A Genetic Algorithm Approach for ImageRepresentation Learning through Color Quantization
This work addresses the need for more effective and compact image representations in content-based image retrieval, though it is incremental as it combines existing methods.
The authors tackled the problem of learning image representations for content-based retrieval by optimizing color quantization schemes using genetic algorithms, resulting in one approach outperforming baselines across eight datasets and another achieving competitive results while reducing feature vector dimensionality by up to 25%.
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%.