Model-based character recognition in low resolution

We propose a combined character separation and recognition approach for low-resolution images of alphanumeric text. By synthesising the image formation process a set of low-resolution templates is created for each character. Cluster algorithms and normalised cross-correlation are then applied to match these templates and thereby allowing both character separation and recognition to be achieved at the same time. Thus characters are recognised using their low-resolution appearance only without applying image enhancement methods. Experiments showed that this approach is able to recognise low-resolution alphanumeric text of down to 5 pixels in size.

Polar transformation system for offline handwritten character recognition

Offline handwritten recognition is an important automated process in pattern recognition and computer vision field. This paper presents an approach of polar coordinate-based handwritten recognition system involving Support Vector Machines (SVM) classification methodology to achieve high recognition performance. We provide comparison and evaluation for zoning feature extraction methods applied in Polar system. The recognition results we proposed were trained and tested by using SVM with a set of 650 handwritten character images. All the input images are segmented (isolated) handwritten characters. Compared with Cartesian based handwritten recognition system, the recognition rate is more stable and improved up to 86.63%.

Portable form filling assistant for the visually impaired

The filling of printed forms has always been an issue for the visually impaired. Though optical character recognition technology has helped many blind people to ‘read’ the world, there is not a single device that allows them to fill out a paper-based form without a human assistant. The task of filling forms is however an essential part of their daily lives, for example, for access to social security or benefits. This paper describes a solution that allows a blind person to complete paper-based forms, pervasively and independently, using only off-the-shelf equipment including a Smartphone, a clipboard with sliding ruler, and a ballpoint pen. A dynamic color fiduciary (point of reference) marker is designed so that it can be moved by the user to any part of the form such that all regions can be “visited”. This dynamic color fiduciary marker is robust to camera focus and partial occlusion, allowing flexibility in handling the Smartphone with embedded camera. Feedback is given to the blind user via both voice and tone to facilitate efficient guidance in filling out the form. Experimental results have shown that this prototype can help visually impaired people to fill out a form independently.

Using a circular grid for offline handwritten character recognition

Offline handwritten recognition is more challenging as indicated by the recognition technologies. This study demonstrates significantly higher rates recognition when compared with other comparable studies. In this paper, we present a circular grid zoning method applied on Polar transformation recognition system. It compares the circular grid zoning (CGZ) and standard zoning (SZ) feature extraction method on Polar and Cartesian coordinate system. We report recognition rates of 92.3%, which are considerably higher than previous studies of zoning based Polar transformation system (86.6%) and zoning based Cartesian recognition system (80.6%). Based on the finding, we propose that our circular grid zoning based Polar transformation system may provide improved classification rates for complex offline handwritten recognition.

Efficient Coxian duration modelling for activity recognition in smart environment with the hidden semi-Markov model

In this paper, we exploit the discrete Coxian distribution and propose a novel form of stochastic model, termed as the Coxian hidden semi-Makov model (Cox-HSMM), and apply it to the task of recognising activities of daily living (ADLs) in a smart house environment. The use of the Coxian has several advantages over traditional parameterization (e.g. multinomial or continuous distributions) including the low number of free parameters needed, its computational efficiency, and the existing of closed-form solution. To further enrich the model in real-world applications, we also address the problem of handling missing observation for the proposed Cox-HSMM. In the domain of ADLs, we emphasize the importance of the duration information and model it via the Cox-HSMM. Our experimental results have shown the superiority of the Cox-HSMM in all cases when compared with the standard HMM. Our results have further shown that outstanding recognition accuracy can be achieved with relatively low number of phases required in the Coxian, thus making the Cox-HSMM particularly suitable in recognizing ADLs whose movement trajectories are typically very long in nature.

Hierarchical hidden Markov models with general state hierarchy

The hierarchical hidden Markov model (HHMM) is an extension of the hidden Markov model to include a hierarchy of the hidden states. This form of hierarchical modeling has been found useful in applications such as handwritten character recognition, behavior recognition, video indexing, and text retrieval. Nevertheless, the state hierarchy in the original HHMM is restricted to a tree structure. This prohibits two different states from having the same child, and thus does not allow for sharing of common substructures in the model. In this paper, we present a general HHMM in which the state hierarchy can be a lattice allowing arbitrary sharing of substructures. Furthermore, we provide a method for numerical scaling to avoid underflow, an important issue in dealing with long observation sequences. We demonstrate the working of our method in a simulated environment where a hierarchical behavioral model is automatically learned and later used for recognition.

