Back to Catalog

Automating visual inspection with Machine Learning (ML)

Premium
ExpertGuided Project

Computer Vision paired with Machine Learning (ML) is becoming a popular way to automate the high-volume quality inspection of products in many industries. In this project, you will learn how to inspect the quality of lemons by using basic ML methods of image classification.

4.6 (37 Reviews)

Language

  • English

Topic

  • Artificial Intelligence

Industries

  • Agriculture

Enrollment Count

  • 366

Skills You Will Learn

  • Machine Learning, Artificial Intelligence, Data Science

Offered By

  • IBM

Estimated Effort

  • 2 hours

Platform

  • SkillsNetwork

Last Update

  • April 29, 2024
About This Guided Project

About

Computer vision is a field of artificial intelligence (AI) that enables computers and systems to derive meaningful information from digital images, videos, and other visual inputs — and take actions or make recommendations based on that information. If AI enables computers to think, computer vision enables them to see, observe and understand. Computer vision works much the same as human vision, except humans have a head start. Human sight has the advantage of lifetimes of context to train how to tell objects apart, how far away they are, whether they are moving, and whether there is something wrong in an image. Computer vision trains machines to perform these functions, but it has to do it in much less time with cameras, data, and algorithms rather than retinas, optic nerves, and the visual cortex. Because a system trained to inspect products or watch a production asset can analyze thousands of products a minute, noticing imperceptible defects or issues, it can quickly surpass human capabilities.
Computer vision is used in industries ranging from energy and utilities to manufacturing and automotive – and the market is continuing to grow. 

In this project, we will apply computer vision for the purpose of visual inspection. We will learn how to train a Machine Learning model to classify agricultural products based on their quality. Instead of using real cameras to capture images, we will use existing photographs to train our model. We will learn to form a DataSet from photographs of lemons and compare different types of classifiers. In the end, we will create a report that forms a DataSet on the lemons' quality.


 In this project, we will learn the basic methods of image classification. The project consists of four stages:
  • Download the image data set and perform the preliminary transformation of images
  • Create image features
  • Compare different classical classification methods
  • Create function for lemon quality classification

Prerequisites

  • Python - basic level
  • numpy - middle level
  • SeaBorn - basic level
  • Matplotlib - basic level
  • mahotas - middle level
  • scikit-learn - middle level
  • pandas — basic level

After completing this project, you will be able to:

  • Download and transform images
  • Create features of images
  • Build different classification models
  • Build a DataSet with the quality level of agricultural products.

Instructors

Yaroslav Vyklyuk

Full Professor, Doctor of Computer Science, PhD

Dr. Yaroslav Vyklyuk is a full professor at the Lviv Polytechnic National University, Department of Artificial Intelligence Systems. He is an author of over 210 scientific works, 10 monographs, and books, a member of the Editorial Board of 6 international scientific journals, member of the Academic Councils on protection Ph.D. and DrSc thesis in "Mathematical modeling and computational methods". Research Interests: Data Science, Applied System Analysis, Mathematical Modeling, and Decision Making of Complex Dynamic Systems (socio-economic, geographical, tourist, and crisis systems) using Artificial Intelligence Technology, DataMining, Big Data, Parallel Calculations, Statistics, Econometrics, Econophysics and other Advanced Mathematical Methods with implementation into information, WEB, and geographic information systems.

Read more

Bogdan Norkin

Dr.Sc. in applied mathematics.

Research Fellow, V.M. Glushkov Institute of Cybernetics of NAS of Ukraine.

Read more

Kateryna Hazdiuk

PhD of Software Engineering

I am an assistant professor at the Yuriy Fedcovych Chernivtsi National University, Software of Computer Systems Department; an author of over 40 scientific works and 10 training manuals. Research Interests: Mathematical Modeling of Complex Dynamic Systems (bio-like systems, socio-economic, geographical systems), Data Science, Decision Making using Artificial Intelligence Technology, DataMining, Big Data, Parallel Calculations, Statistics, and other methods.

Read more

Contributors

Leon Katsnelson

Director & CTO, IBM Developer Skills Network

I've had a very productive career in tech. I've touched many areas from mainframe, to manufacturing automation (IoT), to databases, big data, data science and AI, blockchain, and of course full stack and cloud-native development and DevOps. I started my career in test and QA, did quite a bit of development, product management, team leadership, and people management before becoming an executive. I had some great wins including bringing to market a billion $ product. And had some failures along the way. But throughout my career, one thing has always remained constant. I learned everything I could and used every chance I had to get a new skill. My goal in life is to help those who have an appetite for learning to acquire knowledge and skill to build their career or simply become better users of the latest tech.

Read more