Deep Learning and Machine Learning for Computer Vision

6 hour workshop

4 Nov 2017, Bangalore

The human body is one of the most complex machines on Earth. We are fascinated by how the Human Visual System works. How as a human, we see the world, store the visual information and learn from what we see and recognize patterns from previous experiences. The goal of the workshop is to help build an understanding of how to solve real world problems using Computer Vision with examples. We start from biological motivations for Computer Vision, developing intuitions to solve problems, converting the intuitions into the language of mathematics and finally developing code that represents the mathematics. With the help of Machine Learning and Deep learning, we are able to attain state-of-art performance in many Computer Vision problems. The workshop is meant for those who want to get get a hands-on experience of using ML / DL for solving Computer Vision problems.

Who is it for?

  • Beginners in any of Computer Vision, Machine Learning and Deep learning
  • Or those with exposure to ML / DL and new to ML / DL in Computer Vision


  • Background Knowledge
    • Good Experience in Python (can not support non programmers during session due to lack of time)
    • Good to have: Knowledge of Numpy
  • Devices
    • PC with minimum configuration: 8 GB RAM and i5 Processor
    • Install VirtualBox Software & Download and run image provided


  • The participants have to install the required software before the session (link will be provided shortly).
  • We will conduct a Installation Clinic to help the participants install the software package one day before the session.
  • We would like to have one volunteer to help the participants in case of any software conflicts


The workshop builds an intuition behind how a digital image is captured, stored and processed. It aims to show what are the traditional and simple object detection mechanisms in Computer Vision and their limitations by examples. Then we show how Machine Learning came to the aid and solved the problems which the traditional CV techniques could not solve.

We will spend time on analyzing the limitations of Machine Learning and how we can address some of these using the Deep Learning techniques. We will dive into the Black box (DL) and try to understand what each layer is doing and so that we can solve problems in an effective manner. We will finally talk about best practises in solving Computer Vision problems, which technique to use, which parameter to tweak, etc.,

The workshop is going to have 3 major parts each with a example problems that we will experiment on, using Jupyter notebooks. At the end of the workshop, each participant should be able to build a network using Keras (Python library for Deep Learning), train and test the model. It is going to be a hands-on and with some mathematics, especially suitable for the beginners to Computer Vision or practitioners who have not had a chance to build from basics.

Part I

  • Motivation: Interesting applications of Computer Vision
  • What is Computer Vision, Machine Vision and Image Processing ?
  • Simple Computer Vision based classification (hands-on)

Part II

  • Machine Learning in CV
  • Classification using ML (hands-on)

Part III

  • Emergence and Dominance of Deep Learning
  • Applications of DL (hands-on)
  • Compare ML and DL (hands-on)
  • How to solve a CV problem by choosing the appropriate technique?


Sumod Mohan

CTO of Digital Aristotle and heads the Computer Vision and Machine Learning at Soliton Technologies

Shivarajkumar Magadi

Leads the 3D Vision team at Soliton Technologies

Dhivakar Kanagaraj

Computer Vision and Machine Learning Engineer at Soliton Technologies

Senthil Palanisamy

Computer Vision and Machine Learning Engineer in Soliton Technologies