Figure 4 - uploaded by Rene Van leuken
Content may be subject to copyright.
![Figure 2.6 Flowchart of enhancement algorithm proposed by Hong [2]](profile/Rene-Van-Leuken/publication/268041882/figure/fig3/AS:368280779935746@1464816388726/Flowchart-of-enhancement-algorithm-proposed-by-Hong-2_Q320.jpg)
Similar publications
A new theoretical approach to construction of efficient algo-
rithms for fingerprint image enhancement is proposed. The approach
comprises novel modifications of advanced orientation field estimation
techniques such as the method of fingerprint core extraction based on
Poincar ́e indexes and model-based smoothing for the gradient-based
approximatio...
In this paper, a new robust orientation estimation
for Coherence Enhancement Diffusion (CED)
is proposed. In CED, proper scale selection is very
important as the gradient vector at that
scale reflects the orientation of local ridge. For
this purpose, a new scheme is proposed in
which pre calculated orientation, by using orientat
ion diffusion,...
Citations
... The image was processed first with the widely used Hong method [10]. The method was later adopted by [18,23] and [5] for their hardware implementation for its computationally simple structure. Figure 1b depicts the result of Hong method. ...
... Although several FPGA implementations have been presented in the literature for fingerprint image normalization, most of them use the global mean and variance. Qin [18] implemented a fingerprint image normalization similar to the one proposed by [10]. In this implementation, global and local means as well as global and local variances are linearly mixed to process a 16Â16 block. ...
... Fons et al. [5] used an 8Â8 block instead of 16Â16. In this technique, parallel processing is used, which increases the overall speed of the system as compared to [18]. Vitabile et al. [23] also used Hong's technique for image normalization. ...
Global techniques do not produce satisfying and definitive results for fingerprint image normalization due to the non-stationary nature of the image contents. Local normalization techniques are employed, which are a better alternative to deal with local image statistics. Conventional local normalization techniques involve pixelwise division by the local variance and thus have the potential to amplify unwanted noise structures, especially in low-activity background regions. To counter the background noise amplification, the research work presented here introduces a correction factor that, once multiplied with the output of the conventional normalization algorithm, will enhance only the feature region of the image while avoiding the background area entirely. In essence, its task is to provide the job of foreground segmentation. A modified local normalization has been proposed along with its efficient hardware structure. On the way to achieve real-time hardware implementation, certain important computationally efficient approximations are deployed. Test results show an improved speed for the hardware architecture while sustaining reasonable enhancement benchmarks.
... Although several efficient FPGA implementations have been presented in the literature for separable as well as non-separable filters, research on the oriented-filter implementation on an FPGA is limited. Fons [15]- [18], Alilla [19], Qin [20] and Garcia [21] used conventional Gabor filters for FPGA-based fingerprint image enhancement. Qin used a 16×16 block for Gabor filter implementation. ...
... The accuracy of fingerprint recognition can be improved considerably by normalizing the image for background variations and contrast before filtering. In the literature, most researchers implement an adaptive normalization algorithm based on a local mean and variance [15]- [18], [20]. This type of normalization requires two processing passes of the whole image [15], [17], [18]. ...
... For complete fingerprint image enhancement, the proposed method is compared with two prominent FPGA-based fingerprint image-enhancement algorithms, one proposed by Fons [15] and the other proposed by Qin [20]. In the literature, Fons was the fastest and most efficient algorithm for fingerprint image enhancement. ...
A real-time image filtering technique is proposed which could result in faster implementation for fingerprint image enhancement. One major hurdle associated with fingerprint filtering techniques is the expensive nature of their hardware implementations. To circumvent this, a modified anisotropic Gaussian filter is efficiently adopted in hardware by decomposing the filter into two orthogonal Gaussians and an oriented line Gaussian. An architecture is developed for dynamically controlling the orientation of the line Gaussian filter. To further improve the performance of the filter, the input image is homogenized by a local image normalization. In the proposed structure, for a middle-range reconfigurable FPGA, both parallel computeintensive and real-time demands were achieved. We manage to efficiently speed up the image-processing time and improve the resource utilization of the FPGA. Test results show an improved speed for its hardware architecture while maintaining reasonable enhancement benchmarks.
... was later adopted by [184], [185], and [186] for their hardware implementation for its computationally simple structure. Fig. 6.2(b) depicts the result of Hong method. ...
... Although several FPGA implementations have been presented in the literature for fingerprint image normalisation, most of them use the global mean and variance. [184] implemented a fingerprint image normalisation similar to the one proposed by [60]. In this implementation, global and local means as well as global and local variances are linearly mixed to process a 16×16 block. ...
... [186] used an 8×8 block instead of 16×16. In this technique, parallel processing is used, which increases the overall speed of the system as compared to [184]. [185] also used Hong's technique for image normalisation. ...
A multimodal biometric system is considered to be more reliable for person identification. It uses multiple biometric credentials/traits to identify a person rather than a single biometric trait. It uses multiple sensors to acquire biometric traits. This system allows capturing either samples of multiple biometric traits or multiple samples of a single biometric trait. This system improves the accuracy and dependability by providing an optimal False Acceptance Rate (FAR) and False Rejection Rate (FRR).
