Centre de documentation
scientifique

Deep learning-based image de-raining using discrete Fourier transformation / Prasen Kumar Sharma in The Visual Computer, vol 37 n° 8 (August 2021)  

Public [article]  inThe Visual Computer > vol 37 n° 8 (August 2021) . - pp 2083 - 2096 Titre : Deep learning-based image de-raining using discrete Fourier transformation Type de document : Article/Communication Auteurs : Prasen Kumar Sharma, Auteur ; Sathisha Basavaraju, Auteur ; Arijit Sur, Auteur Année de publication : 2021 Article en page(s) : pp 2083 - 2096 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] bruit (théorie du signal) [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] décomposition d'image [Termes IGN] filtrage du bruit [Termes IGN] pluie [Termes IGN] transformation de Fourier Résumé : (auteur) Single image rain streak removal is a well-explored topic in the field of computer vision. The de-raining problem is modeled as an image decomposition task where a rainy image is decomposed into rain-free background image and rain streek map. Unlike most of the existing de-raining methods, this paper attempts to decompose the rainy image in the frequency domain. The idea is inspired by pseudo-periodic characteristics of the noise signal (here the rain streaks) which leave some traces in the frequency domain, and the same can be utilized to predict the noise signal. In this paper, a deep learning-based rain streak prediction model is proposed which learns in discrete Fourier transform Oppenheim and Schafer (Discrete-Time Signal Processing, Prentice Hall, Upper Saddle River, 1989) domain. To the best of our knowledge, this is the first approach where compressed domain coefficients are directly used as input to a deep convolutional neural network. The proposed model has been tested on publicly available synthetic datasets Fu et al. (in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. https://doi.org/10.1109/CVPR.2017.186, Yang et al. (in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. https://doi.org/10.1109/CVPR.2017.183), Yeh et al. (in: 2015 IEEE International Conference on Consumer Electronics-Taiwan, 2015. https://doi.org/10.1109/ICCE-TW.2015.7216999) and results are found to be comparable with the state of the art methods in the spatial domain. The presented analysis and study have an obvious indication to extend transform domain input to train the deep learning architecture especially image de-noising like problems. Numéro de notice : A2021-597 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00371-020-01971-w Date de publication en ligne : 16/09/2020 En ligne : https://doi.org/10.1007/s00371-020-01971-w Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98226 [article]