Assessing invariance to affine transformations in image quality metrics
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912593384308736 |
|---|---|
| author | Alabau-Bosque, Nuria Daudén-Oliver, Paula Vila-Tomás, Jorge Laparra, Valero Malo, Jesús |
| author_facet | Alabau-Bosque, Nuria Daudén-Oliver, Paula Vila-Tomás, Jorge Laparra, Valero Malo, Jesús |
| contents | Subjective image quality metrics are usually evaluated according to the correlation with human opinion in databases with distortions that may appear in digital media. However, these oversee affine transformations which may represent better the changes in the images actually happening in natural conditions. Humans can be particularly invariant to these natural transformations, as opposed to the digital ones.
In this work, we propose a methodology to evaluate any image quality metric by assessing their invariance to affine transformations, specifically: rotation, translation, scaling, and changes in spectral illumination. Here, invariance refers to the fact that certain distances should be neglected if their values are below a threshold. This is what we call invisibility threshold of a metric. Our methodology consists of two elements: (1) the determination of a visibility threshold in a subjective representation common to every metric, and (2) a transduction from the distance values of the metric and this common representation. This common representation is based on subjective ratings of readily available image quality databases. We determine the threshold in such common representation (the first element) using accurate psychophysics. Then, the transduction (the second element) can be trivially fitted for any metric: with the provided threshold extension of the method to any metric is straightforward. We test our methodology with some well-established metrics and find that none of them show human-like invisibility thresholds.
This means that tuning the models exclusively to predict the visibility of generic distortions may disregard other properties of human vision as for instance invariances or invisibility thresholds. The data and code are publicly available to test other metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_17927 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Assessing invariance to affine transformations in image quality metrics Alabau-Bosque, Nuria Daudén-Oliver, Paula Vila-Tomás, Jorge Laparra, Valero Malo, Jesús Computer Vision and Pattern Recognition Artificial Intelligence Subjective image quality metrics are usually evaluated according to the correlation with human opinion in databases with distortions that may appear in digital media. However, these oversee affine transformations which may represent better the changes in the images actually happening in natural conditions. Humans can be particularly invariant to these natural transformations, as opposed to the digital ones. In this work, we propose a methodology to evaluate any image quality metric by assessing their invariance to affine transformations, specifically: rotation, translation, scaling, and changes in spectral illumination. Here, invariance refers to the fact that certain distances should be neglected if their values are below a threshold. This is what we call invisibility threshold of a metric. Our methodology consists of two elements: (1) the determination of a visibility threshold in a subjective representation common to every metric, and (2) a transduction from the distance values of the metric and this common representation. This common representation is based on subjective ratings of readily available image quality databases. We determine the threshold in such common representation (the first element) using accurate psychophysics. Then, the transduction (the second element) can be trivially fitted for any metric: with the provided threshold extension of the method to any metric is straightforward. We test our methodology with some well-established metrics and find that none of them show human-like invisibility thresholds. This means that tuning the models exclusively to predict the visibility of generic distortions may disregard other properties of human vision as for instance invariances or invisibility thresholds. The data and code are publicly available to test other metrics. |
| title | Assessing invariance to affine transformations in image quality metrics |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.17927 |