An Image Enhancement Method Based on Gamma Correction

The research of the wheel alignment system based on computer vision is a popular field for automobile safety. For realizing the effective and accurate feature recognition for the chessboard calibration target of the system, the enhancement algorithms based on Gamma correction are indicated. According to the research object, identification requires decreasing the pixel values in low grayscale and increasing the pixel values in high grayscale while keeping the pixels values in the middle grayscale. For this purpose, the novel Gamma correction curve is presented to enhance the target image. Experimental result shows that the enhancement method increases the contrast ratio of the chessboard target image which is benefit for feature extraction, points matching and vision measurement. Its effect and reliability meet the requirements of the detecting system for vehicle wheel alignment based on computer vision.

[1]  YU Liang-ying.  Reconstruction of 3-D surface of mirror by processing fringe pattern , 2007 .

[2]  Xiong Xing-long.  Improved Gamma Correction Method in Weakening Illumination , 2006 .

[3]  Sun Hui.  Real FFT based on graphic processing unit for image processing , 2008 .

[4]  Liu Wei-qi.  Principle and realization of laser display technique , 2006 .

[5]  Zhou Xiao-dong,et al.  Small target trace acquisition algorithm for sequence star images with moving background , 2008 .

[6]  Xia Fei.  Laser guiding measurement robot and its geometric error analysis , 2008 .

[7]  Yu Yang.  An image encryption scheme based on sequential CA , 2008 .

[8]  Jian Su,et al.  A Novel Method for Wheel Rim Recognition , 2008, 2008 International Symposium on Electronic Commerce and Security.

[9]  Tang Jian-xun,et al.  Random vibration analysis of mechanically dithered ring laser gyroscope , 2007 .

[10]  Li Guo-fa.  Precision measurement for small size parts based on support vector regression , 2007 .

[11]  Zhou Zhao-feng.  Development of high-speed CCD laser displacement sensor , 2008 .

[12]  Jia Guo-xin.  Preprocessing of color image based on digital camera , 2009 .

[13]  Shi Jin-fei.  A high-precision dimension measurement method based on sequential partial images , 2008 .

[14]  Yao Qing-hua.  Application of wavelet neural network in removing CCD noise of digital images , 2008 .

[15]  Zhang Guangjun.  Image feature extraction in insect kinetic deformation measurement , 2007 .

[16]  Yue Jun-hua.  New technology of ship distortion measurement , 2008 .

[17]  Huang Lian-qing,et al.  Image processing based on integral lifting scheme and its implementation by DSP , 2006 .

[18]  Shen Sheng.  Implementation and improvement of area-based stereo matching algorithm , 2008 .

[19]  He Xiao-yuan.  Optical testing of dynamic characteristic of vibrating wheel micromechanical gyroscope , 2008 .

[20]  Li Wei.  Detection of surface cracks of corn kernel based on morphology , 2007 .

[21]  T. Ueda,et al.  Research on a Novel Sensor for Measuring Force in Arbitrary Direction , 2008, 2008 International Conference on Computer and Electrical Engineering.

[22]  Wang Chun-mei.  Control points' light spot image recognition in light-pen vision coordinate measurement , 2007 .

[23]  Wang Si-wen.  Aircraft recognition based on affine transform , 2009 .

[24]  Zhang Tao.  Signal-to-noise ratio model of laser active imaging system , 2008 .

[25]  Zhao Yuejin.  Motion filtering algorithm for tracking technology based on image stabilization , 2009 .

[26]  Deng Weijie.  Improvement of measuring accuracy of CCD laser autocollimator by changing hardware parameters , 2008 .

[27]  Zhu Wei-le.  Image fusion algorithms using discrete cosine transform , 2006 .

[28]  Wei Zhen-zhong.  Global calibration of multi-vision sensor based on one dimensional target , 2008 .