Jin Guang Sun's research while affiliated with Liaoning Technical University and other places

Publications (6)

Article
A new face image feature extraction and recognition algorithm based on Scale Invariant Feature Transform (SIFT) and Local Linary Patterns (LBP) is proposed in this paper. Firstly, a set of keypoints are extracted from images by using the SIFT algorithm; Secondly, each keypoint is described by LBP patterns; Finally, a combination of the global and l...
Article
In this paper it proposes a meaningful digital watermarking algorithm for remote sensing image based on DFT and watermarking segmentation. At First, it normalizes the host remote sensing image and determines an invariant centroid, then selects a square area around the invariant centroid for watermark embedding. Next, it generates a pseudo-random se...
Article
This paper presents a point cloud reconstruction algorithm which based on SVR(support vector regression). Firstly, the point cloud data pre-processing, filter out noise points. Then train the point by SVR, and we can get the function of surface expression. Finally, using the Marching Cube algorithm to visualize the implicit function. Experimental r...
Article
In order to extract characteristics of face by making full use of LBP and improve its "adaptive ability", we proposed an algorithm based on global and local fusion LBP. First, we will extract overall face feature histogram with LBP, then segment the image into blocks, extract each LBP histogram feature, then combine the global and local features ac...
Article
Skin color detection is an important in computer vision.This work presents a new efficient method for skin color detection based on an improved direct least square ellipse fitting in the space CrCbCg. The color distribution statistics of three-dimensional CrCbCg is obtained by fitting the color distribution ellipse boundary in the Cr-Cb, Cr-Cg, Cb-...
Article
Computer simulation of the flame is difficult to achieve real-time and realistic problem, proposing a fire simulation method based on fluid model and GPU general computing combining. The method is based on the incompressible flame, low-density, non-sticky and so on. Semi-Lagrange method is using to solve the fluid equations, using volume rendering...

Citations

... 8 Thus, due to the influence difference of the operations for the colour remote sensing image, these statistical feature-based watermarking methods that focus on the single band are sensitive to image manipulations. 9 Frequency domain-based techniques, such as the commonly used discrete cosine transform (DCT), 10 discrete wavelet transform (DWT), 11 and discrete Fourier transform (DFT), 12 utilize different transforms to embed watermarks in the modified frequency coefficients. However, these methods cannot describe local structures efficiently due to a lack of the phase information 13,14 ; thus, they are vulnerable to geometric manipulations. ...
... Fitting nonlinear models to image data is a common yet challenging task in many image processing applications. Examples include machine perception of surrounding environment by 3-D range data segmentation using planes, cylindrical and spherical object models [1][2][3][4][5][6][7][8][9][10][11], ellipse fitting in various applications (such as gait periodicity detection [12], land-mark localization in neuroimages [13], skin colour [14] and nuclear buds [15] detection, gestational age estimation in ultrasound images [16]) and detection and fitting of nonlinear motion models to a dataset of point matches (that may include erroneous mismatches) in 3-D reconstruction and motion tracking applications [17][18][19][20][21][22][23][24]. ...
... In the daily problems, instead of insufficient information to be dealt with in the previous stage, with the increase of processing time, the information of some images increases progressively, and thus it is necessary to screen the required image information in the background database from the limited amount of information [9]. Then, the number of images filtered in the later stage is large enough, and in comparison with previous images, the basic features of composite images can be found [10]. ...
... Local Binary Patterns (LBP) operator, initially proposed by Ojala et al. (1996), is a powerful tool for texture description and has been widely used in many fields. Sun et al. (2011) extracted an overall face feature histogram with the LBP operator. Then the least squares support vector machine (LS-SVM) was used to identify and train samples of face images in order to improve the recognition rate of the face. ...