Evaluating the Potential of Texture and Color Descriptors for Remote Sensing Image Retrieval and Classification

By J. A. D. Santos, Otávio Augusto Bizetto Penatti, Ricardo da Silva Torres. 2010

89 citations recorded by the source corpus.

Classifying Remote Sensing Images (RSI) is a hard task. There are automatic approaches whose results normally need to be revised. The identification and polygon extraction tasks usually rely on applying classification strategies that exploit visual aspects related to spectral and texture patterns identified in RSI regions. There are a lot of image descriptors proposed in the literature for content-based image retrieval purposes that can be useful for RSI classification. This paper presents a comparative study to evaluate the potential of using successful color and texture image descriptors for remote sensing retrieval and classification. Seven descriptors that encode texture information and twelve color descriptors that can be used to encode spectral information were selected. We perform experiments to evaluate the effectiveness of these descriptors, considering image retrieval and classification tasks. To evaluate descriptors in classification tasks, we also propose a methodology based on KNN classifier. Experiments demonstrate that Joint Auto-Correlogram (JAC), Color Bitmap, Invariant Steerable Pyramid Decomposition (SID) and Quantized Compound Change Histogram (QCCH) yield the

Subfields: Computer Vision and Pattern Recognition, Media Technology, Information Retrieval & Search, Remote Sensing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

In Information Retrieval & Search

In Remote Sensing

Citations in the corpus

Towards better exploiting convolutional neural networks for remote sensing scene classification (2016, methodology): “Although several of these visual descriptors have been proposed or successfully used for remote sensing image processing [26, 2, 27], there are many applications that demand more speciﬁc techniques mainly due to the presence of non-visible information provided by multiple spectral bands and the…”
Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks (2016, methodology): “To evaluate the influence of using L number of stacked CNN layers for our task of per-pixel classification, we use four different CNNs with varying context sizes m = [15, 25, 35, 45] and calculate the accuracy using L = [1, 2, 3, 4, 5] numbers of CNN layers.”
Scene Classification With Recurrent Attention of VHR Remote Sensing Images (2019, background): “Color histograms and texture descriptors [8], [27] are global features that can be sent to the classifier directly.”
AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification (2016, methodology): “Although single type of features works well for classification [54], [55], [61], the combinations of complementary features can often improve the results [12], [19], [27].”
Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? (2015, methodology): “Although many descriptors have been proposed or successfully used for RS image processing [42, 11, 3], some applications require more specific description techniques.”