Image retrieval based on texture using latent space representation of discrete Fourier transformed maps
[EN] Texture-based instance retrieval is typically performed on images that present a single texture pattern and is mainly applied to the retrieval of fabrics or textiles. In this work, we apply it to indoor scene images that typically present many different texture patterns, which constitutes a mor...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión aceptada para publicación |
| Fecha de publicación: | 2021 |
| País: | España |
| Institución: | Universidad de León |
| Repositorio: | BULERIA. Repositorio Institucional de la Universidad de León |
| OAI Identifier: | oai:buleria.unileon.es:10612/23237 |
| Acceso en línea: | https://link.springer.com/article/10.1007/s00521-021-05955-2 https://hdl.handle.net/10612/23237 |
| Access Level: | acceso abierto |
| Palabra clave: | Informática Ingeniería de sistemas Texture retrieval Convolutional autoencoders Texture classification Discrete Fourier transform 2209.90 Tratamiento Digital. Imágenes 1203.12 Bancos de Datos 1203.04 Inteligencia Artificial 1203.17 Informática |
| Sumario: | [EN] Texture-based instance retrieval is typically performed on images that present a single texture pattern and is mainly applied to the retrieval of fabrics or textiles. In this work, we apply it to indoor scene images that typically present many different texture patterns, which constitutes a more challenging problem. Such retrieval systems, together with the retrieval of faces and objects, can be used as a valuable tool for evidence matching in crime scene investigation. Even though recent deep learning-based approaches have made significant improvement in many computer vision tasks, texture retrieval remains an open problem. In this work, we introduce a Fourier-based approach, in which spatial images and their discrete Fourier transform maps are combined to derive a novel texture representation. We further present a new and efficient texture-based image retrieval framework based on region proposal networks, convolutional autoencoders and transfer learning, in which we extract the features from the latent space layer of the encoder as texture descriptors. The experimental results on four datasets: TextileTube, Outex, USPtex and Stex, validated the effectiveness of our proposed method, yielding better results than the current state of the art. |
|---|