Camera Text Recognition based on Perspective Invariants (2009)
As camera resolution increases, high-speed non-contact text capture through a digital camera is opening up a new channel for document capture and understanding. Unfortunately, perspective and...
A Fast Keyword-Spotting Technique (2009)
Linlin Li, Shijian Lu, Chew Lim Tan
In order to capture the content of an imaged document but avoid the time-consuming full-scale OCR which is fragile to handle touching characters, a fast and segmentationfree keyword spotting method...
Identification of Latin-based Languages through Character Stroke Categorization (2009)
Shijian Lu, Linlin Li, Chew Lim Tan
This paper presents a language identification technique that detects Latin-based languages of imaged documents without OCR. The proposed technique detects languages through the word shape coding,...
This paper presents an automatic orientation detection and categorization technique that is capable of detecting the orientation of multilingual documents with arbitrary skew and categorizing...
Automatic Acquisition of Task Models From Objet Oriented Design Specifications: A Case Study (2008)
Task analysis and modelling have been successfully employed in training, design evaluation, and user documentation productopn. However, building task models from scratch can be a time consuming...
Keyword Spotting and Retrieval of Document Images Captured by a Digital Camera (2008)
This paper presents a keyword spotting technique that locates keywords within document images captured by a digital camera. In the proposed technique, the shape of word images in perspective view is...
Cécile Paris, Keith V, Er Linden, Nathalie Colineau, Shijian Lu
This paper presents an environment that supports the production of instructions, exploiting methodologies and technologies from Human-Computer-Interaction, Natural Language Processing and Software...
†CSIRO/CMIS, Locked Bag 17, (2008)
Shijian Lu, Cécile Paris, Keith V, Er Linden, Nathalie Colineau
The importance of task analysis and modelling to software system development is well recognised. After all, the central mission for most software systems is to help users accomplish their tasks....
Binarization of Badly Illuminated Document Images through Shading Estimation and Compensation (2008)
This paper presents a document image binarization technique that segments text from badly illuminated document images. Based on the observations that text documents normally lie over a planar or...
Fast and Accurate Detection of Document Skew and Orientation (2008)
Shijian Lu, Jie Wang, Chew Lim Tan
This paper presents a document skew and orientation detection technique. The proposed technique estimates document skew and orientation based on the observation that text images normally hold a large...
Stefanie Kethers, Peter Lamb, Shijian Lu, Cécile Paris, Ross Wilkinson, Kathleen Griffiths
Mental health is designated an Australian health priority and is recognized as the third largest source of Australia’s disease burden, after cardiovascular disease and cancer. In particular,...
Keith V, Er Linden, Cecile Paris, Shijian Lu
Abstract. Instructional text has been a popular target for research-oriented generation systems because it is a useful and relatively constrained sublanguage. The success of these systems shows that...
Retrieval of Machine-printed Latin Documents through Word Shape Coding Abstract (2008)
This paper reports a document retrieval technique that retrieves machine-printed Latin-based document images through word shape coding. Adopting the idea of image annotation, a word shape coding...
Automatic Detection of Document Script and Orientation (2008)
This paper presents an identification technique that automatically detects the underlying script and orientation of scanned document images. In the proposed technique, document script and orientation...
Cecile Paris, Nathalie Colineau, Shijian Lu, Keith Vander Linden
Instructional text, and procedural text in particular, is a genre that users heavily rely upon when they are learning new procedures, devices or systems. It is, however, also well-known to be a genre...
A Graphic Page Image Processing System (2008)
Linlin Li, Shijian Lu, Chew Lim Tan
Abstract. Patent images maintained by the U.S. patent database have figures and related description separated in different pages. This makes it difficult for users to refer to a figure while reading...
Computer Aided Task Model Acquisition From Heterogeneous Sources (2008)
Shijian Lu, Cécile Paris, Keith V, Er Linden
Task models have proven useful in many different areas, including user requirements analysis, user interface design, user documentation generation and usability evaluation. However, building task...
Abstract As the amount of information available to people multiplies at an increasing speed, it becomes ever more important to deliver information customised to users ’ specific needs. Natural...