Hardware implementation of a multimodal biometric system, in resources- constrained embedded systems, poses great challenges. Although there has been a substantial amount of work on combining different biometrics for a variety of purposes, not much work has focused on the hardware implementation of the multimodal biometric system. The aim of this dissertation is to build a reliable multimodal biometric system that takes into account multiple constraints: low cost, real-time processing, hygienic, straightforward, user-friendly, limited memory, etc. To achieve this, we present a hardware architecture of a multimodal biometric system that massively exploits the inherent parallelism.
The proposed system is based on multiple biometric fusions that use two biometric traits, fingerprint, and iris. In fingerprint feature extraction, several challenges are addressed that directly affect the minutiae extraction process like fingerprint normalization, scar removal, orientation estimation, fingerprint enhancement, binarization and thinning and feature extraction. In iris recognition, each individual block involved in feature extraction is optimised independently, including pupil segmentation, iris segmentation, normalisation and iris feature enhancement. After completing the software design, its hardware equivalent is implemented in VHDL. In both biometric identifiers, each sub-block operates in sequence. For example, in fingerprint identification, first normalisation is per- formed followed by image enhancement then binarization and thinning and finally feature extraction. This allows the hardware implementation to form a temporal parallelism. The temporal parallelism allows the design to be implemented com- ponent by component. Separate processors are used for each component to form a pipelined architecture for both biometrics. Finally, the extracted features are fused with matching-level fusion. To the best of the author’s knowledge, no other FPGA-based design that uses these two traits exists to date.
... The original Hong et al algorithm in [1] was executed on a Pentuim 200MHz PC and achieved a running time of 2.49s on the MSU fingerprint database. While the hardware implementation given in [22] achieved a running time of up to 0.742s. ...
Fingerprint enhancement is a crucial step in fingerprint recognition. The accuracy of the recognition algorithm directly depends on the accurate extraction of features which is achieved through a series of image en-hancement steps. Unfortunately, the fingerprint enhancement process consists of a series of computationally expensive image processing techniques. This results in slow recognition algorithms. Researchers have examined ways of improv-ing the performance of fingerprint enhancement algorithms through parallel processing. The majority of such techniques are architecture-or machine-specific and do not port well other platforms. We propose a cheaper and portable al-ternative through the utilization of mixed-mode distributed and parallel algorithms that make use of multicore clusters for processing strength. We tackle a few design concerns encountered when distributing image processing operations. One such concern is dealing with pixels along the borders of the partitioning axis. The other is distributing data that needs to be processed in blocks rather than pixel-wise.
In this paper, an algorithm is proposed to enhance fingerprint image which includes in one of its steps a smoothing process in which the suggested genetic algorithms by Mitras and Anwar in 2007 which used image smooth filters in both spatial and frequency domain will be employed to know their efficiency in enhancing and regaining the damaged sides of the fingerprint image to remove two types of noise, first one deals with noise added to the image, and the second one the noise already found in the image. Then histogram technique is used to enhance the fingerprint image.
In this paper, an algorithm is proposed to enhance fingerprint image which includes in one of its steps a smoothing process in which the suggested genetic algorithms by Mitras and Anwar in 2007 which used image smooth filters in both spatial and frequency domain will be employed to know their efficiency in enhancing and regaining the damage sides of the fingerprint image to remove two type of noise, first one deals with noise added to the image, and the second one the noise already found in the image. then histogram technique is used to enhance the fingerprint image.
Our objective of this project is to apply the theory of linear algebra called 'singular value decomposition (SVD)' to digital image processing, specifically for fingerprint images verification. For optimal recognition, we proceed in two steps. In the first step, we begin by identifying the fingerprint features with SVD approach. In the second step, the classification accuracy of the proposed approach is evaluated with Back Propagation Neural Network (BPNN) classifier. I have implemented many extensive experiments, they prove that the fingerprint classification based on a novel SVD features and the BPNN give better results in fingerprint verification than several other features and methods.
Our objective of this project is to apply the theory of linear algebra called 'singular value decomposition (SVD)' to digital image processing, specifically for fingerprint images verification. For optimal recognition, we proceed in two steps. In the first step, we begin by identifying the fingerprint features with SVD approach. In the second step, the classification accuracy of the proposed approach is evaluated with Back Propagation Neural Network (BPNN) classifier. I have implemented many extensive experiments, they prove that the fingerprint classification based on a novel SVD features and the BPNN give better results in fingerprint verification than several other features and methods.
This paper is concerned with novel features for fingerprint classification based on the Euclidian distance between the center point and their nearest neighbor bifurcation minutia's. The main advantage of the new method is the dimension reduction of the features vectors used to characterize fingerprint, compared with the classic characterization method based on the relative position of bifurcation minutia points. In addition, this new method avoids the problem of geometric rotation and translation over the acquisition phase. The characterization efficiency of the proposed method is compared with the method based on the spatial coordinate position of fingerprint minutia's. The comparison is based on a characterization criterion, usually used to evaluate the class quantification and the features discriminating ability. After that, the classification accuracy of the proposed approach is evaluated with Back Propagation Neural Network (BPNN). Extensive experiments prove that the Fingerprint classification based on a novel features and BPNN classifier give better results in fingerprint classification than several other features and methods.
