<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Deconvolutional neural networks are a very accurate tool for semantic image segmentation. Segmenting curvilinear meandering regions is a typical task in computer vision applied to navigational, civil engineering, and defence problems. In the study, such regions of interest are modelled as meandering transparent stripes whose width is not constant. The stripe on the white background is formed by the upper and lower non-parallel black curves so that the upper and lower image parts are completely separated. An algorithm of generating datasets of such regions is developed. It is revealed that deeper networks segment the regions more accurately. However, the segmentation is harder when the regions become bigger. This is why an alternative method of the region segmentation consisting in segmenting the upper and lower image parts by subsequently unifying the results is not effective. If the region of interest becomes bigger, it must be squeezed in order to avoid segmenting the empty image. Once the squeezed region is segmented, the image is conversely rescaled to the original view. To control the accuracy, the mean BF score having the least value among the other accuracy indicators should be maximised first.</p></abstract>

Deconvolutional neural networks are a very accurate tool for semantic image segmentation. Segmenting curvilinear meandering regions is a typical task in computer vision applied to navigational, civil engineering, and defence problems. In the study, such regions of interest are modelled as meandering transparent stripes whose width is not constant. The stripe on the white background is formed by the upper and lower non-parallel black curves so that the upper and lower image parts are completely separated. An algorithm of generating datasets of such regions is developed. It is revealed that deeper networks segment the regions more accurately. However, the segmentation is harder when the regions become bigger. This is why an alternative method of the region segmentation consisting in segmenting the upper and lower image parts by subsequently unifying the results is not effective. If the region of interest becomes bigger, it must be squeezed in order to avoid segmenting the empty image. Once the squeezed region is segmented, the image is conversely rescaled to the original view. To control the accuracy, the mean BF score having the least value among the other accuracy indicators should be maximised first.

A Prototype Model for Semantic Segmentation of Curvilinear Meandering Regions by Deconvolutional Neural Networks

Applied Computer Systems

This work is licensed under the Creative Commons Attribution 4.0 Public License.

Deconvolutional neural networks are a very accurate tool for semantic image segmentation. Segmenting curvilinear meandering regions is a typical task in...

A Prototype Model for Semantic Segmentation of Curvilinear Meandering Regions by Deconvolutional Neural Networks

Online veröffentlicht: 05. Juni 2020

Seitenbereich: 62 - 69

DOI: https://doi.org/10.2478/acss-2020-0008

Schlüsselwörter
Curvilinear meandering region, deconvolutional layer, empty image segmentation, mean BF score, neural network, overfitting, semantic segmentation, toy dataset

© 2020 Vadim Romanuke, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 Public License.

A Prototype Model for Semantic Segmentation of Curvilinear Meandering Regions by Deconvolutional Neural Networks

Online veröffentlicht: 05. Juni 2020

Seitenbereich: 62 - 69

DOI: https://doi.org/10.2478/acss-2020-0008

SchlüsselwörterCurvilinear meandering region, deconvolutional layer, empty image segmentation, mean BF score, neural network, overfitting, semantic segmentation, toy dataset

© 2020 Vadim Romanuke, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 Public License.

Schlüsselwörter
Curvilinear meandering region, deconvolutional layer, empty image segmentation, mean BF score, neural network, overfitting, semantic segmentation, toy dataset