Workshop: DL and ML for Computer Vision

Get a hands-on experience of using ML / DL for solving computer vision problems

09:30 AM to 06:00 PM, 13 – 14 Oct 2018, Great Learning 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 a hands-on experience of using ML / DL for solving Computer Vision problems.

This is a two-day workshop on Computer Vision and Machine Learning. The first day would be an introduction to Computer Vision, Machine Learning and Deep Learning. The second day would cover more advanced topics in 3D Computer Vision (including some topics used in navigation like localization: SLAM), advanced topics in 2D Vision and Machine Learning closing with End-To-End Solution Development session using Computer Vision and Machine Learning.

Whom is it for?

  • Day 1: Intermediate in Computer Vision and Machine Learning and Beginner in Deep learning

  • Day 1: Or those with exposure to ML / DL and new to ML / DL in Computer Vision

  • Day 2: Experienced with Computer Vision, Machine Learning and Deep Learning or have attended Day 1. Want to know more 3D Vision and wants to learn how to do Disciplined Machine Learning.


  • Background Knowledge

    • Good Experience in Python (cannot support non-programmers during session due to lack of time)
    • Knowledge of Numpy
    • Basic concepts and hands-on experience in Digital Image Processing
  • Devices

    • PC with minimum configuration: 8 GB RAM and i5 Processor
    • Install VirtualBox Software & Download and run image provided (will be shared shortly)
  • You can register for Day 2 only if you have attended last years Computer Vision Workshop. (If you have an advanced degree in ML/DL or experienced with the same, please email us to confirm for Day 2 only)


  • The participants have to install the required software before the session (link will be provided shortly).
  • We will conduct an Installation Clinic to help the participants install the software package one day before the session.


The workshop 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 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 practices in solving Computer Vision problems, which technique to use, which parameter to tweak, etc.,

The workshop is going to have 5 major parts each with example problems that we will experiment on, using Jupyter notebooks. At the end of Day 1 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 hands-on and with enough mathematics, especially suitable for the beginners to Deep Learning or practitioners who have not had a chance to build from basics. At the end of Day 2 of the workshop, you will be introduced to various problems in 3D Vision and approaches to solve them. During the last part, we will walk you through Disciplined Machine Learning to solve the practical vision problems.

Part I (Day 1)

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

Part II (Day 1)

  • Machine Learning in CV
  • Classification using ML (hands-on)
  • Emergence and Dominance of Deep Learning
  • Applications of DL (hands-on)

Part III (Day 1)

  • Compare ML and DL (hands-on)
  • Real world examples of DL (Demo)
  • How to solve a CV problem by choosing the appropriate technique?
  • Hand’s on with Soliton’s Neura Camera Platform

PART IV (Day 2)

  • 3D Vision: Stereo Vision
  • 3D Vision: Reconstruction
  • Localization: SLAM
  • Hands of problem 3D problem solving

PART V (Day 2)

  • Design Thinking using CV/ML: Framing Business Problem
  • Advice on applying CV/ML: Case Studies with
  • Disciplined Machine Learning


Sumod K Mohan

Founder, AutoInfer

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





Great Learning Bangalore (Great Lakes E-Learning), Ground Floor, Plot No. 758 - 759, 19th Main Rd, Sector 2, HSR Layout, (Near Sri Sai Mandir), Bengaluru, Karnataka 560102


Venue Partner