Semantic filtering through deep source separation on microscopy images
By their very nature microscopy images of cells and tissues consist of a limited number of object types or components. In contrast to most natural scenes, the composition is known a priori. Decomposing biological images into semantically meaningful objects and layers is the aim of this paper. Buildi...
| Main Authors: | , |
|---|---|
| Format: | Conference item |
| Published: |
Springer
2019
|
| _version_ | 1826271090740035584 |
|---|---|
| author | Javer, A Rittscher, J |
| author_facet | Javer, A Rittscher, J |
| author_sort | Javer, A |
| collection | OXFORD |
| description | By their very nature microscopy images of cells and tissues consist of a limited number of object types or components. In contrast to most natural scenes, the composition is known a priori. Decomposing biological images into semantically meaningful objects and layers is the aim of this paper. Building on recent approaches to image de-noising we present a framework that achieves state-of-the-art segmentation results requiring little or no manual annotations. Here, synthetic images generated by adding cell crops are sufficient to train the model. Extensive experiments on cellular images, a histology data set, and small animal videos demonstrate that our approach generalizes to a broad range of experimental settings. As the proposed methodology does not require densely labelled training images and is capable of resolving the partially overlapping objects it holds the promise of being of use in a number of different applications. |
| first_indexed | 2024-03-06T21:51:09Z |
| format | Conference item |
| id | oxford-uuid:4b4f2a6e-ef5b-4bc4-a6b7-600cf21abe1e |
| institution | University of Oxford |
| last_indexed | 2024-03-06T21:51:09Z |
| publishDate | 2019 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:4b4f2a6e-ef5b-4bc4-a6b7-600cf21abe1e2022-03-26T15:42:49ZSemantic filtering through deep source separation on microscopy imagesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:4b4f2a6e-ef5b-4bc4-a6b7-600cf21abe1eSymplectic Elements at OxfordSpringer2019Javer, ARittscher, JBy their very nature microscopy images of cells and tissues consist of a limited number of object types or components. In contrast to most natural scenes, the composition is known a priori. Decomposing biological images into semantically meaningful objects and layers is the aim of this paper. Building on recent approaches to image de-noising we present a framework that achieves state-of-the-art segmentation results requiring little or no manual annotations. Here, synthetic images generated by adding cell crops are sufficient to train the model. Extensive experiments on cellular images, a histology data set, and small animal videos demonstrate that our approach generalizes to a broad range of experimental settings. As the proposed methodology does not require densely labelled training images and is capable of resolving the partially overlapping objects it holds the promise of being of use in a number of different applications. |
| spellingShingle | Javer, A Rittscher, J Semantic filtering through deep source separation on microscopy images |
| title | Semantic filtering through deep source separation on microscopy images |
| title_full | Semantic filtering through deep source separation on microscopy images |
| title_fullStr | Semantic filtering through deep source separation on microscopy images |
| title_full_unstemmed | Semantic filtering through deep source separation on microscopy images |
| title_short | Semantic filtering through deep source separation on microscopy images |
| title_sort | semantic filtering through deep source separation on microscopy images |
| work_keys_str_mv | AT javera semanticfilteringthroughdeepsourceseparationonmicroscopyimages AT rittscherj semanticfilteringthroughdeepsourceseparationonmicroscopyimages |