Wageeh W. Boles

A human identification technique using images of the iris and wavelet transform

A new approach for recognizing the iris of the human eye is presented. Zero-crossings of the wavelet transform at various resolution levels are calculated over concentric circles on the iris, and the resulting one-dimensional (1-D) signals are compared with model features using different dissimilarity functions.

Texture for script identification

The problem of determining the script and language of a document image has a number of important applications in the field of document analysis, such as indexing and sorting of large collections of such images, or as a precursor to optical character recognition (OCR). In this paper, we investigate the use of texture as a tool for determining the script of a document image, based on the observation that text has a distinct visual texture. An experimental evaluation of a number of commonly used texture features is conducted on a newly created script database, providing a qualitative measure of which features are most appropriate for this task. Strategies for improving classification results in situations with limited training data and multiple font types are also proposed.

Recognition of 2D object contours using the wavelet transform zero-crossing representation

A new algorithm to recognize a two-dimensional object of arbitrary shape is presented. The object boundary is first represented by a one-dimensional signal. This signal is then used to build the wavelet transform zero-crossing representation of the object. The algorithm is invariant to translation, rotation and scaling. Experimental results show that, compared with the use of Fourier descriptors, our algorithm gives more stable and accurate results.

Wavelet-based affine invariant representation: a tool for recognizing planar objects in 3D space

A technique is developed to construct a representation of planar objects undergoing a general affine transformation. The representation can be used to describe planar or nearly planar objects in a three-dimensional space, observed by a camera under arbitrary orientations. The technique is based upon object contours, parameterized by an affine invariant parameter and the dyadic wavelet transform. The role of the wavelet transform is the extraction of multiresolution affine invariant features from the affine invariant contour representation. A dissimilarity function is also developed and used to distinguish among different object representations. This function makes use of the extrema on the representations, thus making its computation very efficient. A study of the effect of using different wavelet functions and their order or vanishing moments is also carried out. Experimental results show that the performance of the proposed representation is better than that of other existing methods, particularly when objects are heavily corrupted with noise.

A review of medical image watermarking requirements for teleradiology.

Teleradiology allows medical images to be transmitted over electronic networks for clinical interpretation and for improved healthcare access, delivery, and standards. Although such remote transmission of the images is raising various new and complex legal and ethical issues, including image retention and fraud, privacy, malpractice liability, etc., considerations of the security measures used in teleradiology remain unchanged. Addressing this problem naturally warrants investigations on the security measures for their relative functional limitations and for the scope of considering them further. In this paper, starting with various security and privacy standards, the security requirements of medical images as well as expected threats in teleradiology are reviewed. This will make it possible to determine the limitations of the conventional measures used against the expected threats. Furthermore, we thoroughly study the utilization of digital watermarking for teleradiology. Following the key attributes and roles of various watermarking parameters, justification for watermarking over conventional security measures is made in terms of their various objectives, properties, and requirements. We also outline the main objectives of medical image watermarking for teleradiology and provide recommendations on suitable watermarking techniques and their characterization. Finally, concluding remarks and directions for future research are presented.

Investigation of Fish-Eye Lenses for Small-UAV Aerial Photography

Aerial photography obtained by unmanned aerial vehicles (UAVs) is a rising market for their civil application. Small UAVs are believed to close gaps in niche markets, such as acquiring airborne image data for remote sensing purposes. Small UAVs can fly at low altitudes, in dangerous environments, and over long periods of time. However, their small lightweight construction leads to new problems, such as higher agility and more susceptibility to turbulence, which has a big impact on the quality of the data and their suitability for aerial photography. This paper investigates the use of fish-eye lenses to overcome field-of-view (FOV) issues for highly agile UAV platforms susceptible to turbulence. The fish-eye lens has the benefit of a large observation area (large FOV) and does not add additional weight to the aircraft, such as traditional mechanical stabilizing systems. We present the implementation of a fish-eye lens for aerial photography and mapping purposes, with potential use in remote sensing applications. We describe a detailed investigation from the fish-eye lens distortion to the registering of the images. Results of the process are presented using low-quality sensors typically found on small UAVs. The system was flown on a midsize platform (a more stable Cessna aircraft) and also on ARCAAs small (<10 kg) UAV platform. The effectiveness of the approach is compared for the two sized platforms.

Scale invariant feature matching with wide angle images

Numerous scale-invariant feature matching algorithms using scale-space analysis have been proposed for use with perspective cameras, where scale-space is defined as convolution with a Gaussian. The contribution of this work is a method suitable for use with wide angle cameras. Given an input image, we map it to the unit sphere and obtain scale-space images by convolution with the solution of the spherical diffusion equation on the sphere which we implement in the spherical Fourier domain. Using such an approach, the scale-space response of a point in space is independent of its position on the image plane for a camera subject to pure rotation. Scale-invariant features are then found as local extrema in scale-space. Given this set of scale-invariant features, we then generate feature descriptors by considering a circular support region defined on the sphere whose size is selected relative to the feature scale. We compare our method to a naive implementation of SIFT where the image is treated as perspective, where our results show an improvement in matching performance.

Personal identification using images of the human palm

A prototype system for human identification using images of the palm is introduced. An image capture platform is constructed such that variation of the camera-to-palm distance is minimised to eliminate the need to compensate for scaling transformation. Appropriate lighting conditions are considered in order to enhance the palm features during image capture. The Hough transform is used to detect the palm features as approximated straight lines. Translation and rotation invariance are achieved by using the edge of the palm as a reference for all feature measurements.

Wide-angle Visual Feature Matching for Outdoor Localization

Wide-angle images exhibit significant distortion for which existing scale-space detectors such as the scale-invariant feature transform (SIFT) are inappropriate. The required scale-space images for feature detection are correctly obtained through the convolution of the image, mapped to the sphere, with the spherical Gaussian. A new visual key-point detector, based on this principle, is developed and several computational approaches to the convolution are investigated in both the spatial and frequency domain. In particular, a close approximation is developed that has comparable computation time to conventional SIFT but with improved matching performance. Results are presented for monocular wide-angle outdoor image sequences obtained using fisheye and equiangular catadioptric cameras. We evaluate the overall matching performance (recall versus 1-precision) of these methods compared to conventional SIFT. We also demonstrate the use of the technique for variable frame-rate visual odometry and its application to place recognition.

An application of wavelet-based affine-invariant representation

Recently, a novel technique used to construct an affine-invariant representation based on the dyadic wavelet transform was proposed and tested on synthesised 2D contours (Tieng and Boles, 1994). In this paper, the performance of this representation with real objects under perspective transformation is considered. In comparison with a similarity invariant (curvature) representation, experimental results show that the proposed affine-invariant representation is the most appropriate one to represent and recognise objects under perspective transform.