Fingerprint Verification using HMAX model and SVM classification
Publish place: 16th Iranian Conference on Electric Engineering
Publish Year: 1387
نوع سند: مقاله کنفرانسی
زبان: English
View: 2,459
This Paper With 6 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICEE16_022
تاریخ نمایه سازی: 6 اسفند 1386
Abstract:
In this paper, we introduce a new set of biologically inspired features for human recognition. Our system’s architecture is motivated by a quantitative model of visual cortex. We show that our approach exhibits excellent recognition performance and outperforms several state-of-the art systems on a variety of image datasets including many different finger categories. We implement our system using a Support Vector Machine (SVM) and K-nearest neighbor (KNN) classifiers. Experimental results using the combination HMAX model and support vector machine (SVM) classifier obtains higher recognition rate than HMAX model with k-nearest neighbor (KNN) classifier in identity verification system based on finger. and also demonstrated that the HMAX model, compared with PCA method, not only obtains higher recognition rate, but also this method is scale and rotate invariant, whereas PCA method provide high recognition rate only in closely controlled conditions. In addition to, in experiment, it was found that using of Gaussian filter in HMAX model in compared to using of Gabor filter, not only increases performance of person recognition, but also increases speed of feature extraction from finger images.
Keywords:
biometric , Fingerprint biometric , HMAX model , support vector machine (SVM) , visual cortex , K-nearest neighbor (KNN).
Authors
Sara Motamed
Qazvin Azad university
karim Faez
Amirkabir university university
Mahboubeh Yaqubi
Qazvin Azad university
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :