We present an analysis and demonstration of using laser-speckle contrast imaging (LSCI) as a sensing modality for presentation attack detection in biometric authentication systems. We provide the design of an experimental testbed for the quantitative characterization of LSCI and measurement results for optimization of the parameters of the active imaging testbed. LSCI has traditionally been used as a qualitative tool for identification of blood flow in dermal micro-vasculature for diagnosis of tissue health. We have built a laboratory phantom model, simulating blood flow beneath diffuse tissue to enable quantitative characterization of the performance of LSCI as a function of both target and imaging system parameters. Our first testbed configuration was an objective LSCI setup, detecting unfocused light on a focal plane array. In objective configuration, we characterized speckle size and speckle contrast as a function of the testbed parameters. In the second testbed configuration, we evaluated the performance of objective LSCI for complex fluid flow scenes. Finally, we report on the quantitative measurement of speckle contrast as a function of fluid flow rate, thereby demonstrating the use of optimized LSCI as an important sensing modality for the detection of presentation attacks in biometric authentication systems.
In this paper, we present a novel method for extracting handwritten and printed text zones from noisy document
images with mixed content. We use Triple-Adjacent-Segment (TAS) based features which encode local shape
characteristics of text in a consistent manner. We first construct two codebooks of the shape features extracted
from a set of handwritten and printed text documents respectively. We then compute the normalized histogram
of codewords for each segmented zone and use it to train a Support Vector Machine (SVM) classifier. The
codebook based approach is robust to the background noise present in the image and TAS features are invariant
to translation, scale and rotation of text. In experiments, we show that a pixel-weighted zone classification
accuracy of 98% can be achieved for noisy Arabic documents. Further, we demonstrate the effectiveness of our
method for document page classification and show that a high precision can be achieved for the detection of
machine printed documents. The proposed method is robust to the size of zones, which may contain text content
at line or paragraph level.
In this paper, a new formulation for the parametric active contour
model is presented. The new formulation is based on statistical
pattern recognition theory. A hybrid of kernel density estimation
and fuzzy logic is used to show that active contours can be
thought of as a pattern recognition problem. The proposed approach
is used in two different application domains, with different
performance requirements, to demonstrate its effectiveness. First,
the proposed approach is used for a magnetic resonance image
segmentation problem to demonstrate the segmentation accuracy.
Second, the contour is used in a target tracking experiment to
show its tracking capabilities.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.