3D Texture Recognition Using Bidirectional Feature Histograms
Citations
1,145 citations
Cites background or methods or result from "3D Texture Recognition Using Bidire..."
..., 1999), the same database used by Cula and Dana (2004) and Leung and Malik (2001). It is demonstrated that the classifier developed here achieves performance superior to that of Cula and Dana (2004) and Leung and Malik (2001), while requiring only a single image as input and with no information (implicit or explicit) about the illumination and viewing conditions. The CUReT database contains 61 textures, and each texture has 205 images obtained under different viewing and illumination conditions. The variety of textures in this database is shown in Fig. 3. Results are reported for all 61 textures. A preliminary version of these results appeared in Varma and Zisserman (2002)....
[...]
...The first experiment, where we classify images from 20 textures, corresponds to the setup employed by Cula and Dana (2004)....
[...]
...Cula and Dana (2004) presented an algorithm based on Leung and Malik’s framework but capable of classifying single images without requiring any a priori information. Using much the same filter bank as Leung and Malik, they showed how to achieve results comparable to Leung and Malik (2001) but using 2D textons generated from single images instead of registered image stacks....
[...]
...Our approach is most closely related to those of Leung and Malik (2001), Schmid (2001) and Cula and Dana (2004)....
[...]
...Our approach is most closely related to those of Leung and Malik (2001), Schmid (2001) and Cula and Dana (2004). Leung and Malik’s method is not rotationally invariant and requires as input a set of registered images acquired under a (implicitly) known set of imaging conditions. Schmid’s approach is rotationally invariant but the invariance is achieved in a different manner to ours, and texton clustering is in a higher dimensional space. More importantly, only a single model is used to characterise each texture class rather than having multiple models to account for the variations in imaging conditions. Cula and Dana classify from single images, but the method is not rotationally invariant and their algorithm for model selection differs from the one developed in this paper. These points are discussed in more detail subsequently. The paper is organised as follows: in Section 2, the basic classification algorithm is developed within a rotationally invariant framework. The clustering, learning and classification steps of the algorithm are described, and the performance of four filter sets is compared. The sets include those used by Schmid (2001) and Leung and Malik (2001), and two rotationally invariant sets based on maximal filter responses....
[...]
810 citations
Additional excerpts
..., [16, 73, 75]....
[...]
649 citations
Cites background or methods from "3D Texture Recognition Using Bidire..."
...The power of the method is demonstrated by classifying 2806 images of all 61 materials present in the Columbia-Utrecht database....
[...]
...Each of the materials in the database has been imaged under 205 different viewing and illumination conditions....
[...]
...Out of these, 46 images per class are randomly chosen for training and the remaining 46 per class are chosen for testing....
[...]
310 citations
Additional excerpts
...Ç...
[...]
273 citations
Cites methods from "3D Texture Recognition Using Bidire..."
...χ(2) was successfully used for texture and object categories classifica tion [5,6,7], near duplicate image identification[ 8], local descriptors matching [ 9], shape classification [ 10,11] and boundary detection [ 12]....
[...]
References
2,037 citations
"3D Texture Recognition Using Bidire..." refers methods in this paper
...Principal component analysis is performed on the histogram of filter outputs and recognition is done using the SLAM library (Nene et al., 1994) (Murase and Nayar, 1995)....
[...]
...Principal component analysis is performed on the histogram of filter outputs and recognition is done using the SLAM library (Nene et al., 1994; Murase and Nayar, 1995)....
[...]
...This approach has been inspired by (Murase and Nayar, 1995), where a similar problem is treated, specifically an object is represented by set of images taken from various poses, and PCA is used to obtain a compact lower-dimensional representation....
[...]
...In all our experiments, PCA is accomplished by employing the SLAM software library (Nene et al., 1994; Murase and Nayar, 1995)....
[...]
...In all our experiments, PCA is accomplished by employing the SLAM software library (Nene et al., 1994) (Murase and Nayar, 1995)....
[...]
1,762 citations
"3D Texture Recognition Using Bidire..." refers background or methods in this paper
...A widely used computational approach for encoding the local structural attributes of textures is based on multichannel filtering (Bovik et al., 1990) (Jain et al., 1999) (Randen and Husoy, 1999) (Leung and Malik, 2001)....
[...]
...As in many approaches in texture literature (Leung and Malik, 2001) (Aksoy and Haralick, 1999) (Puzicha et al., 1999) (Ma and Manjunath, 1996), we cluster the feature space to determine the set of prototypes among the population....
[...]
...Based on the classic concept of textons, and also based on modern generalizations (Leung and Malik, 2001), we obtain a finite set of local structural features that can be found within a large collection of texture images from various samples....
[...]
...…appearance and it has been used in numerous recent studies (Koenderink et al., 1999) (van Ginneken et al., 1998) (Leung and Malik, 1999) (Leung and Malik, 2001) (Suen and Healey, 1998) (Dana and Nayar, 1998) (Dana and Nayar, 1999b) (Dana and Nayar, 1999a) (Suen and Healey, 2000) (Liu et al.,…...
[...]
...The most notable prior work is the 3D texton method (Leung and Malik, 1999) (Leung and Malik, 2001)....
[...]
1,757 citations
"3D Texture Recognition Using Bidire..." refers background in this paper
...Early psychophysical studies brought evidence that discrimination of black and white textures is based on pre-attentively discriminable conspicuous local features called textons (Julesz, 1981)....
[...]
1,582 citations
"3D Texture Recognition Using Bidire..." refers methods in this paper
...A widely used computational approach for encoding the local structural attributes of textures is based on multichannel filtering (Bovik et al., 1990) (Jain et al....
[...]
...A widely used computational approach for encoding the local structural attributes of textures is based on multichannel filtering (Bovik et al., 1990) (Jain et al., 1999) (Randen and Husoy, 1999) (Leung and Malik, 2001)....
[...]
1,567 citations
"3D Texture Recognition Using Bidire..." refers methods in this paper
...A widely used computational approach for encoding the local structural attributes of textures is based on multichannel filtering (Bovik et al., 1990; Jain et al., 1999; Randen and Husoy, 1999; Leung and Malik, 2001)....
[...]
...A widely used computational approach for encoding the local structural attributes of textures is based on multichannel filtering (Bovik et al., 1990) (Jain et al., 1999) (Randen and Husoy, 1999) (Leung and Malik, 2001)....
[...]