Published on Sat Nov 18 2017

A Genetic Algorithm Approach for ImageRepresentation Learning through Color Quantization

Érico M. Pereira, Ricardo da S. Torres, Jefersson A. dos Santos

Data-driven approaches have been successfully explored as alternatives for producing more representative visual features. We hypothesize that changing the quantization affects the quality of image description approaches,leading to effective and efficient representations.

0
0
0
Abstract

Over the last decades, hand-crafted feature extractors have been used to encode image visual properties into feature vectors. Recently, data-driven feature learning approaches have been successfully explored as alternatives for producing more representative visual features. In this work, we combine both research venues, focusing on the color quantization problem. We propose two data-driven approaches to learn image representations through the search for optimized quantization schemes, which lead to more effective feature extraction algorithms and compact representations. Our strategy employs Genetic Algorithm, a soft-computing apparatus successfully utilized in Information-retrieval-related optimization problems. We hypothesize that changing the quantization affects the quality of image description approaches, leading to effective and efficient representations. We evaluate our approaches in content-based image retrieval tasks, considering eight well-known datasets with different visual properties. Results indicate that the approach focused on representation effectiveness outperformed baselines in all tested scenarios. The other approach, which also considers the size of created representations, produced competitive results keeping or even reducing the dimensionality of feature vectors up to 25%.

Tue Mar 17 2020
Computer Vision
Learning to Structure an Image with Few Colors
0
0
0
Wed Apr 11 2012
Computer Vision
Feature Extraction Methods for Color Image Similarity
Many User interactive systems are proposed all methods are trying to implement as a user friendly and various approaches proposed. In this paper we focus on the retrieval of images within a large image collection based on color projections and different mathematical approaches.
0
0
0
Wed Feb 25 2015
Computer Vision
Describing Colors, Textures and Shapes for Content Based Image Retrieval - A Survey
Images carry a lot of information in them which needs be utilized in an effective manner. Image retrieval has promising applications in numerous fields and has motivated researchers all over the world.
0
0
0
Wed Feb 26 2014
Computer Vision
Large-margin Learning of Compact Binary Image Encodings
The use of high-dimensional features has become a normal practice in many computer vision applications. The large dimension of these features is a limiting factor on the number of data points which may be effectively stored and processed. We address this problem by developing a novel approach to learning a compact binary encoding.
0
0
0
Tue Oct 02 2012
Machine Learning
A fast compression-based similarity measure with applications to content-based image retrieval
Compression-based similarity measures are effectively employed in applications on diverse data types with a basically parameter-free approach. There are problems in applying these techniques to medium-to-large datasets which have been seldom addressed. This paper proposes a similarity measure based on compression with dictionaries,
0
0
0
Thu Jan 30 2020
Machine Learning
Optimized Feature Space Learning for Generating Efficient Binary Codes for Image Retrieval
We address the problem of high-dimensionality of feature vectors extracted from neural networks by taking care of the global statistics of feature space. Classical approach of Linear Discriminant Analysis (LDA) is typically used for generating an optimized low dimensional feature space for single-labeled images.
0
0
0