Seeing Through the Eyes of Machines

The method of observing the surrounding environment through machines such as computers or mobile phones is called computer vision. The rigorous work of simulating the human eye dates back to the 1950s, and we have come a long way in this field. Computer vision has entered our smartphones through various e-commerce or camera applications.

When machines have eyes like humans, they will be able to do more things. The human eye has a complex structure, and understanding the environment through observation is an even more complex phenomenon. In a similar way, enabling machines to see things and giving them enough capability to understand what they see and further classify it remains a daunting task.

Using computer vision is equivalent to performing millions of calculations in the blink of an eye, with an accuracy almost comparable to that of the human eye.This involves not only converting images into pixels and then trying to understand the content of the image through those pixels but also first understanding how to extract information from those pixels and what they represent.

1. Understanding How Machines See

A. Digital Representation of Colors: In computer science, each color is represented by a specific hexadecimal value. This is a way for machines to understand the color composition of image pixels. As humans, we have the ability to distinguish different colors based on their shades.

B. Image Segmentation: Computers are used to identify groups of similar colors and then segment the image, distinguishing the foreground from the background. Color gradient techniques are used to find the edges of different objects.

C. Finding Corner Points:After segmentation, certain specific features in the image, also known as corner points, are searched for. In short, the algorithm searches for lines that intersect at certain angles and covers specific parts of the image with a color shade. Features (also known as corner points) act like building blocks, helping to find more detailed information contained in the image.

D. Finding Textures:Another important aspect of correctly identifying an image is distinguishing the textures within the image. The texture differences between two objects make it easier for machines to classify objects correctly.

E. Making Guesses: After executing the above steps, the machine needs to make a high-probability correct guess and match the image with those present in the database.

F. Finally, Seeing the Big Picture: Ultimately, a machine will see a larger, clearer picture and check if it has correctly identified the image based on the provided algorithm instructions. Accuracy has greatly improved over the past few years, but machines still make mistakes when required to process images with mixed objects.

2. Universities with Computer Vision Research Groups

Universities in the USA:

Carnegie Mellon University Robotics Institute

University of California, Los Angeles

University of North Carolina at Chapel Hill

University of Washington

University of California, Berkeley

Stanford University

Massachusetts Institute of Technology

Cornell University

University of Pennsylvania

University of California, Irvine

Columbia University

University of Illinois at Urbana-Champaign

University of Southern California

University of Michigan

Princeton University

University of Rochester

The University of Texas at Austin

University of Maryland, College Park

Brown University

University of Central Florida

New York University

Michigan State University

University of Massachusetts, Amherst

Northwestern University

University of California, San Diego

Universities in Canada:

University of Alberta

University of Toronto

University of British Columbia

Simon Fraser University

Universities in Europe:

INRIA France

University of Oxford (http://www.robots.ox.ac.uk/~vgg/)

ETH Zurich

Max Planck Institute in Germany

University of Edinburgh

University of Surrey

University of Freiburg

KTH Sweden

Dresden University

Darmstadt University of Technology

EPFL Switzerland

KU Leuven

Barcelona Computer Vision Center

IDIAP Switzerland

Imperial College London

Heidelberg International Airport

University of Manchester

University of Bonn

RWTH Aachen University

University of Amsterdam

Technical University of Munich

Czech Technical University

University of Cambridge

Graz

IST Austria

Queen Mary University of London

University of Zurich

Delft University of Technology

University of Leeds

University of Bern

Lund University

University of Trento, Italy

University of Florence, Italy

University of Stuttgart

University of Saarland

École Centrale Paris

École Polytechnique

University of Oulu

Karlsruhe Institute of Technology

3. For Beginners in the Field of Computer Vision, Here is a Comprehensive List of Topics You Must Understand.

A. Beginner Level

Mathematics:

1. Linear Algebra

2. Singular Value Decomposition

3. Introductory Pattern Recognition

4. Principal Component Analysis

5. Kalman Filtering

6. Fourier Transform

7. Wavelets

Image Processing:

1. Online course offered by Duke University on Coursera

2. Digital Image Processing by Gonzalez and Woods

B. Advanced

1. Linear Discriminant Analysis

2. Probability, Bayes’ Rule, Maximum Likelihood, MAP

3. Mixture and Expectation-Maximization Algorithms

4. Introductory Statistical Learning

5. Support Vector Machines

6. Genetic Algorithms

7. Hidden Markov Models

8. Bayesian Networks