IMAGE SEGMENTATION AND OBJECT RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORK TECHNOLOGY
Background. An analysis of the processes of image segmentation is being carried out. An original method of image segmentation using a convolutional neural network is proposed. Materials and methods. A comparative assessment of existing segmentation methods such as threshold segmentation methods: O...
Guardado en:
Autores principales: | , , |
---|---|
Formato: | article |
Lenguaje: | EN RU |
Publicado: |
Penza State University Publishing House
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/4724ca36bfbe461fbf58fbd8179bca2a |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:4724ca36bfbe461fbf58fbd8179bca2a |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:4724ca36bfbe461fbf58fbd8179bca2a2021-12-01T11:54:30ZIMAGE SEGMENTATION AND OBJECT RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORK TECHNOLOGY10.21685/2307-4205-2021-3-82307-4205https://doaj.org/article/4724ca36bfbe461fbf58fbd8179bca2a2021-11-01T00:00:00Zhttps://doaj.org/toc/2307-4205Background. An analysis of the processes of image segmentation is being carried out. An original method of image segmentation using a convolutional neural network is proposed. Materials and methods. A comparative assessment of existing segmentation methods such as threshold segmentation methods: Otsu, Niblack, Bernsen, Savola, as well as the method of image segmentation using a convolutional neural network is carried out. Their advantages and disadvantages are evaluated. Examples of image segmentation by various methods are given. Algorithmic descriptions of segmentation methods are presented. Experiments were carried out to study the segmentation of frames (images) from a given video sequence. Results and conclusions. The results of the experiment, showing the operation of one or another segmentation method, are presented.A.I. GodunovS.T. BalanyanP.S. EgorovPenza State University Publishing Housearticleadaptive methodsthreshold methodssegmentationotsu's methodniblack's methodbernsen's methodsavol's methodconvolutional neural networkMotor vehicles. Aeronautics. AstronauticsTL1-4050ENRUНадежность и качество сложных систем, Iss 3 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN RU |
topic |
adaptive methods threshold methods segmentation otsu's method niblack's method bernsen's method savol's method convolutional neural network Motor vehicles. Aeronautics. Astronautics TL1-4050 |
spellingShingle |
adaptive methods threshold methods segmentation otsu's method niblack's method bernsen's method savol's method convolutional neural network Motor vehicles. Aeronautics. Astronautics TL1-4050 A.I. Godunov S.T. Balanyan P.S. Egorov IMAGE SEGMENTATION AND OBJECT RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORK TECHNOLOGY |
description |
Background. An analysis of the processes of image segmentation is being carried out. An original
method of image segmentation using a convolutional neural network is proposed. Materials and methods. A comparative
assessment of existing segmentation methods such as threshold segmentation methods: Otsu, Niblack, Bernsen,
Savola, as well as the method of image segmentation using a convolutional neural network is carried out. Their advantages
and disadvantages are evaluated. Examples of image segmentation by various methods are given. Algorithmic
descriptions of segmentation methods are presented. Experiments were carried out to study the segmentation of
frames (images) from a given video sequence. Results and conclusions. The results of the experiment, showing the operation
of one or another segmentation method, are presented. |
format |
article |
author |
A.I. Godunov S.T. Balanyan P.S. Egorov |
author_facet |
A.I. Godunov S.T. Balanyan P.S. Egorov |
author_sort |
A.I. Godunov |
title |
IMAGE SEGMENTATION AND OBJECT RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORK TECHNOLOGY |
title_short |
IMAGE SEGMENTATION AND OBJECT RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORK TECHNOLOGY |
title_full |
IMAGE SEGMENTATION AND OBJECT RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORK TECHNOLOGY |
title_fullStr |
IMAGE SEGMENTATION AND OBJECT RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORK TECHNOLOGY |
title_full_unstemmed |
IMAGE SEGMENTATION AND OBJECT RECOGNITION BASED ON CONVOLUTIONAL NEURAL NETWORK TECHNOLOGY |
title_sort |
image segmentation and object recognition based on convolutional neural network technology |
publisher |
Penza State University Publishing House |
publishDate |
2021 |
url |
https://doaj.org/article/4724ca36bfbe461fbf58fbd8179bca2a |
work_keys_str_mv |
AT aigodunov imagesegmentationandobjectrecognitionbasedonconvolutionalneuralnetworktechnology AT stbalanyan imagesegmentationandobjectrecognitionbasedonconvolutionalneuralnetworktechnology AT psegorov imagesegmentationandobjectrecognitionbasedonconvolutionalneuralnetworktechnology |
_version_ |
1718405230141374464 |