Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDesign a Weighting and Fusion Model of Iris Features To Improve Performance Of Iris Recognition Systems
تصميم نموذج وزن و اختيار ودمج لسمات القزحية لتحسين أداء نظام التعرف على الأشخاص باستخدام صور القزحية
2333
2 20
0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يقترح النظام تصميم نموذج وزن لسمات القزحية و انتقاء السمات الأفضل منها بغية دراسة تأثير عملية الوزن و الاختيار على أداء نظم التعرف. يقدم البحث خوارزمية جديدة في مجال وزن السمات و دمجها تعتمد على الفروق بين الأصناف و الفروق داخل الصنف الواحد و المنطق الضبابي، و يكون خرج هذه الخوارزمية عبارة عن أرقام تمثل أوزان السمات المختارة لمرحلة التصنيف. يتكون النظام المصمم من أربعة مراحل أساسية هي تجزيء القزحية و استخلاص سماتها و تطبيق نموذج الوزن و الاختيار و الدمج ثم التعرف. لاقتطاع منطقة القزحية يقترح النظام استخدام واصفات المنطقة من أجل تحديد نصف قطر القزحية و مركزها، و من ثم يتم تطبيق عملية الاقتطاع و إجراء نقل من الإحداثيات الديكارتية للإحداثيات القطبية عن طريق عملية التدوير و اقتطاع ما يعادل نصف القطر من بكسلات نافذة ثابتة اعتباراً من نقطة المركز و حتى المحيط. يتم استخلاص سمات القزحية باستخدام المعاملات العمودية لتحويل المويجات و يتم تدعيمها بالمعاملات الإحصائية لنواتج الاشتقاق من الدرجة الأولى و الثانية لمنطقة القزحية. و في مرحلة الوزن و الدمج يتم اختيار السمات الأفضل و وزنها و دمجها ليتم لاحقاً في مرحلة التصنيف الاستعانة بمصنف المسافة لإنجاز عملية التعرف. طبقت الخوارزمية على قاعدة بيانات CASIA العالمية المؤلفة من صور تعود لـ 250 شخص و تم التوصل لدقة 100% في مرحلة التجزيء، و معدل تعرف أعظمي98.7%. تظهر النتائج العملية أن خوارزمية التجزيء المصممة فعالة مع تغيرات الإضاءة و الدوران و التغطية الجزئية بالرموش و الأجفان،و أن خوارزمية وزن سمات القزحية و اختيارها و دمجها تحسن من أداء النظام.
The study suggests designing a weighting model for iris features and selection of the best ones to show the effect of weighting and selection process on system performance. The search introduces a new weighting and fusion algorithm depends on the inter and intra class differences and the fuzzy logic. The output of the algorithm is the feature’s weight of the selected features. The designed system consists of four stages which are iris segmentation, feature extraction, feature weighting_selection_fusion model implementation and recognition. System suggests using region descriptors for defining the center and radius of iris region, then the iris is cropped and transformed into the polar coordinates via rotation and selection of radius-size pixels of fixed window from center to circumference. Feature extraction stage is done by wavelet vertical details and the statistical metrics of 1st and 2nd derivative of normalized iris image. At weighting and fusion step the best features are selected and fused for classification stage which is done by distance classifier. The algorithm is applied on CASIA database which consists of iris images related to 250 persons. It achieved 100% segmentation precision and 98.7% recognition rate. The results show that segmentation algorithm is robust against illumination and rotation variations and occlusion by eye lash and lid, and the weighting_selection_fusion algorithm enhances the system performance.
References used
AYRA P, LINSANGANN and CALUYOF, “Wavelet-based Feature Extraction Algorithm for an Iris Recognition System”, Journal of Information Processing Systems, Vol.7, No.3, September 2011,PP:425-434
AVIILA S, SANCHEZ R, MARTIN-ROCHE D, “Iris-based biometric using Dyadic Wavelet Transform”,IEEE AESS systems Magazine, October 2002, pp:3-6
BOLES W and BOASHASHB, “A human identification technique using images of the iris and wavelet transform”, IEEE Transactions on Signal Processing, Vol. 46, No. 4, 1998, pp. 1185-1188
rate research
Read More
This paper introduces a new approach to extract palm print features
and select the best ones. The paper also studies the effectiveness of
the selection process on speed and performance of system.
This paper presents a new technique to extract the features of a
common case of images of the iris called off-angle iris which
taken for persons identification system. The main problem when
using biological iris measurements to identify the persons is the
difficulty of identifying and extracting features of the iris. This
problem increasing when dealing with off-angle iris and it leading
to decrease system accuracy and increase system rate error.
The research presents a design for an automated checking system for students. The
system takes a picture of the student, then it extracts his/her basic facial features. The
network was trained using the reverse spreading algorithm. If a training da
tabase is
generated for each student consisting of 15 training samples contained of the necessary
facial expressions to identify the student for one time at the beginning of the semester, then
the neural network will be trained on students database to obtain a trained neural network
able to identify the students of each category depending on their physical appearance. That
will result in knowing who attends and who does not attend the session. The system
designed for this purpose was supplied with the trained network. The system provides the
possibility of automated checking for students according to the content of the study giving
the alarm in case of the existence of the picture of a student who does not belong to the
same group.
The use of traditional methods to analyze massive amounts of
data sets is not conducive to the discovery of new knowledge
patterns supports the decision-making process So the purpose
of this article is designed visual analysis system that supports
analysis of data sets through the use of automated analysis,
which includes many of the techniques such as assembly
process (clustering) and Altnsnev (classification) and the
correlation base (association Rule) And the process of visual
data exploration techniques Manifesting, and then the
comparison with other data sets manifestation techniques and
evaluation of the proposed Manifesting system.
For decades, published Automatic Signature Verification (ASV) works depended on using one feature set. Some researchers selected this feature set based on their experience, and some others selected it using some feature selection algorithms that can
select the best
feature set (bfs). In practical systems, the documents containing the signatures could be noisy, and recognition of check writer in multi-signatory accounts is required. Due to the error caused by such requirements and data quality, improving the performance of ASV
becomes a necessity. In this paper, a new technique for ASV decision making using Multi-Sets of Features is introduced. The experimental results have shown that the introduced technique gives important improvement in forgery detection and in the overall performance of the system.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
