IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

True Color Image Segmentation by MUSIG Activation Function Using Self-Supervised QMLSONN Architecture With Context-Sensitive Thresholding

True Color Image Segmentation by MUSIG Activation Function Using Self-Supervised QMLSONN Architecture With Context-Sensitive Thresholding
View Sample PDF
Author(s): Pankaj Pal (RCC Institute of Information Technology, India) and Siddhartha Bhattacharyya (RCC Institute of Information Technology, India)
Copyright: 2018
Pages: 49
Source title: Quantum-Inspired Intelligent Systems for Multimedia Data Analysis
Source Author(s)/Editor(s): Siddhartha Bhattacharyya (RCC Institute of Information Technology, India)
DOI: 10.4018/978-1-5225-5219-2.ch007

Purchase


Abstract

In this chapter, the authors propose the true color image segmentation in real-life images as well as synthetic images by means of thresholded MUSIG function, which is learnt by quantum-formulated self-supervised neural network according to change of phase. In the initial phase, the true color image is segregated in the source module to fragment three different components—red, green, and blue colors—for three parallel layers of QMLSONN architecture. This information is fused in the sink module of QPSONN to get the preferred output. Each pixel of the input image is converted to the corresponding qubit neurons according to the phase manner. The interconnection weights between the layers are represented by qubit rotation gates. The quantum measurement at the output layer destroys the quantum states and gets the output for the processed information by means of quantum backpropagation algorithm using fuzziness measure.

Related Content

Sucet Jimena Martínez-Vergara, Jaume Valls-Pasola. © 2020. 23 pages.
Joana Coutinho de Sousa, Jorge Gaspar. © 2020. 26 pages.
João P. C. Marques. © 2020. 25 pages.
George Leal Jamil. © 2020. 22 pages.
Stephen Burdon, Kyeong Kang, Grant Mooney. © 2020. 14 pages.
Yudi Fernando, Wen Xin Wah. © 2020. 14 pages.
Nasima Mohamed Hoosen Carrim. © 2020. 23 pages.
Body Bottom