03-03-2017, 11:02 AM
The fingerprint recognition system is a reliable alternative to the conventional fingerprint recognition system. The tactile system is different from the conventional system in that they make use of the digital camera to acquire the fingerprint image where, like the conventional system, it uses live acquisition techniques. Conventional fingerprint systems are simple but suffer from various problems, such as hygiene, maintenance and latent fingerprints. In this article we present a review of fingerprint recognition systems using digital cameras. We present some challenging problems that occur while developing the touch-less system. These problems are of low contrast between the crest and valley pattern in the fingerprint image, non-uniform illumination, motion blurriness and defocus due to the shallower depth of field of the digital camera.
The fingerprint recognition system can be divided into three main modules: preprocessing, feature extraction and pairing. Preprocessing is an important step prior to fingerprint extraction and pairing. In this work we place our greatest emphasis on preprocessing so that the aforementioned drawbacks can be eliminated. The additional preprocessing is divided into four parts: the first is the normalization, the second is the fingerprint segmentation, the third is the improvement of the fingerprint and the last is the detection of the central point. Feature extraction can be done by Gabor filter or minutia extraction and mapping can be done by the help vector machine or main component analysis and three distance method.
The fingerprint recognition system can be divided into three main modules: preprocessing, feature extraction and pairing. Preprocessing is an important step prior to fingerprint extraction and pairing. In this work we place our greatest emphasis on preprocessing so that the aforementioned drawbacks can be eliminated. The additional preprocessing is divided into four parts: the first is the normalization, the second is the fingerprint segmentation, the third is the improvement of the fingerprint and the last is the detection of the central point. Feature extraction can be done by Gabor filter or minutia extraction and mapping can be done by the help vector machine or main component analysis and three distance method.