Color and texture descriptors

By Bangalore S. Manjunath, Jens-Rainer Ohm, V. Vasudevan, A. Yamada. IEEE Trans. Circuits Syst. Video Technol., 2001

1,884 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/685b1fb262a2be4749f8ed23f36230699d85c997

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

Citations in the corpus

Content-based image retrieval: approaches and trends of the new age (2005, positive): “A set of color and texture descriptors rigorously tested for inclusion in the MPEG-7 standard, and well suited to natural images and video, is described in [69].”
Content-based image retrieval using color difference histogram (2013, methodology): “In the MPEG-7 standard, color descriptors consist of a number of histogram descriptors, such as the dominant color descriptor, the color layout descriptor, and a scalable color descriptor [9,10].”
A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data (2014, methodology): “3, bottom-up global features, such as Gist [27] and MPEG-7 descriptors [28], can also play an important role inmultimodal datamodeling [12].”
Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval (2006, background): “In the system, images are represented by three main features: color [23], [17], [14], [9], [16], texture [14], [24], [13], [15], [4], [30], and shape [9], [16].”
Cross-modal Retrieval with Correspondence Autoencoder (2014, neutral): “• MPEG-7 descriptors [16].”
Saliency Detection via a Multiple Self-Weighted Graph-Based Manifold Ranking (2020, methodology): “1) Low-Level Appearance Features: Three kinds of low-level appearance features are used in our work, consisting of color and texture [42], which are used to represent each super-pixel.”
Improved Multimodal Deep Learning with Variation of Information (2014, methodology): “6 Specifically, the image feature is 3857 dimensional vector composed of Pyramid Histogram of Words (PHOW) features [3], GIST [22], and MPEG-7 descriptors [18].”
A comparative study of image retargeting (2010, methodology): “For this purpose we used two measures from the MPEG-7 standard [MPEG-7 2002; Manjunath et al. 2001] based on edge histogram (EH) [Manjunath et al.”
A Three-Layered Graph-Based Learning Approach for Remote Sensing Image Retrieval (2016, methodology): “We also notice that the overall computational time of the second layer-SIFT is less than the methods in [19] and [51], but the average ANMRR is the smallest.”
“Knock! Knock! Who is it?” probabilistic person identification in TV-series (2012, methodology): “Thus, we are able to detect these sequences reliably by thresholding the difference between each frame and its eight dominant colour representation [11] (19 detections, 0 false positives, 0 misses).”
Features for image retrieval: an experimental comparison (2008, background): “An overview of these features can be found in [68, 69, 70, 71].”
Evaluating the Potential of Texture and Color Descriptors for Remote Sensing Image Retrieval and Classification (2010, methodology): “Color Structure (CSD) [17] is one of the color descriptors used in the MPEG-7 standa rd.”
A Privacy-Preserving and Copy-Deterrence Content-Based Image Retrieval Scheme in Cloud Computing (2016, background): “MPEG-7 is a multimedia content description standard which offers a comprehensive set of descriptors for the multimedia data description [34].”
Deep Variational Canonical Correlation Analysis (2016, background): “, 2007), GIST (Oliva and Torralba, 2001), and MPEG-7 descriptors (Manjunath et al., 2001), while the text feature is a 2000-dimensional binary vector of frequent tags.”
Content-Based Image Retrieval Using Multiresolution Color and Texture Features (2008, methodology): “As measures of retrieval accuracy, we used precision versus recall [27] and ANMRR (average normalized modified retrieval rank) [28], [29].”
A survey of content-based image retrieval with high-level semantics (2007, methodology): “Color spaces shown to be closer to human perception and used widely in RBIR include, RGB, LAB, LUV, HSV (HSL), YCrCb and the hue-min-max-difference (HMMD) [21,25,27,31,33].”
Dissimilarity-based people re-identification and search for intelligent video surveillance (2013, methodology): “The Color Structure Descriptor (CSD) of MPEG-7 [90] is used in [62], and encodes the distribution of colour by the following steps: (i) move a window of size 8×8 pixel over the picture ; (ii) determine which colours are present in within the window; (iii) increase the corresponding bins in a color h”