Local features are widely utilized in a large number of applications, eg, object
categorization, image retrieval, robust matching, and robot localization. In this review, we …

The use of the deep learning approach in the textile industry for the purpose of defect
detection has become an increasing trend in the past 20 years. The majority of publications …

Research in texture recognition often concentrates on the problem of material recognition in
uncluttered conditions, an assumption rarely met by applications. In this work we conduct a …

Texture is a fundamental characteristic of many types of images, and texture representation
is one of the essential and challenging problems in computer vision and pattern recognition …

Patterns and textures are key characteristics of many natural objects: a shirt can be striped,
the wings of a butterfly can be veined, and the skin of an animal can be scaly. Aiming at …

In this paper, we propose a very simple deep learning network for image classification that is
based on very basic data processing components: 1) cascaded principal component …

Recognizing materials in real-world images is a challenging task. Real-world materials have
rich surface texture, geometry, lighting conditions, and clutter, which combine to make the …

Fire is one of the most frequent and common emergencies threatening public safety and
social development. Recently, intelligent fire detection technologies represented by …

A wavelet scattering network computes a translation invariant image representation which is
stable to deformations and preserves high-frequency information for classification. It …

Deep learning has established many new state of the art solutions in the last decade in
areas such as object, scene and speech recognition. In particular Convolutional Neural …