Histogram Layers for Neural Engineered Features
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_ | 1866915411646218240 |
|---|---|
| author | Peeples, Joshua Kharsa, Salim Al Saleh, Luke Zare, Alina |
| author_facet | Peeples, Joshua Kharsa, Salim Al Saleh, Luke Zare, Alina |
| contents | In the computer vision literature, many effective histogram-based features have been developed. These engineered features include local binary patterns and edge histogram descriptors among others and they have been shown to be informative features for a variety of computer vision tasks. In this paper, we explore whether these features can be learned through histogram layers embedded in a neural network and, therefore, be leveraged within deep learning frameworks. By using histogram features, local statistics of the feature maps from the convolution neural networks can be used to better represent the data. We present neural versions of local binary pattern and edge histogram descriptors that jointly improve the feature representation and perform image classification. Experiments are presented on benchmark and real-world datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17176 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Histogram Layers for Neural Engineered Features Peeples, Joshua Kharsa, Salim Al Saleh, Luke Zare, Alina Computer Vision and Pattern Recognition In the computer vision literature, many effective histogram-based features have been developed. These engineered features include local binary patterns and edge histogram descriptors among others and they have been shown to be informative features for a variety of computer vision tasks. In this paper, we explore whether these features can be learned through histogram layers embedded in a neural network and, therefore, be leveraged within deep learning frameworks. By using histogram features, local statistics of the feature maps from the convolution neural networks can be used to better represent the data. We present neural versions of local binary pattern and edge histogram descriptors that jointly improve the feature representation and perform image classification. Experiments are presented on benchmark and real-world datasets. |
| title | Histogram Layers for Neural Engineered Features |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.17176 |