A Genetic Algorithm Approach for ImageRepresentation Learning through Color Quantization

TL;DR

This paper introduces a genetic algorithm-based method for optimizing color quantization to improve image feature extraction and representation efficiency, enhancing content-based image retrieval performance.

Contribution

It presents two novel data-driven approaches using genetic algorithms for optimized color quantization in image representation learning, combining handcrafted and learned features.

Findings

Outperformed baseline methods in image retrieval accuracy.

Achieved up to 25% reduction in feature vector dimensionality.

Demonstrated effectiveness across eight diverse datasets.

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%.