LVQ base models for recognition of human faces

Int. J. Patt. Recogn. Artif. Intell.

Laghari

2002

In this paper an learning vector quantization network architecture based on varying parameters and eliminating blind neurons 28 is developed that learns the correlation of gender patterns and recognizes facial expressions of human faces. The network is developed to classify the 1 -neutral, 2 -smile or happiness, 3 -anger and 4 -scream or fear expressions. A peak accuracy rate of (a) 100% on the expression recognition task and (b) 100% on the gender recognition task for random training and test samples is achieved. The computer execution time for the recognition is about 0.004 seconds per face image for the latex expression classification task and 0.02 for the gender recognition task on an IBM PC. It is demonstrated that the proposed architecture is capable of achieving better recognition results with both good generalization performance and a fast training-time on a variety of test problems. The developed system showed potential for real life application domains.

“…28 These neurons do not see the faces, which are clamped to the neurons of the input layer. Survival of the fittest neurons are then crucial to the progress of the learning process.…”

Section: Invariant Facial Expression and Gender Recognition 29mentioning

confidence: 99%

Section: Algorithmmentioning

confidence: 99%

A Parameter-Based Combined Classifier for Invariant Facial Expression and Gender Recognition

Int. J. Patt. Recogn. Artif. Intell.

Laghari

2002

“…The fingerprint images are matched based on features extracted with an adaptive learning vector quantization (LVQ) neural network compact architecture. 22 The neural network approach has long been in use for pattern recognition and has recently been adopted for biometric fingerprint identification. The inkless images are acquired for this purpose using a digital still camera (see Fig.…”

Section: Introductionmentioning

confidence: 99%

Data Acquisition and Recognition of Fingerprints With LVQ

Int. J. Comp. Intel. Appl.

Abu-Rezq

2003

A typical biometric system has three distinct phases. These are biometric data acquisition, feature extraction, and decision-making. The first step, the acquisition phase, is extremely important. If high quality images are not obtained, the next phase cannot operate reliably. Fingerprint recognition remains as one of the most prominent biometric identification methods. In this paper, we develop a prototype optical-based fingerprints data acquisition system using a CCD digital still camera to capture a complete impression of finger area required for accurately identifying an individual and present an image-based approach for online fingerprint recognition with the objective to increase the overall matching performance. The fingerprint images are matched based on features extracted with an adaptive learning vector quantization (LVQ) neural network to yield peak recognition of 98.6% for a random set of 300 test prints (100 fingers × 3 images). This system can be adopted as a multi-modal biometrics where two or more fingers are matched.personal identification has become a very important topic. Accurate automatic personal identification is now needed in a wide range of civilian applications involving the use of passports, cellular phones, automatic teller machines, and driver licenses.Among all the biometrics: fingerprints, face, hand geometry, iris, retina, signature, voice print, facial thermogram, hand vein, gait, ear, odor, keystroke dynamics, etc. fingerprint-based identification is one of the most mature and proven technique because of their immutability and individuality. 2 Immutability refers to the permanent and unchanging character of the pattern on each finger from before birth until decomposition after death. Individuality refers to the uniqueness of ridge details across individuals even our own two hands are never quite alike.Computer vision based techniques that recognize human features such as faces, fingerprints, palms, and eyes have many applications in surveillance and security. 3-5 Some of these include magnetic swipe cards, pin numbers, signature, handwriting, voice, and fingerprint recognition. Some of the advantages of fingerprint recognition are that the fingerprint cannot be forged, stolen, or lost. A fingerprint recognition system would only require the user to place his or her hand on a platform for image capture and analysis.The fingerprint sensors are becoming smaller and cheaper, automatic identification based on fingerprints is becoming an attractive alternative/complement to the traditional methods of identification. The critical factor in the widespread use of fingerprints is in satisfying the performance (e.g. matching speed and accuracy) requirements of the emerging civilian identification applications. Some of these applications (e.g. fingerprint-based smart cards) will also benefit from a compact representation.The goal of fingerprint classification is to assign a fingerprint a specific class according to its geometric properties. 6 Fingerprints are full of ridge and valley structur...

“…This means that after convergence, some neurons will be redundant in the sense that they do not evolve significantly and thus do not capture any data structure. Visualizing the learned pattem of the hidden layer neurons, it is found that there are neurons with completely blurred patterns, blind neurons [5], as these neurons did not see the images which are clamped to the neurons of the input layer. Survival of the fittest neurons is then crucial to the progress of the learning process.…”

Section: Lvq Base Modelsmentioning

confidence: 99%

“…The fingerprint images are matched based on features extracted with an adaptive learning vector quantization (LVQ) neural network compact architecture [5]. The neural network approach has long been in use for pattem recognition and has recently been adopted for biometric fingerprint identification.…”

Section: Introductionmentioning

confidence: 99%

Fingerprint identification with LVQ

Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02.

Self Cite

Biometrics, which refers to identifying an individual based on his or her physiological or behavioral characteristics, has the capability to reliably distinguish between an authorized person and an imposter. This paper presents a high speed and low cost system for identification of fingerprints based on adaptive learning vector quantization neural network. The inkless images are acquired for this purpose using a digital still camera.