Proposal on image compression method using synchronization

Ishihara, Hiroyuki; Yoshioka, Kengo; Hirose, Masao

doi:10.1109/isot.2012.6403257

Cited by 1 publication

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are studies devoted to adaptation of the Kuramoto model for solving various problems, for example, several algorithms and approaches of cluster analysis [3,17,20], image compression method [9], learning patterns [21], also there are papers devoted to graph coloring problem that is solved by oscillatory network based on the considered model with negative connections [25,26]. In the following section, the oscillatory network based on modified Kuramoto model has been presented for image segmentation problem.…”

Section: Preliminariesmentioning

confidence: 99%

Oscillatory Network Based on Kuramoto Model for Image Segmentation

Новиков

Benderskaya

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Oscillatory networks represent biologically inspired models that implement cognitive functions such as vision, motion and memory. Vision functions are most attractive brain ability. Despite recognition problems have been successfully solved by traditional neural networks, segmentation problems still require close attention. In this paper, we propose oscillatory network based on Kuramoto phase oscillator for image segmentation where each allocated feature is encoded by ensemble of synchronous oscillators like in biologically plausible systems. The proposed model is designed to perform color segmentation and object segmentation using synchronization phenomena. Processes of synchronization between oscillators during image processing and multi-core implementation of the network for simulation are discussed. Experimental results of segmentation by the network using formal and real images have been presented.

show abstract