Cecile Paris, Nathalie Colineau, Shijian Lu, Keith Vander Linden
Instructional text, and procedural text in particular, is a genre that users heavily rely upon when they are learning new procedures, devices or systems. It is, however, also well-known to be a genre...
John Artim, John Artim, Mark Van Harmelen, Mark Van Harmelen, Keith Butler, Keith Butler, ...
Reports can be ordered from:
Thresholding of Badly Illuminated Document Images through Photometric Correction (2007)
This paper presents a document image thresholding technique that binarizes badly illuminated document images by the photometric correction. Based on the observation that illumination normally varies...
A partition approach for the restoration of camera images of plannar and curled document (2006)
Shijian Lu, Ben M. Chen, C. C. Ko
As camera resolution increases, high-speed non-contact text capture through a digital camera is opening up a new channel for text capture and understanding. Unfortunately, the captured document...
Document flattening through grid modeling and regularization (2006)
For document images captured by a digital camera, perspective and geometric distortions make it hard to recognize the document content properly. In this paper, we propose an integrated document...
Script and language identification in degraded and distorted document images (2006)
Shijian Lu, Chew Lim Tan, Weihua Huang
Abstract. This paper presents a language identification technique that differentiates Latin-based languages in degraded and distorted document images. Different from the reported methods that...
The restoration of camera documents through image segmentation (2006)
Abstract. This paper presents a document restoration technique that is able to flatten curled document images captured through a digital camera. The proposed method corrects camera images of...
Perspective rectification of document images using fuzzy set and morphological operations (2005)
Shijian Lu, Ben M. Chen, C. C. Ko
In this paper, we deal with the problem of document image rectification from image captured by digital cameras. The improvement on the resolution of digital camera sensors has brought more and more...
Myriad: An Architecture for Contextualized Information Retrieval and Delivery (2004)
Cécile Paris, Mingfang Wu, Keith V, Er Linden, Matthew Post, Shijian Lu
Abstract. Users ’ information needs are largely driven by the context in which they make their decisions. This context is dynamic. It includes the users ’ characteristics, their current domain of...
Myriad: An Architecture for Contextualized Information Retrieval and Delivery (2004)
Cécile Paris, Mingfang Wu, Keith V, Er Linden, Matthew Post, Shijian Lu
Abstract. Users ’ information needs are largely driven by the context in which they make their decisions. This context is dynamic. It includes the users ’ characteristics, their current domain of...
Environments for the Construction and Use of Task Models (2003)
Cécile Paris, Shijian Lu, Keith V, Er Linden
Task models are useful because they support the design and evaluation of interactive systems from the point of view of the intended users. Unfortunately, they are also difficult to build. To help...
K.: Tamot: Towards a flexible task modelling tool (2002)
Shijian Lu, Cécile Paris, Keith V, Er Linden
The usefulness of task analysis and task modeling has been widely acknowledged in software design and development. However, the rate of adoption of task analysis and modeling has been painstakingly...
Generating Personal Travel Guides from Discourse Plans (2000)
Ross Wilkinson, Shijian Lu, François Paradis, Cécile Paris, Stephen Wan, Mingfang Wu
This paper describes a system that delivers travel guides tailored to individual needs. It does so by integrating a discourse planner with a system for querying the web and generating synthesised web...
Generating Personal Travel Guides from Discourse Plans (2000)
Shijian Lu, François Paradis, Cécile Paris, Stephen Wan, Ross Wilkinson, Mingfang Wu
This paper describes a system that delivers travel guides tailored to individual needs. It does so by integrating a discourse planner with a system for querying the web and generating synthesised web...
Towards the Automatic Construction of Task Models from Object-Oriented Diagrams (1998)
Shijian Lu, Cécile Paris, Keith V, Er Linden
Abstract: Task models bridge the gap between HCI and Software Engineering. They are useful both for interface design and for generating user interface code and user documentation. These benefits,...
Niels Ole Bernsen, Shijian Lu, Michael May
This paper presents the layout and functionality of Version 2 of the Taxonomy Workbench and Theory Demonstrator which is being developed at the Centre for Cognitive Science. The Theory Demonstrator...