Florence Tushabe

Learn More
This work proposes a region-based shape signature that uses a combination of three different types of pattern spectra. The proposed method is inspired by the connected shape filter proposed by Urbach et al. We extract pattern spectra from the red, green and blue color bands of an image then incorporate machine learning techniques for application in(More)
Fusion of multiple impressions resulting from multiple fingerprint enrollments is one of the ways often used to improve fingerprint recognition performance. In this research, we perform an evaluation of the effectiveness of using multiple enrollment in fingerprint recognition systems. We design a multiple enrollment algorithm and use it together with(More)
This paper proposes a new method of processing color images using mathematical morphology techniques. It adapts the Max-tree image representation to accommodate color and other vectorial images. The proposed method introduces three new ways of transforming the color image into a gray scale image that is filtered using conventional methods. Three new color(More)
This paper presents the results of using the shape, size and color features of an image for content-based image retrieval. The use of granulometries has been applied to model the size and shape of the connected components of the image. Granulometry are computed by successively sieving an image using filters of increasing size parameter so that information(More)
Multiple enrollment based fingerprint recognition systems have for long been known for good recognition accuracies. They however suffer poor matching speeds, a lot of memory consumption and the recognition accuracies are still very low; making implementation in real-world applications difficult. This paper presents a novel approach that performs prior(More)
Minutiae-based matching techniques have been widely used in the implementation of multiple enrollment fingerprint recognition systems. However, these techniques suffer the difficulty of automatically extracting all minutiae points due to failure to detect the complete ridge structures of a fingerprint. With poor quality fingerprint images, detection of(More)
As the enormous growth of information challenges the existing string analysis techniques for processing huge volume of data, there always seem to be a hope for newer inventions. Moreover, the problems encountered with the traditional methods such as low pruning power, increased false positives and poor scalability should be addressed with the appropriate(More)
Minutiae-based fingerprint matching methods suffer difficulty in automatically extracting all minutiae points due to failure to detect the complete ridge structures of a fingerprint, as well as describing all the local ridge structures as minutiae points. These make matching a difficult process for example, the case where two fingerprints have different(More)