Recursive Learning Fuzzy Logic Model for Building Feature Extractor in Identification Biometric System
ثبت نشده
چکیده
vii صخلم ھلامعتساب كلذو ،ةیرتمویبلا فرعتلا ةمظنأ يف يبابضلا قطنملا قیبطت وھ انیدیأ نیب يتلا ةركذملا هذھ نم فدھلا يرتمویب ماظن يأ يف ةمھم ةلحرم يھ يتلاو روصلا نم ةیصخشلا صئاصخلا جرختسم ءانب يف . جذومنلا رایتخا مت لاود لامعتساب كلذو ةیلمعلا هذھل بسانملا يبابضلا ةمیقلل ةیطقن ءامتنا لاود و روصلا لسكب تایثادحلا ةیصوغ ءامتنا لسكبلل ةیدامرلا . بیردت ةیلمعل عضخی جذومنلا اذھ ریخلأا يف ربتعُتل ةمدقملا صخشلا ةروص عم ھتاجرخم بسانتتل صئاصخ عاعشك نرمملا جذومنلا اذھ رصانع صخشلل فرعم . ماظنب زھجملا بوساحلا لامعتسا ریخلأا يف متی بلاطاملا ثیح دیدجلا يرتمویبلا ماظنلا رابتخلا كلذو ،دحأ لكل ةروص رشع ينثاب صخش ةئامسمخ نم ةلكشم تامولعم ةدعاق اذكو ةحضوملا تانایبلا بسح ةدیج جئاتن ىلع لوصحلا مت . ةیللادلا تاملكلا : ،صئاصخلا جرختسم ،يبابضلا قطنملا ،يرتمویبلا ماظنلا Résumé L'objectif de cette mémoire est d'appliquer la logique floue dans les systèmes biométrique d'identification. Cette logique est utilisée exactement pour construire un extracteur de caractéristiques qu'est une étape essentielle dans le système biométrique. Pour cela, un modèle flou est choisi par ces fonctions d'appartenance des coordonnées de pixels d'image de type gaussien et celles de niveau de gri de type constants. Ce modèle est subi à une opération d'apprentissage afin de l'approcher à l'image en cours d'utilisation. Les paramètres de modèle apprenti sont les éléments du vecteur de caractéristique. Les tests de ce système biométrique sont fait à l'aide du logiciel Matlab et une base de données de 500 personnes de 12 images chacun. Les résultats obtenus justifient ce choix. Mots clés: Système biométrique, logique floue, image palmaire, apprentissage, vecteur de caractéristiques Abstract The objective of this dissertation is the integration of fuzzy logic to biometric systems for person identification. Fuzzy logic is used exactly to build the feature extractor of the biometric system. For this propose a fuzzy model for the image is chosen by selecting Gaussian membership functions for pixel coordinates and constants functions for gray level of pixels. The fuzzy model will be learned by an iterative procedure to extract the vector of characteristics. This biometric system is tested using Matlab software and a database of 500 persons with 12 images for each person. The results of simulation give good results with the FRR, FAR and EER values.
منابع مشابه
Security analysis of password hardened multimodal biometric fuzzy vault with combined feature points extracted from fingerprint, iris and retina for high security applications
personal authentication and identification as compared to the traditional authentication methods. Biometric templates are vulnerable to variety of attacks due to their inherent nature. When a person's biometric is compromised his identity is lost. In contrast to password, biometric is not revocable. Therefore, providing security to the stored biometric template is very crucial. Crypto biometric...
متن کاملPassword Hardened Multimodal Biometric Fuzzy Vault with Feature Points Extracted from Retina and Iris
Biometric techniques are gaining importance for personal authentication and identification as compared to the traditional authentication methods. Biometric templates are vulnerable to variety of attacks due to their inherent nature. When a person’s biometric is compromised his identity is lost. In contrast to password, biometric is not revocable. Therefore, providing security to the stored biom...
متن کاملSecurity Analysis of Password Hardened Multimodal Biometric Fuzzy Vault
Biometric techniques are gaining importance for personal authentication and identification as compared to the traditional authentication methods. Biometric templates are vulnerable to variety of attacks due to their inherent nature. When a person’s biometric is compromised his identity is lost. In contrast to password, biometric is not revocable. Therefore, providing security to the stored biom...
متن کاملFuzzy extractors for continuous distributions
We show that there is a direct relation between the maximum length of the keys extracted from biometric data and the error rates of the biometric system. The length of the bio-key depends on the amount of distinguishing information that can be extracted from the source data. This information can be used a-priori to evaluate the potential of the biometric data in the context of a specific crypto...
متن کاملReinforcement learning based feedback control of tumor growth by limiting maximum chemo-drug dose using fuzzy logic
In this paper, a model-free reinforcement learning-based controller is designed to extract a treatment protocol because the design of a model-based controller is complex due to the highly nonlinear dynamics of cancer. The Q-learning algorithm is used to develop an optimal controller for cancer chemotherapy drug dosing. In the Q-learning algorithm, each entry of the Q-table is updated using data...
متن کامل