19 April, 2017 Knowledge and image processing algorithms for real-life applications. Dr. Maria Athelogou Principal Scientist & Scientific Liaison Manager.

Slides:



Advertisements
Similar presentations
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Advertisements

Introduction to Machine Learning BITS C464/BITS F464
The 20th International Conference on Software Engineering and Knowledge Engineering (SEKE2008) Department of Electrical and Computer Engineering
1.Data categorization 2.Information 3.Knowledge 4.Wisdom 5.Social understanding Which of the following requires a firm to expend resources to organize.
Markov Logic Networks Instructor: Pedro Domingos.
Quadtrees, Octrees and their Applications in Digital Image Processing
WRSTA, 13 August, 2006 Rough Sets in Hybrid Intelligent Systems For Breast Cancer Detection By Aboul Ella Hassanien Cairo University, Faculty of Computer.
Artificial Intelligence
The Decision-Making Process IT Brainpower
SESSION 10 MANAGING KNOWLEDGE FOR THE DIGITAL FIRM.
1 McGraw-Hill/Irwin Copyright © 2004, The McGraw-Hill Companies, Inc. All rights reserved. Chapter 8: Decision Support Systems What kind of decisions?
Quadtrees, Octrees and their Applications in Digital Image Processing
CSE 574: Artificial Intelligence II Statistical Relational Learning Instructor: Pedro Domingos.
From Discrete Mathematics to AI applications: A progression path for an undergraduate program in math Abdul Huq Middle East College of Information Technology,
Automated Changes of Problem Representation Eugene Fink LTI Retreat 2007.
2007Theo Schouten1 Introduction. 2007Theo Schouten2 Human Eye Cones, Rods Reaction time: 0.1 sec (enough for transferring 100 nerve.
1 McGraw-Hill/Irwin Copyright © 2004, The McGraw-Hill Companies, Inc. All rights reserved. Chapter 8: Decision Support Systems Decision Support in Business.
KDD for Science Data Analysis Issues and Examples.
Artificial Intelligence
What is Machine Learning?
Chapter 11 Managing Knowledge. Dimensions of Knowledge.
Semantic Web Technologies Lecture # 2 Faculty of Computer Science, IBA.
Artificial Intelligence
Artificial Intelligence (AI) Addition to the lecture 11.
Data Mining Techniques
Kansas State University Department of Computing and Information Sciences CIS 830: Advanced Topics in Artificial Intelligence From Data Mining To Knowledge.
Katanosh Morovat.   This concept is a formal approach for identifying the rules that encapsulate the structure, constraint, and control of the operation.
Data Management Turban, Aronson, and Liang Decision Support Systems and Intelligent Systems, Seventh Edition.
Artificial Intelligence Dr. Paul Wagner Department of Computer Science University of Wisconsin – Eau Claire.
Artificial Intelligence: Its Roots and Scope
Tennessee Technological University1 The Scientific Importance of Big Data Xia Li Tennessee Technological University.
Introduction to Machine Learning MSE 2400 EaLiCaRA Spring 2015 Dr. Tom Way Based in part on notes from Gavin Brown, University of Manchester.
Knowledge representation
Introduction GAM 376 Robin Burke Winter Outline Introductions Syllabus.
11 C H A P T E R Artificial Intelligence and Expert Systems.
10/6/2015 1Intelligent Systems and Soft Computing Lecture 0 What is Soft Computing.
Copyright © 2006, The McGraw-Hill Companies, Inc. All rights reserved. Decision Support Systems Chapter 10.
Artificial Intelligence And Machine learning. Drag picture to placeholder or click icon to add What is AI?
Quadtrees, Octrees and their Applications in Digital Image Processing.
Ihr Logo Chapter 5 Business Intelligence: Data Warehousing, Data Acquisition, Data Mining, Business Analytics, and Visualization Turban, Aronson, and Liang.
I Robot.
Chapter 5: Business Intelligence: Data Warehousing, Data Acquisition, Data Mining, Business Analytics, and Visualization DECISION SUPPORT SYSTEMS AND BUSINESS.
Data Mining BY JEMINI ISLAM. Data Mining Outline: What is data mining? Why use data mining? How does data mining work The process of data mining Tools.
Introduction to Artificial Intelligence CS 438 Spring 2008.
Spring, 2005 CSE391 – Lecture 1 1 Introduction to Artificial Intelligence Martha Palmer CSE391 Spring, 2005.
Artificial Intelligence: Research and Collaborative Possibilities a presentation by: Dr. Ernest L. McDuffie, Assistant Professor Department of Computer.
Presented by:- Reema Tariq Artificial Intelligence.
Pattern Recognition. What is Pattern Recognition? Pattern recognition is a sub-topic of machine learning. PR is the science that concerns the description.
Chapter 9 : Application Areas. 2 Some Advance Application Areas of Computers  Software Development  Artificial Intelligence  Robotics  Industrial.
COMPUTER SYSTEM FUNDAMENTAL Genetic Computer School INTRODUCTION TO ARTIFICIAL INTELLIGENCE LESSON 11.
Network Management Lecture 13. MACHINE LEARNING TECHNIQUES 2 Dr. Atiq Ahmed Université de Balouchistan.
Decision Support and Business Intelligence Systems (9 th Ed., Prentice Hall) Chapter 12: Artificial Intelligence and Expert Systems.
Artificial Intelligence
Semantic Web Technologies Readings discussion Research presentations Projects & Papers discussions.
Introduction to Artificial Intelligence Heshaam Faili University of Tehran.
Brief Intro to Machine Learning CS539
Machine Learning for Computer Security
CHAPTER 1 Introduction BIC 3337 EXPERT SYSTEM.
Siemens Enables Digitalization: Data Analytics & Artificial Intelligence Dr. Mike Roshchin, CT RDA BAM.
School of Computer Science & Engineering
Image Recognition. Contents: Motivation Objective Definition Introduction Preprocessing / Edge Detection Neural Networks in Image Recognition Practical.
What is Pattern Recognition?
Basic Intro Tutorial on Machine Learning and Data Mining
Artificial Intelligence introduction(2)
AI empowering business
Intelligent Systems and
TA : Mubarakah Otbi, Duaa al Ofi , Huda al Hakami
Principles of Computing – UFCFA3-30-1
Introduction to Artificial Intelligence Instructor: Dr. Eduardo Urbina
Presentation transcript:

