Robust Extraction of Text from Camera Images using Colour and Spatial Information Simultaneously

The importance and use of text extraction from camera based coloured scene images is rapidly increasing with time. Text within a camera grabbed image can contain a huge amount of meta data about that scene. Such meta data can be useful for identification, indexing and retrieval purposes. While the segmentation and recognition of text from document images is quite successful, detection of coloured scene text is a new challenge for all camera based images. Common problems for text extraction from camera based images are the lack of prior knowledge of any kind of text features such as colour, font, size and orientation as well as the location of the probable text regions. In this paper, we document the development of a fully automatic and extremely robust text segmentation technique that can be used for any type of camera grabbed frame be it single image or video. A new algorithm is proposed which can overcome the current problems of text segmentation. The algorithm exploits text appearance in terms of colour and spatial distribution. When the new text extraction technique was tested on a variety of camera based images it was found to out perform existing techniques (or something similar). The proposed technique also overcomes any problems that can arise due to an unconstraint complex background. The novelty in the works arises from the fact that this is the first time that colour and spatial information are used simultaneously for the purpose of text extraction.

Confidence factor determination for performance evaluation of lighting pattern

In this paper the authors propose a new technique for determining a confidence factor applied to the performance prediction of individual luminaires within an overall pattern of luminaires. This work has relevance to any application where it is necessary to determine the performance of a lighting pattern e.g. street lighting, signal lighting etc. In this paper we apply our technique to a transportation application, namely, an airport landing lighting pattern. In the aviation industry it is imperative that the landing lighting pattern at individual airports performs according to standards. We have developed an automated technique which can be used to access the performance of luminaires within this pattern. We extend this work to also derive a confidence factor related to this prediction based on the quality of the data being utilised. ©2010 IEEE.

Modelling 3D camera movement for vibration characterisation and multiple object identification with application to lighting assessment

Utilising cameras as a means to survey the surrounding environment is becoming increasingly popular in a number of different research areas and applications. Central to using camera sensors as input to a vision system, is the need to be able to manipulate and process the information captured in these images. One such application, is the use of cameras to monitor the quality of airport landing lighting at aerodromes where a camera is placed inside an aircraft and used to record images of the lighting pattern during the landing phase of a flight. The images are processed to determine a performance metric. This requires the development of custom software for the localisation and identification of luminaires within the image data. However, because of the necessity to keep airport operations functioning as efficiently as possible, it is difficult to collect enough image data to develop, test and validate any developed software. In this paper, we present a technique to model a virtual landing lighting pattern. A mathematical model is postulated which represents the glide path of the aircraft including random deviations from the expected path. A morphological method has been developed to localise and track the luminaires under different operating conditions. © 2011 IEEE.

MHJ_0125 is an M42 glutamyl aminopeptidase that moonlights as a multifunctional adhesin on the surface of Mycoplasma hyopneumoniae

Bacterial aminopeptidases play important roles in pathogenesis by providing a source of amino acids from exogenous proteins, destroying host immunological effector peptides and executing posttranslational modification of bacterial and host proteins. We show that MHJ_0125 from the swine respiratory pathogen Mycoplasma hyopneumoniae represents a new member of the M42 class of bacterial aminopeptidases. Despite lacking a recognizable signal sequence, MHJ_0125 is detectable on the cell surface by fluorescence microscopy and LC-MS/MS of (i) biotinylated surface proteins captured by avidin chromatography and (ii) peptides released by mild trypsin shaving. Furthermore, surface-associated glutamyl aminopeptidase activity was detected by incubation of live M. hyopneumoniae cells with the diagnostic substrate H-Glu-AMC. MHJ_0125 moonlights as a multifunctional adhesin, binding to both heparin and plasminogen. Native proteomics and comparative modelling studies suggest MHJ_0125 forms a dodecameric, homopolymeric structure and provide insight into the positions of key residues that are predicted to interact with heparin and plasminogen. MHJ_0125 is the first aminopeptidase shown to both bind plasminogen and facilitate its activation by tissue plasminogen activator. Plasmin cleaves host extracellular matrix proteins and activates matrix metalloproteases, generating peptide substrates for MHJ_0125 and a source of amino acids for growth of M. hyopneumoniae. This unique interaction represents a new paradigm in microbial pathogenesis.

Hydrogeochemistry and Arsenic Contamination of Groundwater in the Haor Basins of Bangladesh

Hydrogeochemical relationships and the level of arsenic (As) contamination of groundwater in the Haor Basin, a low-lying, semi-natural, region of remnant wetland environs to the northeast of Bangladesh, were studied to assess the As biogeochemical cycling. Most of the shallow and deep tubewells in the study area are contaminated with As (2-331 mu g/l). The relatively higher proportions of Na+ (8-156 mg/l) in groundwater suggest a mixing of connate marine water with freshwater aquifer. Non-significant association between As and PO43- has been found. Highly significant (P <0.001) relationship of As with DOC in groundwater indicates biodegradation of organic matter, creating an overall reducing environment in the aquifer sediments, which facilitates the release of As in the groundwater. The inverse As-Fe, As-Mn, As-Ca and As-Mg relationships in groundwater could be related to the precipitation of Fe-, Mn-, Ca-and Mg-minerals.