A rigid-motion scattering computes adaptive invariants along translations and rotations, with
a deep convolutional network. Convolutions are calculated on the rigid-motion group, with …

An affine invariant representation is constructed with a cascade of invariants, which
preserves information for classification. A joint translation and rotation invariant …

Designing effective features is a fundamental problem in computer vision. However, it is
usually difficult to achieve a great tradeoff between discriminative power and robustness …

Texture analysis is a very important area in the field of computer vision and related fields.
There are a good number of databases developed by different research groups for various …

Local binary patterns (LBP) have powerful discriminative capabilities. However, traditional
methods with LBP histograms cannot capture spatial structures of LBP codes. To extract the …

Large variations in image background may cause partial matching and normalization
problems for histogram-based representations, ie, the histograms of the same category may …

Texture characterization is a key problem in image understanding and pattern recognition. In
this paper, we present a flexible shape-based texture representation using shape co …

In this paper, we address seabed characterization and recognition in sonar images using
keypoint-based approaches. Keypoint-based texture recognition has recently emerged as a …

The autocorrelation is often used in signal processing as a tool for finding repeating patterns
in a signal. In image processing, there are various image analysis techniques that use the …

Color and Texture are two important aspects of natural images. It is widely recognized that
they provide strong complementary cues to each other in a lot of computer vision …