ANN based fingerprint image ROI segmentation

Stojanović, Branka; Nešković, Aleksandar N.; Popovic, Zdravko; Lukic, Vojislav

doi:10.1109/telfor.2014.7034457

Cited by 11 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sometimes, two hidden layers will be used for more complicated problems. Multiple papers have been published on MLP neural network applications, for example on fingerprint image region of interest segmentation [20], high-electron-mobility transistor (HEMT) modelling [21], and the modelling of terminal electrical noise in semiconductor lasers [22]. The basic feature of an ANN is the capability to learn the patterns of the input samples to predict the system behaviour.…”

Section: Multilayer Perceptron and Gaussian Processmentioning

confidence: 99%

Transmission line impulse response modelling using machine learning techniques

Lim,

How,

Goay

et al. 2023

IJ-AI

View full text Add to dashboard Cite

<p>Conventional methods of circuit simulation such as full-wave electromagnetic ﬁeldsolvers can be very slow. Machine learning is an emerging technology in modelling, simulation, optimization, and design that present attractive alternatives to the conventional methodologies because they can be trained with a small amount of data, and then used to perform fast circuit predictions within the same design space. In this paper, we present applications of machine learning techniques for the modelling of transmission lines from their impulse reponses. The standard multilayer perceptron (MLP) neural network and the gaussian process (GP) regression techniques are demonstrated, and<br />both models are successfully implemented to model the impulse responses of transmission lines with great accuracies. We show that the GP outperforms the MLP in terms of prediction accuracies and that the GP is more data efﬁcient than the MLP. This is beneﬁcial considering that each training sample is expensive, making the GP a good candidate for the task, compared to the more popular MLP.</p>

show abstract

Section: Multilayer Perceptron and Gaussian Processmentioning

confidence: 99%

Transmission line impulse response modelling using machine learning techniques

Lim,

How,

Goay

et al. 2023

IJ-AI

View full text Add to dashboard Cite

show abstract

“…The method presented in this paper is based on two related approaches -NN-based methods for single fingerprint image ROI segmentation [20,30] that were trained and tested on fingerprint images of good quality (i.e. not latents).…”

Section: Description Of the Algorithmsmentioning

confidence: 99%

“…not latents). These approaches differ in the way by which inputs are presented to the NNs -the first approach uses pixel values contained in image blocks [30], whereas the second one uses Fourier coefficients calculated on the image blocks [20]. Both approaches present fingerprint image blocks' representations as input to previously trained NNs, which classify them as either ROI or background blocks, and consist of the same basic steps:…”

Section: Description Of the Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning‐based approach to latent overlapped fingerprints mask segmentation

Stojanović

Marques

Nešković

2018

IET Image Processing

View full text Add to dashboard Cite

“…The filtered image is again normalized; and is binarized using an empirical threshold. RoI segmentation built upon Artificial Neural Network (ANN) is devised [22]. The trained ANN decides whether the specific FI section is a part of RoI or not.…”

Section: Related Workmentioning

confidence: 99%

Enhancement of Latent Fingerprint Images with Segmentation Perspective

Baig

Huqqani

Khurshid

2015

2015 11th International Conference on Signal-Image Technology &Amp; Internet-Based Systems (SITIS)

View full text Add to dashboard Cite

Latent fingerprints are of decisive influence when it comes to identifying suspects; as these are usually encountered at crime scenes. Also, these serve as a compelling evidence in a court of law. Some of the formidable challenges with latent fingerprints are deficient ridge information and poor ridge clarity due to background noise and non-linear distortions. An effective fingerprint enhancement scheme is suggested to meliorate the clarity and continuity of ridges and valleys in a latent fingerprint image. The proposed method deals with both local (minutia or singular points; ridge termination, bifurcation, broken ridges, short ridges, core and delta) and global features (ridge orientation and ridge frequency), while retaining the true ridge-valley structures and removing noise at the same time. The proposed design establishes scalability, accessibility and flexibility.

show abstract

ANN based fingerprint image ROI segmentation

Cited by 11 publications

References 13 publications

Transmission line impulse response modelling using machine learning techniques

Transmission line impulse response modelling using machine learning techniques

Deep learning‐based approach to latent overlapped fingerprints mask segmentation

Enhancement of Latent Fingerprint Images with Segmentation Perspective

Contact Info

Product

Resources

About