Categorisation and Retrieval of Scene Photographs from JPEG Compressed Database

Ladret, Patricia; Guérin–Dugué, Anne

doi:10.1007/s100440170016

Cited by 10 publications

(16 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DCT domain was explored by Ladret and Guérin-Dugué [11] to perform image classification and retrieval by using K-nearest neighbour (KNN) algorithm. Tests were performed on a database consisting of only 470 pictures (256 × 256 pixels, grey levels values) from COREL database.…”

Section: Scene Classification Extracting Features On Frequency Domainmentioning

confidence: 99%

“…Taking into account the memory constraints in imaging devices, the reviewed approaches cannot be used in their original form. Our work is partially inspired by [11]. We have assessed [11] on a benchmark standard data set used by computer vision community adapting it to work on constrained domain by means of ad hoc strategies better specified in the forthcoming sections.…”

Section: Scene Classification Extracting Features On Frequency Domainmentioning

confidence: 99%

“…Our work is partially inspired by [11]. We have assessed [11] on a benchmark standard data set used by computer vision community adapting it to work on constrained domain by means of ad hoc strategies better specified in the forthcoming sections. We propose to extract features from the DCT blocks just to have useful insight with respect to the overall orientation of the main details present in the image; as described in [18,26] such info can be used to infer the category of a scene at superordinate level of description.…”

Section: Scene Classification Extracting Features On Frequency Domainmentioning

confidence: 99%

“…The power spectrum of an image contains enough relevant information about its global structure [11,18,26]. As discussed in Section 2.1, different studies pointed out that information extracted in frequency domain can be holistically encoded to represent the scene for naturalness classification.…”

Section: Histograms Of Oriented Dct Blocksmentioning

confidence: 99%

“…Images are represented as histograms of oriented blocks [11] coupled with statistical weights to evaluate how important is an orientation in discriminating the classes under consideration [12]. Two local features are extracted and used to represent each 8 × 8 spatial block belonging to a considered image ( Fig.…”

Section: Introduction and Motivationsmentioning

confidence: 99%

See 4 more Smart Citations

Scene classification in compressed and constrained domain

Farinella

Battiato

2011

IET Comput. Vis.

View full text Add to dashboard Cite

Holistic representations of natural scenes are an effective and powerful source of information for semantic classification and analysis of images. Despite the technological hardware and software advances, consumer single-sensor imaging devices technology are quite far from the ability of recognising scenes and/or to exploit the visual content during (or after) acquisition time. The frequency domain has been successfully exploited to holistically encode the content of natural scenes in order to obtain a robust representation for scene classification. The authors exploit a holistic representation of the scene in the discrete cosine transform domain fully compatible with the JPEG format. The advised representation is coupled with a logistic classifier to perform classification of the scene at superordinate level of description (e.g. natural against artificial), or to discriminate between multiple classes of scenes usually acquired by a consumer imaging device (e.g. portrait, landscape and document). The proposed method is able to work in constrained domain. Experiments confirm the effectiveness of the proposed method. The obtained results closely match state-of-the-art methods in terms of accuracy outperforming in terms of computational resources.

show abstract

Section: Scene Classification Extracting Features On Frequency Domainmentioning

confidence: 99%

Section: Scene Classification Extracting Features On Frequency Domainmentioning

confidence: 99%

Section: Scene Classification Extracting Features On Frequency Domainmentioning

confidence: 99%

Section: Histograms Of Oriented Dct Blocksmentioning

confidence: 99%

Section: Introduction and Motivationsmentioning

confidence: 99%

See 3 more Smart Citations

Scene classification in compressed and constrained domain

Farinella

Battiato

2011

IET Comput. Vis.

View full text Add to dashboard Cite

show abstract

Spatial Hierarchy of Textons Distributions for Scene Classification

Battiato

Farinella

Gallo

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper proposes a method to recognize scene categories using bags of visual words obtained hierarchically partitioning into subregion the input images. Specifically, for each subregion the Textons distribution and the extension of the corresponding subregion are taken into account. The bags of visual words computed on the subregions are weighted and used to represent the whole scene. The classification of scenes is carried out by a Support Vector Machine. A k-nearest neighbor algorithm and a similarity measure based on Bhattacharyya coefficient are used to retrieve from the scene database those that contain similar visual content to a given a scene used as query. Experimental tests using fifteen different scene categories show that the proposed approach achieves good performances with respect to the state of the art methods.

show abstract