No abstract

No abstract

No abstract

The fabric weave pattern recognition process is a structure identification process that detects the yarn location as well as the yarn crossing structure in a woven fabric. A new local orientation feature is proposed for fabric structure detection by using high-resolution images. The detection process consists of two main steps. Firstly, the yarn location is detected through a series of image enhancement techniques and an edge-based projection method. Secondly, the yarn float is recognized with a local orientation detection approach based on Radon transform. Three kinds of yarn-dyed cotton fabrics are investigated in this study, including the single yarn, the double yarn, and the twisted yarn fabric. Experimental results and discussions demonstrate that the research method is effective in detecting fabric structure and yarn float even with long hairiness.

This paper presents a novel real-time palmprint recognition system for cooperative user applications. This system is the first one achieving noncontact capturing and recognizing palmprint images under unconstrained scenes. Its novelties can be described in two aspects. The first is a novel design of image capturing device. The hardware can reduce influences of background objects and segment out hand regions efficiently. The second is a process of automatic hand detection and fast palmprint alignment, which aims to obtain normalized palmprint images for subsequent feature extraction. The palmprint recognition algorithm used in the system is based on accurate ordinal palmprint representation. By integrating power of the novel imaging device, the palmprint preprocessing approach and the palmprint recognition engine, the proposed system provides a friendly user interface and achieves a good performance under unconstrained scenes simultaneously.