19 April, 2017 Knowledge and image processing algorithms for real-life applications. Dr. Maria Athelogou Principal Scientist & Scientific Liaison Manager Email: mathelogou@definiens.com

Artificial intelligence (AI) is the technology and a branch of computer science that studies and develops intelligent machines and software.  Goals Knowledge Based Systems Speech Recognition Pattern Recognition and Pattern Analysis / Image Analysis Robotics Tools Search and Optimization Planning Logic Probabilistic Methods Classifiers and statistical Learning Neural Networks Control theory Languages

Knowledge Based Image Analysis Image analysis is the extraction of meaningful information from images; mainly from digital images by means of digital image processing techniques. Problem: Many powerful programs and many different program libraries have been developed. In such libraries the individual programs are integrated from a low level point of view. But not support is provided to users who need to solve practical image processing problems. Every end – user cannot have a deep understanding of program semantic and syntax. A Knowledge-based system is a computer program  that reasons and uses knowledge to solve complex problems. Knowledge Based Image Analysis: Experts create systems, which can use knowledge to compose complex image analysis processes from primitive image processing operators. These systems have a Graphical User Interface, which enables the users to use the systems in order to solve image analysis tasks. Example: GNORASI

Segmentation – Classification for Image Analysis Segmentation:  the partitioning of a digital image into two or more regions Classification:  analyzes the numerical properties of various image features and organizes data into categories (Classes).

