Quantum-Inspired Soft Computing for Binary Image Analysis

Quantum-Inspired Soft Computing for Binary Image Analysis

Siddhartha Bhattacharyya (RCC Institute of Information Technology, India)
Release Date: May, 2016|Copyright: © 2016 |Runtime: 1 hr 16 mins
EISBN13: 9781522507680|DOI: 10.4018/978-1-5225-0768-0
Institution (Multi User Access) Video Prices
Streaming Access:
$180.00
DVD:
$190.00
Individual (Single User Access) Video Prices
Streaming Access:
$90.00
DVD:
$100.00

Description

Several classical techniques have evolved over the years for the purpose of de-noising binary images as a part of image enhancement. Filtering techniques remain at the helm as different filters can be designed to cater to various noisy characteristics. The main disadvantages of these classical techniques lie in that an a priori information regarding the noise characteristics is required during the extraction process. Among the intelligent techniques in vogue, the multilayer self-organizing neural network (MLSONN) architecture is suitable for binary image preprocessing tasks.

Quantum-Inspired Soft Computing for Binary Image Analysis introduces a quantum version of the MLSONN architecture. Similar to the MLSONN architecture, the proposed quantum multilayer self-organizing neural network (QMLSONN) architecture comprises three processing layers viz., input, hidden and output layers. This video lecture is an innovative resource for practitioners, researchers, and graduate-level students interested in learning about emerging computer vision techniques.

Topics Covered

  • Algorithms
  • Image Data Sets
  • Network Architecture
  • Network Stabilization
  • Noise Characteristics
  • Quantum computing

Table of Contents

Introduction
13:42 mins
Section 1:Quantum-Inspired Soft Computing for Binary Image Enhancement
 
Lesson 1:Quantum Computing Fundamentals
10:20 mins
 
Lesson 2:Multilayer Self Organizing Neural Network (MLSONN) Architecture
10:50 mins
 
Lesson 3:Hopfield Networks
8:01 mins
 
Lesson 4:Quantum Multilayer Self Organizing Neural Network (QMLSONN) Architecture
14:17 mins
 
Lesson 5:Experimental Results
7:06 mins
 
Conclusion and Dedication
4:22 mins