Difference between revisions of "Publications/hermary.21.seminar"
From LRDE
(Created page with "{{CSIReport | authors = Romain Hermary | title = Integration of Morphological Operators in Neural Networks | year = 2021 | number = 2122 | abstract = FIXME | type = techreport...") |
|||
| (One intermediate revision by the same user not shown) | |||
| Line 4: | Line 4: | ||
| year = 2021 |
| year = 2021 |
||
| number = 2122 |
| number = 2122 |
||
| + | | abstract = Image processing is a very broad field of study that encompasses a multitude of operations, each of them with different purposes and circumstances of use, complexities and results. Nowadays, the bests results for automatic image study (image segmentation, image classificationobject detection, etc.) are obtained using deep learningand more specifically convolutional neural networks. We explore and conduct experiments on a specific part of image processing, mathematical morphology, investigating on the best way of circumventing operations' complexities regarding their integration in a supervised learning pipeline. |
||
| − | | abstract = FIXME |
||
| type = techreport |
| type = techreport |
||
| id = hermary.21.seminar |
| id = hermary.21.seminar |
||
Latest revision as of 16:39, 30 June 2022
- Authors
- Romain Hermary
- Type
- techreport
- Year
- 2021
- Number
- 2122
Abstract
Image processing is a very broad field of study that encompasses a multitude of operations, each of them with different purposes and circumstances of use, complexities and results. Nowadays, the bests results for automatic image study (image segmentation, image classificationobject detection, etc.) are obtained using deep learningand more specifically convolutional neural networks. We explore and conduct experiments on a specific part of image processing, mathematical morphology, investigating on the best way of circumventing operations' complexities regarding their integration in a supervised learning pipeline.