An unsupervised method for clustering images based on their salient regions of interest

Authors:
Gustavo B. Borba;Humberto R. Gamba;Oge Marques;Liam M. Mayron
Affiliations:
Universidade Tecnológica Federal do Paraná, Curitiba - Paraná - Brasil;Universidade Tecnológica Federal do Paraná, Curitiba - Paraná - Brasil;Florida Atlantic University, Boca Raton, FL;Florida Atlantic University, Boca Raton, FL
Venue:
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Year:
2006

Citing 4
Cited 2

A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Content-Based Image Retrieval at the End of the Early Years

IEEE Transactions on Pattern Analysis and Machine Intelligence
An attention-driven model for grouping similar images with image retrieval applications

EURASIP Journal on Applied Signal Processing
CLUE: cluster-based retrieval of images by unsupervised learning

IEEE Transactions on Image Processing

A cognitive approach for robots' vision using unsupervised learning and visual saliency

IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part I
A machine learning based intelligent vision system for autonomous object detection and recognition

Applied Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We have developed a biologically-motivated, unsupervised way of grouping together images whose salient regions of interest (ROIs) are perceptually similar regardless of the visual contents of other (less relevant) parts of the image. In the implemented model cluster membership is assigned based on feature vectors extracted from salient ROIs. This paper focuses on the experimental evaluation of the proposed approach for several combinations of feature extraction techniques and unsupervised clustering algorithms. The results reported here show that this is a valid approach and encourage further research.