Elective Course 4- course code CSE 3415

Introduction to
Computer Vision
Lecture 1
Dr. Sarah M. Ayyad
Faculty of engineering, Mansoura university
Back Next
Course Goals
● How to analyze images and extract contents from images.
● How to build computer software to receive and interpret an image.
● Understanding the applications, theories, and techniques of computer vision.
● Basic concepts, mathematical and computation methods that will enable us to
implement computer vision systems.
● Development and prototyping Computer Vision software by M-files in Matlab to
implement computer vision algorithms.

Back Next
Course Topics
● Image Features
● Feature Detection
● Feature Extraction
● Feature Matching
● Estimating Geometric Transformation
● Feature based Image Registration
● Image Stitching
● Classification Models for Images
● Preparing Images for Classification
● Object Detection with Matlab

Back Next
Assessment:
● Final Exam: 90 pt.
● Mid-term: 20 pt.
● Lab: 10 pt.
● Project: 10 pt.

Total: 125 pt.

Back Next
What is image processing?
The processing of images using mathematical operations for which the
input is an image, a series of images or a video, such as a photograph or
video frame; the output of image processing is an image.

Basically: image in, image out

Back
What is computer vision?
An interdisciplinary field that deals with how computers can be made for
gaining high-level understanding from digital images or videos.
From the perspective of engineering, it seeks to automate tasks that the
human visual system can do.
Basically: image in, knowledge out.

Back Next
Compter Imaging
These two categories are not totally separate and distinct.

Computer Image
Vision Processing

Back Next
 Every picture tells a story

The goal of computer vison write programs that can interpret images.
The goal of image processing manipulation of images.

Back Next
 Why Study Computer Vision (CV)?
▪ Because their numerous applications in various fields such as
healthcare, transportation, security, entertainment.
▪ With the rise of machine leaning and deep learning techniques,
CV has become more accurate and efficient.

Back Next
Why is the state-of-the-art in CV?
1. Technology that convert scanned documents to text.

Back Next
Why is the state-of-the-art in CV?
2. License plate readers

Back Next
Why is the state-of-the-art in CV?
3. Handwritten digit recognition

Back Next
Why is the state-of-the-art in CV?
4. Face Detection

Next
 5. Object Recognition
Object recognition is a basic research field of computer vision for finding and identifying
objects in an image or video sequence, so that the computer can simulate the human brain
and human eye function.

Back Next
5. Object Recognition
Smart glasses

Back Next
6.Special Effects and 3D Modelling

Motion Capture

Next
6.Special Effects and 3D Modelling
Capturing shape of somebody.

Back Next
 6.Special Effects and 3D Modelling
Earth Viewers (3D modeling)
E.g., google earth, Microsoft
virtual earth

Back Next
 7. Automotive
Smart Cars
▪ Automatically recognize signs.
▪ Identifying where the pedestrians
▪ They have a system that alerts you
if pedestrians getting closer.

Next
 8. Sports
Another big economic place for computer vision is sports.

Back Next
8. Sports
9. Video Games / vision-based interaction

Back Next
10. Medical Imaging (healthcare)

Rapid disease early-detection

tumor/cancer detection
medical image segmentation

Next
 There are a tremendous of
opportunities in computer vision