Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPattern Analysis and detection in images using neural networks
تحليل النماذج في الصور و التعرف عليها باستخدام الشبكات العصبونية
3128
1 206
0
(
0
)
Authors
سهى عراج( باحث )
Created by
Shamra Editor
Ask ChatGPT about the research
يقدم البحث طريقة مطورة لكشف مكان نموذج الوجه في الصورة, و ذلك بجمع أكثر من تقنية لتحقيق أفضل نسبة كشف. يبنى نموذج لون بشرة باستخدام الفضاء اللوني (RGB) Red, Green, Blue, لكشف مناطق البشرة و ينتج المناطق المرشحة لتكون الوجه في الصورة. و من خلال تقنية الشبكة العصبونية يتم تدريب مجموعة من صور الوجوه و صور لغير الوجوه (الخلفية) ، بعد إسقاطها على حيز جزئي بواسطة تقنية تحليل المعاملات الأولية بهدف تقليل أبعاد صور التدريب و تقليل الزمن الحسابي. يوجد تعديلين للاستخدام التقليدي للشبكة العصبونية و هما: أولاً, تختبر الشبكة العصبونية مناطق الصورة المرشحة لتكون وجوه فقط, بالنتيجة يتم تقليل حيز البحث. ثانياً, يتم تكييف نافذة مسح الشبكة العصبونية لصورة الدخل, بحيث تعتمد على حجم المنطقة المرشحة لتكون وجه مما يمكن نظام الكشف من كشف الوجوه بحجوم متعددة.
A new face detection system is presented. The system combines several techniques for face detection to achieve better detection rates, a skin colormodel based on RGB color space is built and used to detect skin regions. The detected skin regions are the face candidate regions. Neural network is used and trained with training set of faces and non-faces that projected into subspace by principal component analysis technique. we have added two modifications for the classical use of neural networks in face detection. First, the neural network tests only the face candidate regions for faces, so the search space is reduced. Second, the window size used by the neural network in scanning the input image is adaptive and depends on the size of the face candidate region. This enables the face detection system to detect faces with any size.
References used
CHELLAPPA, R. ; AMIT, K. R. and SHAOHUA, K. Z."Recognition of Humans and Their Activities Using Video".United States of America,First Edition, 2012
YANG,M.H. ; KRIEGMAN, J. D and AHUJA,N." Detecting Faces in Images: A Survey". IEEE 3-Transactions on Pattern Analysis and Intelligence,Vol.24,No.1,2004,34- 58
YANG,G. ; HUANG,T.S. “Human Face Detection in Complex Background.” Pattern Recognition, Vol. 27, No. 1,2007, 53-63
rate research
Read More
This paper presents a new technique based on artificial neural networks (ANNs) to
correct power factor. A synchronous motor controlled by the neural controller was used to
handle the problem of reactive power compensation of the system, in order to
correct
power factor.
In this paper, the electrical system and the neural controller were simulated using
MATLAB. The results have shown that the presented technique overcomes the problems
in conventional compensators (using static capacitors) such as time delay and step changes
of reactive power besides to the fast compensation compared to the technique with
capacitors groups.
In this paper, we presented a scientific methodicalness in
very short term load forecasting depends on back propagation
artificial neural networks, and we relied upon real data of Syrian
electrical power system.
In this research, We present a scientific advanced developed
study and keeping up with new studies and technologies of very
short-term electrical load forecasting and applying this study for
electrical load forecasting of basic Syrian electrical p
ower system
by studying this prediction for next four hours according to the
criterion applied in the Syrian Electricity Ministry with ten minutes
intervals ,we call it "Instant electrical load forecasting".
The contribution of our research include building an artificial neural
network in MATLAB program environment and improvement of
maximum loading point algorithm, to compute the most critical
voltage stability margin, for on-line voltage stability a
ssessment,
and a method to approximate the most critical voltage stability
margin accurately. a method to create a (ARTIFICIAL NEURAL
NETWORK) approach.
In recent years, the problem of classifying objects in images has increased by using deep learning as a result of the industrial sector requirements. Despite of many algorithms used in this field, such as Deep Learning Neural Network DNN and Convolut
ional Neural Network CNN, the proposed systems to address this problem Lack of comprehensive solution to the difficulties of long training time and floating memory during the training process, low rating classification. Convolutional Neural Networks (CNNs), which are the most used algorithms for this task, were a mathematical pattern for analyzing images data. A new deep-traversal network pattern was proposed to solve the above problems. The aim of the research is to demonstrate the performance of the recognition system using CNNs networks on the available memory and training time by adapting appropriate variables for the bypass network. The database used in this research is CIFAR10, which consists of 60000 colorful images belonging to ten categories, as every 6,000 images are for a class of these items. Where there are 50,000 training images and 10,000 test tubes. When tested on a sample of selected images from the CIFAR10 database, the model achieved a rating classification of 98.87%.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
