten documents. After categorization of a document into a topic e.g. sports, science etc. we use smaller lexicons that include only words with high mutual information with that topic and hence increase performance of recognizers. In this paper we present different techniques and report results on a publicly available dataset.

Despite several decades of research in document analysis, recognition of unconstrained handwritten documents is still considered a challenging task. Previous research in this area has shown that word recognizers produce reasonably clean output when used with a restricted lexicon. But in absence of such a restricted lexicon, the output of an unconstrained handwritten word recognizer is noisy. The objective of this research is to process noisy recognizer output and eliminate spurious recognition choices using a topic based language model. We construct a topic based language model for every document using a training data which is manually categorized. A topic categorization sub-system based on Maximum Entropy model is also trained which is used to generate the topic distribution of a test document. A given test word image is processed by the recognizer and its word recognition likelihood is refined by incorporating topic distribution of the document and topic based language model probability. The proposed method is evaluated on a publicly available IAM dataset and experimental results show significant improvement in the word recognition accuracy from 32% to 40% over a test set consisting of 4033 word images extracted from 70 handwritten document images.

Automatic language identification is an important step prior to optical character recognition (OCR). In this paper we present a system to discriminate between Arabic and Persian in historical Afghan manuscripts. The classification is performed at a sub-sentence level. We propose a feature extraction algorithm for a sub-sentence based on Gabor filters followed by classification using a support vector machine (SVM). An overall precision of 96.72% and 94.90% is obtained for Persian and Arabic respectively.

In this paper we present a system for classification of machine printed and handwritten text in mixed documents. The classification is performed at the word level. We propose a feature extraction algorithm for each word image based on Gabor filters followed by classification using an expectation maximization (EM) based probabilistic neural network that reduces overfitting of training data. An overall precision of 94.62% was obtained for the Arabic script using the modified neural network. The accuracies obtained using a simple backpropagation neural network and an SVM were 83.33% and 90.26% respectively

In order to improve the readability and the automatic recognition of handwritten document images, preprocessing steps are imperative. These steps in addition to conventional steps of noise removal and filtering include text normalization such as baseline correction, slant normalization and skew correction. These steps make the feature extraction process more reliable and effective. Recently Arabic handwriting recognition has received some attention from the research community. Due to the unique nature of the script, the conventional methods do not prove to be effective. In our work, we describe an orientation independent technique for baseline detection of Arabic words. In addition to that we describe, in the rest of the paper, our techniques for slant normalization, slope correction, line and word separation in handwritten Arabic documents. We show how the baseline can be exploited for slope and skew correction before proceeding with the steps of line and word separation.