In this paper we have presented a technique for enhancement and retrieval of historic inscription images. Inscription images in general have no distinction between the text layer and background layer due to absence of color difference and possess highly correlated signals and noise; pertaining to which retrieval of such images using search based on feature matching returns inaccurate results. H...

This paper proposes a method to enhance text images for a system which extracts, recognizes and translates multi-lingual characters in scenery images captured by a digital camera. The proposed method magnifies text images in frequency domain. It restores high-frequency components by a DCT(Discrete Cosine Transform) based approach with an estimated enlarged image, and reduces mosquito and block ...

Using specialised text corpus to automatically enhance a general lexicon is the aim of this study. Indeed, having lexicons which offer maximal cover on a specific topic is an important benefit in many applications of Automatic Speech and Natural Language Processing. The enhancement of these lexicons can be made automatic as big corpora of specialised texts are available. A syntactic tagging pro...

UNLABELLED TPX is a web-based PubMed search enhancement tool that enables faster article searching using analysis and exploration features. These features include identification of relevant biomedical concepts from search results with linkouts to source databases, concept based article categorization, concept assisted search and filtering, query refinement. A distinguishing feature here is the ...

Electronic clinical documentation can be useful for activities such as public health surveillance, quality improvement, and research, but existing methods of de-identification may not provide sufficient protection of patient data. The general-purpose natural language processor MedLEE retains medical concepts while excluding the remaining text so, in addition to processing text into structured d...

We formally propose a new application problem: unsupervised text-image topic discovery. The application problem is important because almost all news articles have one picture associated. Unlike traditional topic modeling which considers text alone, the new task aims to discover heterogeneous topics from web news of multiple data types. The heterogeneous topic discovery is challenging because di...

In the main text, we have considered a single phonon branch which is coupled to the transfer integral between the electron bands. In a more realistic scenario, the system is coupled to multiple phonon branches, and the question we want to address here is whether or not this has a qualitative effect on the mechanism discussed in the main text. In the following, we first introduce another type of...

This paper covers a method for capturing documents using a digital camera. A typical cheap VGA digital camera (resolution 640 by 480 pixels) does not have adequate resolution to capture text over a page. By displacing the sensor spatially and taking multiple acquisitions we seek to enhance the resolution. There are many approaches in the literature to multi-frame reconstruction. Our approach di...

In this paper we discuss the enhancement of Arabic passage retrieval for both diacritisized and nondiacritisized text. Most previous work suggested that retrieval start with pre-processing the Arabic text to remove the diacritical marks (short vowels) to unify the text. In most cases, this process causes considerable ambiguity at the word level in the absence of context. However, searching for ...