Intelligent Systems in Automation

Subject description

Introduction to pattern recognition and artificial intelligence: basic concepts and terminology.
Processing and recognition of visual patterns: image acquisition, image segmentation, shape and texture features, automatic learning, and object recognition.
Automatic visual detection and recognition of persons in surveilled areas. Methods of visual detection and recognition of faces and gaits in images.
Processing and recognition of auditory patterns: speech signal acquisition and segmentation, speech features (energy, cepstral coefficients and dynamic features), and automatic learning for isolated commands recognition.
Speech synthesis: acoustical modelling of speech, main methods of speech synthesis, learning speech synthesis from speech recordings.
Speech-based man-machine communication: system components for speech-based man-machine communication, speech recognition system, speech synthesis system, dialog system.

The subject is taught in programs

Objectives and competences

The objective of the course is to acquaint the student with the basic concepts and components of artificial intelligent systems in automation. In particular, the student is acquainted with the basics of machine vision, automatic speech recognition and speech synthesis, as well as with the basics of the modern methods of human-machine communication. The student is also acquainted with the basic concepts of intelligent systems and examples of the implementations of such systems. The acquired knowledge provides an insight into the possibilities and limitations in the use of image and speech recognition systems for the development of intelligent systems in automation.

Teaching and learning methods

The lectures provide a theoretical background of all the considered models and methods together with simple computational examples that illustrate the key characteristics of all the presented methods. A textbook and other study material, such as lecture notes with solved example problems and lecture slides, are available to the students. As part of the lectures, the students receive optional homework assignments including theoretical questions as well as computational exercises that enable the students to promptly verify the acquired knowledge. Practical work is carried out as part of the laboratory exercises, where the students mostly solve given programming problems.

Expected study results

After successful completion of the course, students should be able to:

describe the basic methods of the automatic recognition of visual and auditory patterns,
present the examples of intelligent systems that include methods of the automatic recognition of visual and auditory patterns,
use application programming interfaces for the development of voice communication between man and machine,
use the OpenCV and WEKA open source development tools, the C ++ and Java programming languages, the GCC compiler, and the Netbeans programming environment for the development of the examples of intelligent systems, and
to design basic examples of intelligent systems that include methods for identifying visual and auditory patterns, and
to evaluate the usefulness of the given intelligent systems that include methods of the automatic recognition of visual and auditory patterns.

Basic sources and literature

N. Pavešić: Razpoznavanje vzorcev : uvod v analizo in razumevanje vidnih in slušnih signalov, 3., popravljena in dopolnjena izdaja, Založba FE in FRI, 2012. 2 zv. ([XVI], 707 str.), ilustr. ISBN 978-961-243-201-0. [COBISS.SI-ID 260256256]
R. C. Gonzalez, R. E. Woods, S. L. Eddins: Digital Image Processing Using MATLAB , 2. izdaja, Gatesmark Publishing, 2009.
J. C. Russ: The Image Processing Handbook, 6. izdaja, CRC, 2011.
R. Pieraccini: The Voice in the Machine: Building Computers That Understand Speech, MIT Press , 2012.
P. Taylor: Text-to-Speech Synthesis, Cambridge University Press, 2009.