Centre de documentation
scientifique

Recognition of varying size scene images using semantic analysis of deep activation maps / Shikha Gupta in Machine Vision and Applications, vol 32 n° 2 (March 2021)  

Public [article]  inMachine Vision and Applications > vol 32 n° 2 (March 2021) . - n° 52 Titre : Recognition of varying size scene images using semantic analysis of deep activation maps Type de document : Article/Communication Auteurs : Shikha Gupta, Auteur ; A.D. Dileep, Auteur ; Veena Thenkanidiyoor, Auteur Année de publication : 2021 Article en page(s) : n° 52 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse de groupement [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] compréhension de l'image [Termes IGN] méthode fondée sur le noyau [Termes IGN] modèle conceptuel de données [Termes IGN] reconnaissance de formes [Termes IGN] segmentation sémantique Résumé : (auteur) Understanding the complex semantic structure of scene images requires mapping the image from pixel space to high-level semantic space. In semantic space, a scene image is represented by the posterior probabilities of concepts (e.g., ‘car,’ ‘chair,’ ‘window,’ etc.) present in it and such representation is known as semantic multinomial (SMN) representation. SMN generation requires a concept annotated dataset for concept modeling which is infeasible to generate manually due to the large size of databases. To tackle this issue, we propose a novel approach of building the concept model via pseudo-concepts. Pseudo-concept acts as a proxy for the actual concept and gives the cue for its presence instead of actual identity. We propose to use filter responses from deeper convolutional layers of convolutional neural networks (CNNs) as pseudo-concepts, as filters in deeper convolutional layers are trained for different semantic concepts. Most of the prior work considers fixed-size (≈227×227) images for semantic analysis which suppresses many concepts present in the images. In this work, we preserve the true-concept structure in images by passing in their original resolution to convolutional layers of CNNs. We further propose to prune the non-prominent pseudo-concepts, group the similar one using kernel clustering and later model them using a dynamic-based support vector machine. We demonstrate that resulting SMN representation indeed captures the semantic concepts better and results in state-of-the-art classification accuracy on varying size scene image datasets such as MIT67 and SUN397. Numéro de notice : A2021-454 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00138-021-01168-8 Date de publication en ligne : 01/03/2021 En ligne : https://doi.org/10.1007/s00138-021-01168-8 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97898 [article]