Segmentation

Image 19 April, 2017

Segmentation Algorithm

Segmentation

Image Features

Classification (knowledge: Nuclei are blue and Cells are brown)

Classification

19 April, 2017 Using Knowledge for Classification (Experts: different kinds of Nuclei according to their Context)

Automated Image Analysis and Quantification 19 April, 2017 The Cognition Network Technology emulates the way the human mind understands images Definiens Cognition Network Technology® examines pixels in context to extract intelligence from images. Multiscale Object based Context based Knowledge driven Find all relevant objects and their mutual relations create a hierarchical linked object structure referred to as „segmentation“ Link these objects with the knowledge about them and their relations knowledge representation hierarchical classification In the context of this technology (CNT) Image Analysis is an Iterative process: Alternation between Segmentation and Classification

Cognition Network Language is a meta language for Image Analysis 19 April, 2017 Cognition Network Language is a meta language for Image Analysis CNT - Image analysis system has a GUI This GUI contains this CNT - meta language that allows for fast and efficient development of rule bases A rule base addresses the solution of a specific image analysis task A rule base is reusable

Creating a network of image objects 2D/2D plus time/3D/3D plus time 19 April 2017 19 April, 2017 Pixels are grouped into meaningful objects… …which have defined relationships to neighbours, across the same scale relationships to bigger or smaller objects Morphology/Geometry/Architecture Intensity Operating on this network: “localized” decision making can account for biological heterogeneity A lot of relational and often decisive context information is accessible: deeper insights, more data. 15

Definiens Cognition Network Technology Cognition Network Language 19 April, 2017 19 April 2017 Definiens Cognition Network Technology Cognition Network Language Process Network Algorithms Hierarchy Image Object Network Semantic Network Class Hierarchy A lot of relational and often decisive context information is accessible: deeper insights, more data. 16

Definiens Cognition Network Technology Cognition Network Language Process Network Algorithms Hierarchy Semantic Network Class Hierarchy Image Object Network

Context – Objects - Features

Semantic Network-Class Hierarchy Class definition using Fuzzy Logic

Real Space / Size of Objects 19 April, 2017 Traveling through the Dimensions Real World Applications Real Space / Size of Objects Wide range of scientific areas which can make use of CNT m=meter 0.1 1nm 10 Atom 100 100 10 1m transistor 1mm Organ 1mm 10 Person 10 10 Cell 100 Car City House 1Km 100 Forest Ship www.eCognition.com www.definiens.com 20 20 20

Real Space / Size of Objects 19 April, 2017 One Technology – Many Applications Automatic Detection of Image Contents Real Space / Size of Objects m=meter 0.1 1nm 10 Atom 100 100 10 1m transistor 1mm Organ 1mm 10 Person 10 10 Cell 100 Car City House 1Km 100 Forest Ship www.eCognition.com www.definiens.com 21 21 21

Electron Microscopy Tissue 19 April, 2017 One Technology – Many Applications Automatic Detection of Image Contents Electron Microscopy Tissue High Content Sreening Cells Proliferation index Tissue Cancer Biomarker Tissue 3D-Confocal Microscopy Tissue Molecular Pathology 3D-Confocal Microscopy Cell biology 3D PET/CT Small animal 22 22 22

19 April, 2017

Real Space / Size of Objects 19 April, 2017 One Technology – Many Applications Automatic Detection of Image Contents Real Space / Size of Objects m=meter 0.1 1nm 10 Atom 100 100 10 1m transistor 1mm Organ 1mm 10 Person 10 10 Cell 100 Car City House 1Km 100 Forest Ship www.definiens.com www.definiens.com 24 24 24

One Technology – Many Applications 19 April, 2017 One Technology – Many Applications Automatic Detection of Image Contents CT Head/Neck Biopsy Tissue Serum Cells X-Ray Mammography CT Liver tumor CT Blood vessels MRI Ventricles CT Lymph Nodes www.definiens.com 25 25 25

19 April, 2017

Real Space / Size of Objects 19 April, 2017 One Technology – Many Applications Automatic Detection of Image Contents Real Space / Size of Objects m=meter 0.1 1nm 10 Atom 100 100 10 1m transistor 1mm Organ 1mm 10 Person 10 10 Cell 100 Car City House 1Km 100 Forest Ship www.definiens.com www.definiens.com 27 27 27

Geo: Impervious Surface Maps Generation www.eCognition.com

Thank You for Your Attention