Are you Xinyu Wang?

Claim your profile

Publications (5)0 Total impact

  • Xinyu Wang, Huosheng Xu, Heng Wang
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a robust method of sketch recognition for course of action (COA) diagrams. User input is through free-hand sketching. COA symbols are recognized incrementally and the informal sketching input is replaced with formal vector graphs or images of the symbols. Multi-stroke COA symbols are divided into temporally continuous uni-stroke shapes. Firstly, it removes over-crossed end part of the uni-stroke shapes. Then, it extracts invariant geometric features of convex hull, largest-area inscribed and smallest-area enclosing polygons, perimeter and area ratios, and distinctive features of the concave and the open ended. Thirdly, the uni-stroke shapes are recognized by support vector machines (SVM). Fourthly, an intermediate feature recognizer is used to recognize shapes of intermediate complexity such as a dashed line, which improves sketch recognition performance in the COA domain. Finally, the system uses the LADDER shape definition language to represent the geometric properties of shapes, and is capable of recognizing common COA symbols of multi-stroke sketches and gesture commands with a recognition accuracy of more than 98%.
    01/2010;
  • Source
    Xinyu Wang, Huosheng Xu, Xi Chen, Heng Li
    [Show abstract] [Hide abstract]
    ABSTRACT: We present a new approach to face detection with skin color mixture models and asymmetric AdaBoost. First, non-skin color pixels of the input image are rapidly removed based on skin color mixture models in RGB and YCbCr chrominance spaces, from which we extract candidate face regions. Then, face detection with fast asymmetric AdaBoost is carried out in candidate face regions where ratios of pixels of skin color to non-skin color are beyond certain thresholds. To further reduce the computational cost, the integral image technique is employed to calculate ratios of pixels of skin color to non-skin color in candidate face regions. Finally, false alarms are gradually merged and removed by relative geometric relation and the rate of skin color pixels on the intersection line of candidate face regions. Experimental results show that our proposed method reduces significantly false alarms and the processing time while achieves detection rates of more than 99%.
    Proc SPIE 10/2009;
  • [Show abstract] [Hide abstract]
    ABSTRACT: The small target detection in infrared image sequences is a fundamental step in the process of infrared search and tracking systems. This paper proposes a fast and adaptive method for infrared small target detection using gray-scale morphology and backward cumulative histogram analysis of the image. The proposed algorithm consists of five phases. Firstly, the perceptually insignificant large image background regions are removed using gray-scale morphology processing. Then, we generate backward cumulative histogram of the image after background elimination. To smooth noisy data, the backward cumulative histogram profile is fitted by a low order polynomial. Thirdly, the lower limit of the threshold that best extracts small targets is obtained based on dynamic analysis of the derivative curve of fitted low-order polynomial. Fourthly, optimal threshold is selected based on reasonable range of the threshold and constant false alarm rate. Finally, false targets are further removed by modified multi-frame data association. Experimental results show that our proposed method obtains very high detection rate and extremely low false alarm rate.
    Information and Automation, 2009. ICIA '09. International Conference on; 07/2009
  • Xinyu Wang, Huosheng Xu, Heng Wang, Heng Li
    [Show abstract] [Hide abstract]
    ABSTRACT: We present the combination of an illumination invariant approach to face detection with skin color detection and the false positive suppression used for improving speed and accuracy of the system. First, the non-skin color pixels of the input image are removed based on the mixed skin color model in the YCbCr and RGB chrominance spaces, from which we extract candidate human face regions. Then, face detection with the modified census transform is carried out in the candidate skin color regions where ratio of pixels of skin colour to non-skin color in the sub-windows is above a threshold. To further reduce the computational cost, ratios of pixels of skin color to non-skin color are computed by use of the integral image. Finally, false detection regions are eliminated by using knowledge-based merging and deleting process of homogeneous skin color regions. A face detection system that integrates the skin color detection and false positive suppression method under the proposed framework is built and tested on the Bao image database and two real videos. Experimental results show that our proposed method reduces significantly the false alarms and the processing time while achieves detection rates of more than 99%.
    Information and Automation, 2008. ICIA 2008. International Conference on; 07/2008
  • Xinyu Wang, Huosheng Xu, Heng Wang
    [Show abstract] [Hide abstract]
    ABSTRACT: The infrared ship segmentation in digital images is a fundamental step in the process of ship recognition. This paper presents an adaptive recursive algorithm for infrared ship image segmentation based on the gray-level histogram analysis of the image. The proposed algorithm consists of four phases. First, the gray-level histogram of the image is generated and de-noised by using wavelets transform. Second, a threshold level which best extracts the ship from the water region is selected according to the histogram profile analysis. Third, the rationality of the selected threshold is analyzed based on the prior information about infrared ship images. If the selected threshold is not reasonable, we can still use it as the recursive initial threshold and the infrared ship image will be further segmented with a local recursive method based on the method proposed by OTSU until it reaches the prescriptive termination criteria. Finally, we eliminate the spurious pixels by extracting the greatest connected region and filling the holes. The segmentation algorithm works successfully for classification of infrared ships, and some experimental results are also presented.
    Proc SPIE 11/2007;