2020
DOI: 10.17081/invinno.8.1.3608
|View full text |Cite
|
Sign up to set email alerts
|

Remoción de lluvia en imágenes por medio de una arquitectura de autoencoder

Abstract: Objetivo: Usar técnicas computacionales para eliminar lluvia en imágenes. La motivación viene dada por el hecho de que, para muchos sistemas de visión por computadora, capturar correctamente la escena es clave, y si estos sistemas reciben imágenes degradadas por lluvia como entrada, su funcionamiento puede verse comprometido. Metodología: Se creó un conjunto de datos compuesto por 11000 imágenes sintéticas de lluvia. Estas fueron redimensionadas y normalizadas, para luego utilizar 9000 de ellas como conjunto d… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2021
2021
2021
2021

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(2 citation statements)
references
References 5 publications
0
2
0
Order By: Relevance
“…Convolutional Autoencoder is established on general autoencoder architecture along with the layers of convolutional encoding and decoding. The core task of this technique is to train the model enough to encode and decode a given image, by reconstructing the given input with the removal of unwanted features [24]. In addition to that, it is better suitable for image processing as the image structures are utilized to maximum capability.…”
Section: Convolutional Autoencodermentioning
confidence: 99%
See 1 more Smart Citation
“…Convolutional Autoencoder is established on general autoencoder architecture along with the layers of convolutional encoding and decoding. The core task of this technique is to train the model enough to encode and decode a given image, by reconstructing the given input with the removal of unwanted features [24]. In addition to that, it is better suitable for image processing as the image structures are utilized to maximum capability.…”
Section: Convolutional Autoencodermentioning
confidence: 99%
“…In our model, the encoding and decoding involve some loss of information in the process and to keep a track of it we have used Mean Squared Error (MSE). Firstly, the difference between the reconstructed output image and original version of the input image is calculated, and the MSE is calculated by averaging the square of the calculated error [24]. MSE can be calculated by the formula,…”
Section: Loss Functionmentioning
confidence: 99%