The authors proposed the texture unit-based texture spectrum approach in 1990, which has been used for texture analysis, including texture characterization, texture classification, texture edge detection, and textural filtering. One of the most important disadvantages related to this method is the large number of texture units (6,561) and its redundancy. This paper aims at simplifying the origi...

Texture is one of the fundamental image characteristics useful in computer vision tasks such as object recognition and scene analysis. Texture segmentation is one of the image analysis tasks. The prospect of texture segmentation depends on the choice of the texture description method and the segmentation procedure. In this paper, color-texture descriptors are proposed to represent the texture c...

Procedural textures usually require spending time testing parameters to realize the diversity of appearances. This paper introduces the idea of a procedural texture preview: A single static image summarizing in a limited pixel space the appearances produced by a given procedure. Unlike grids of thumbnails our previews present a continuous image of appearances, analog to a map. The main challeng...

Level-of-detail modeling is a vital representation for real-time applications. To support texture mapping progressive meshes (PM), we usually allow the whole PM sequence to share a common texture map. Although such a common texture map can be derived by using appropriate mesh parameterizations that consider the minimization of geometry stretch, texture stretch, or even the texture deviation int...

It is a unique approach for steganography using a reversible texture synthesis where rather than using existing image the algorithm will create new texture image using source texture and embeds message by texture synthesis process. The new image with similar appearance can be re-created by using texture synthesis process. The size of new image can be user specified. The important concept behind...

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively expensive, laborious and error-prone. Furthermore, academic corpora like Fisher English (2004) or Switchboard (1992) are inadequate to train models with suf...