نظام اكتشاف الدخيل في المنزل الذكي المعتمد على تحسين خوارزميات التعلم العميق == Smart Home Intruder Detection System Based on Enhance Deep Learning Algorithms
Author name:
هبة حميد علي
Supervisor name:
جولان روكان نايف | وليد رشيد حمود
General topic:
Computer Science
Specific topic:
Computer Science
Degree:
Master
University:
Mustansiriyah University - Faculty Of Education
Language:
English
University location:
Baghdad
Key words:
- Problem Statement
- Aim of The Thesis
- IoT Architecture
- Computer Vision(CV
- Image Preprocessing
- Preprocessing Algorithms for Face Recognition
- Histograms of Oriented Gradients (HOG) for Face Detection
- Machine Learning (ML) Approaches
- Support Vector Machines(SVM
- Convolution Neural Network (CNN
- 4 Fully Connected (FC) Layer
- Overfitting and Underfitting
- Pre-Trained Model for CV
- Raspberry Pi (RPI) Configuration with Camera and Sensors
- 6 Image Preprocessing Phase
- 8 Convert Model To Lite Model phase
- Dataset Creation Result
- Detect and Crop Only Faces Image
- Distribute The Pooled Data Set to Training , Validation, and
- TestingAugmentation Image Data and Resize Image to 224*224
- The Training and Testing Phase
