Ruan Qiuqi

  • Citations Per Year
Learn More
This paper proposes a method to extract facial features using improved deformable templates. Our method include two steps, first locating features using rectangle templates designed by myself; then, extracting features using deformable templates. In the first step, we get rectangle block including facial feature from facial images, the rectangle block is(More)
The Bag of Words (BOW) method with spatio-temporal interest points has achieved great performance in human action recognition. However the traditional BOW methods based on vector quantization (VQ) suffer serious quantization error and lose masses of information. There are two main reasons leading these: the first is the codebook obtained by k-means has no(More)
In this paper, we focus on the hand tacking with a combinatorial restrained optical flow algorithm instead of the feature point. The movement region of hand is segmented and then searched for the target. A new template is used for hand target recognition on the segmented regions for detecting the ROI. Then optical flow is used to initialize step sizes in a(More)
This paper systematically provides information for periodic signal expansion with wavelets on compactly supported interval. Basing on the fruit of generic periodic multi-resolution analysis (PMRA), the paper studies two typical cases, i.e. periodic signals with 1 period and with the finite interval, both of which are the representatives of various periodic(More)
For very low bit-rate video coding, encode the region of interest with higher priority will achieve better decoded image, in this paper, we discuss a simple but robust face tracking technique base on color histogram analysis, this technique can locate the region of interest (face region) in head-shoulder image sequence, moreover, a wavelet based ultra-frame(More)
This paper examines the theory of weighed principal component analysis and linear discriminant analysis. Based on these, the author proposes an improved WPCA plus LDA in face recognition. Experimental results demonstrate that this arithmetic can improve the recognition rate when compared with single-center eclosion function WPCA and PCA
Recently, semi-supervised sparse feature selection, which can exploit the large number unlabeled data and small number labeled data simultaneously, has placed an important role in web image annotation. However, most of the semi-supervised feature selection methods are developed for single-view data, which can not reveal and leverage the correlated and(More)
Recently, two methods called 2D principle component analysis (2DPCA) and 2D linear discriminant analysis (2DLDA) were proposed to overcome the shortcomings in classical PCA and LDA such as time-consuming and singularity. They were used widely in image representation and recognition. A limitation of 2D methods is that, they only reflect the information(More)
  • 1