Constructing models for content-based image retrieval

By Cordelia Schmid. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, 2001

446 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/db7159af39b66cde32cec502a17d48436b541d00

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

Texture classification: are filter banks necessary? (2003, methodology): “This is somewhat similar to the co-occurrence representation of [16] for filter banks.”
Person Re-Identification by Support Vector Ranking (2010, methodology): “Feature Extraction: The features used were 8 colour channels (RGB, HS and YCbCr) and 21 texture filters (Gabor [2] and Schmid [11]) applied to the luminance channel.”
Unsupervised segmentation of natural images via lossy data compression (2008, methodology): “We have experimented with using both simple window features and two classical filter banks, namely, the Leung-Malik set [18] and the Schmid set [30], in conjunction with our clustering algorithm.”
A Visual Category Filter for Google Images (2004, background): “image patches [3, 16], texture regions [18] or Haar wavelets [22]).”
Combined Object Categorization and Segmentation With an Implicit Shape Model (2004, methodology): “When regularly textured objects are used, the shape can be modelled by spatial frequency statistics of texture descriptors [20].”
A Statistical Approach to Texture Classification from Single Images (2004, methodology): “Our approach is most closely related to those of Leung and Malik (2001), Schmid (2001) and Cula and Dana (2004).”
A Statistical Approach to Material Classification Using Image Patch Exemplars (2009, result): “Hence, in this paper, we present comparisons with the MR8 ﬁlter bank.”
Object class recognition by unsupervised scale-invariant learning (2003, background): “[6, 9, 11]), has recently gained some attention in the machine vision literature [1, 2, 3, 4, 13, 14, 19] with an emphasis on the detection of faces [12, 15, 16].”
A sparse texture representation using local affine regions (2005, background): “Invariance to such transformations is highly desirable for many applications, including wide-baseline stereo matching [1, 40, 41, 45], indexing and retrieval in image and video databases [32, 42, 43, 44], and classi(cid:12)cation of images of materials [46, 47].”
Viewpoint Invariant Texture Description Using Fractal Analysis (2009, background): “Closest related to this work are a number of studies, which achieve robustness to view-point changes by using local descriptors or filter responses, which are rotationally or locally affine invariant (Cula and Dana 2001; Schmid 2001; Varma and Zisserman 2002, 2003).”
The Synthesizability of Texture Examples (2014, methodology): “Features for material classification include statistics of filter responses [20, 28, 34], joint intensity distributions within a compact neighborhood [36, 22], geometric features over topographic maps [38], and high-level semantic attributes [29].”
Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features (2008, methodology): “Two families of texture filters are used, Schmid [23] and Gabor [24].”
Classifying Images of Materials: Achieving Viewpoint and Illumination Independence (2002, methodology): “We also plan to investigate how the co-occurrence of textons (as in [18]) can lead to further improvements.”
Region Covariance: A Fast Descriptor for Detection and Classification (2006, methodology): “– S: A set of 13 circular symmetric filters was used by Schmid [14].”
Optic Disk and Cup Segmentation From Monocular Color Retinal Images for Glaucoma Assessment (2011, unknown): “Second, we use a special class of texture filter bank proposed in [49] defined as Fig.”
Animals on the Web (2006, background): “There has been some work on recognizing animal categories using deformable models of shape [17, 18].”