The paper describes a new stroke extraction approach to identify the feature points of a character, using line-filtering and learning-based techniques. The line-filtering technique based on the convolution operations with a set of 1-D Gabor templates is efficient in extracting the stroke segments of the character and robust in noise tolerance. Furthermore, unlike convectional feature-point dete...

Third generation of mobile communications systems (3G) integrate a wide variety of wireless services as multimedia services. Universal Mobile Telecommunications System (UMTS) is the main standard of 3G with WCDMA air interface. The CDMA provides both error detection and error correction as channel coding scheme. The first one is provided by Cyclic Redundancy Check (CRC) coding and the latter by...

A procedure is described for estimating an optimum kernel for the detection by convolution of signals among Poissonian noise. The technique is applied to the detection of x-ray point sources in XMM-Newton data, and is shown to yield an improvement in detection sensitivity of up to 60% over the sliding-box method used in the creation of the 1XMM catalog.

In this paper, for the first time, a comprehensive experimental study is performed on hydroforming process of metallic bellows. For this purpose, the effects of the main process parameters and their interactions on the characteristics of hydroformed metallic bellows are investigated using Response Surface Methodology (RSM). The selected parameters as input variables are internal pressure, die s...

Feature extraction is a crucial step for many systems of face detection and facial expression recognition. In this paper, we present edge-based feature extraction for recognizing six different expressions, which are angry, fear, happy, neutral, sadness and surprise. Edge detection is performed by using Gabor wavelet and convolution filters. In this paper we propose two convolution kernels that ...

The purpose of detecting trace concentrations of analytes often is hindered by occurring noise in the signal curves of analytical methods. This is also a problem when different arsenic species (organic arsenic species such as arsanilic acid, nitarsone and roxarsone) are to be determined in animal meat by HPLC-UV-HG-AFS, which is the basis of this work. In order to improve the detection power, m...

This paper presents a real-time implementation of an audio analysis algorithm. The selected approach is based on two stages, first a local novelty detection by a convolution kernel detects segments, and a distance measurement on statistical data gathered from the segments in the first stage describes the inter-segment similarity.