Automatic face recognition for film character retrieval in feature-length films

The objective of this work is to recognize all the frontal faces of a character in the closed world of a movie or situation comedy, given a small number of query faces. This is challenging because faces in a feature-length film are relatively uncontrolled with a wide variability of scale, pose, illumination, and expressions, and also may be partially occluded. We develop a recognition method based on a cascade of processing steps that normalize for the effects of the changing imaging environment. In particular there are three areas of novelty: (i) we suppress the background surrounding the face, enabling the maximum area of the face to be retained for recognition rather than a subset; (ii) we include a pose refinement step to optimize the registration between the test image and face exemplar; and (iii) we use robust distance to a sub-space to allow for partial occlusion and expression change. The method is applied and evaluated on several feature length films. It is demonstrated that high recall rates (over 92%) can be achieved whilst maintaining good precision (over 93%).

Efficient design of polarization insensitive polymer optical waveguide devices considering stress-induced effects

We present an approach for the efficient design of polarization insensitive polymeric optical waveguide devices considering stress-induced effects. In this approach, the stresses induced in the waveguide during the fabrication process are estimated first using a more realistic model in the finite element analysis. Then we determine the perturbations in the material refractive indices caused by the stress-optic effect. It is observed that the stresses cause non-uniform optical anisotropy in the waveguide materials, which is then incorporated in the modal analysis considering a multilayer structure of waveguide. The approach is exploited in the design of a Bragg grating on strip waveguide. Excellent agreement between calculated and published experimental results confirms the feasibility of our approach in the accurate design of polarization insensitive polymer waveguide devices.

A comparison of Australian and Malaysian views on the use of biometric devices in everyday situations

Since the September 11, 2001 terrorist attacks in New York City, many countries including Australia and Malaysia have been able to justify the use biometric devices such as finger print scans, retina scans and facial recognition for identification and surveillance of its citizens and others in the name of national security. In addition, biometric devices are increasingly being used worldwide by organizations to keep track of their employees and their productivity, leading to concerns of privacy, the safety, reliability, abuse and misuse of the data collected and violations of civil liberties. Taking the critical theory perspective, this paper will analyse the data collected and report on the findings of a survey carried out in Australia and Malaysia, with respect to the responses provided and opinions expressed to the survey s open ended and other questions
by individuals as to their current use, experiences, preferences, concerns about the devices and the situations in which they think biometric devices should be used, including in their workplaces. This descriptive study uses both quantitative and qualitative data to examine what Australians and Malaysians think about the use of biometric devices in everyday situtions
and compare them as to their similarities and differences. The paper will then critically examine the ethical and civil liberties issues involved in the use of biometric devices in everyday life and argues that regulatory and legal measures should be taken to safeguard the rights of citizens while maintaining national security and productivity, in order to avoid the situation of Michel Foucaults Panopticon becoming an unpleasant everyday reality, which could negatively irifluence socialjustice and create social change due to its effects on individuals in two multicultural societies. The paper will argue about the need to educate the general public as to the issues of surveillance and privacy involved in the use of biometric devices in everyday situations.

A comparative analysis of opinions of Americans, Australians and Malaysians on the use of biometric devices in workplaces for security and monitoring of worker productivity

Since the September 11, 2001 terrorist attacks in New York, the use of biometric devices such as fingerprint scans, retina and iris scans and facial recognition in everyday situations for national security and border control, have become commonplace. This has resulted in the biometric industry moving from being a niche technology to one that is ubiquitous. As a result. more and more employers are using biometrics to secure staff access to their facilities as well as for tracking staff work hours, maintaining 'discipline' and carry out surveillance against thefts. detecting work hour abuses and fraud. However, the data thus collected and the technologies themselves are feared of having the potential for and actually being misused - both in terms of the violating staff privacy and discrimination and oppression of targeted workers. This paper examines the issue of using biometric devices in organisational settings their advantages, disadvantages and actual and potential abuses from the point of view of critical theory. From the perspectives of Panoptic surveillance and hegemonic organisational control, the paper examines the issues related to privacy and identification, biometrics and privacy, biometrics and the 'body', and surveillance and modernity. The paper also examines the findings ofa survey carried out in Australia. Malaysia and the USA on respondents' opinions on the use of biometric devices in everyday life including at workplaces. The paper concludes that along with their applications in border control and national security, the use of biometric devices should be covered by relevant laws and regulations. guidelines and codes of practice. in order to balance the rights to privacy and civil liberties of workers with employers' need for improved productivity, reduced costs, safeguards related to occupational health and safety, equal opportunity, and workplace harassment of staff and other matters, that employers are legally responsible for.