• Journal of Applied Optics
  • Vol. 44, Issue 1, 61 (2023)
Xin'gang WANG1, Junwei TIAN1,*, Yalin YU2, Qin WANG1, and Jie ZHANG3
Author Affiliations
  • 1School of Mechatronic Engineering, Xi'an Technological University, Xi'an 710021, China
  • 2School of Opto-electronic Engineering, Xi'an Technological University, Xi'an 710021, China
  • 3Inner Mongolia North Heavy Industries Group Co.,Ltd., Baotou 014030, China
  • show less
    DOI: 10.5768/JAO202344.0102001 Cite this Article
    Xin'gang WANG, Junwei TIAN, Yalin YU, Qin WANG, Jie ZHANG. Edge contour extraction of infrared face image based on improved Canny algorithm[J]. Journal of Applied Optics, 2023, 44(1): 61 Copy Citation Text show less
    Flow chart of edge contour extraction of infrared face image based on improved Canny algorithm
    Fig. 1. Flow chart of edge contour extraction of infrared face image based on improved Canny algorithm
    Schematic of interpolation gradient direction in non-maximum suppression of original Canny algorithm
    Fig. 2. Schematic of interpolation gradient direction in non-maximum suppression of original Canny algorithm
    Schematic of improved interpolation gradient direction in non-maximum suppression
    Fig. 3. Schematic of improved interpolation gradient direction in non-maximum suppression
    Comparison of image filtering processing effect
    Fig. 4. Comparison of image filtering processing effect
    Experimental results of edge contour extraction comparison from partial infrared face images
    Fig. 5. Experimental results of edge contour extraction comparison from partial infrared face images
    Experimental results of edge contour extraction comparison from partial clipping infrared face images
    Fig. 6. Experimental results of edge contour extraction comparison from partial clipping infrared face images
    Comparison of quality coefficients of different edge detection algorithms for uncropped images
    Fig. 7. Comparison of quality coefficients of different edge detection algorithms for uncropped images
    Comparison of quality coefficients of different edge detection algorithms for clipping images
    Fig. 8. Comparison of quality coefficients of different edge detection algorithms for clipping images
    步骤操作
    Step1高斯滤波器平滑图像滤除噪声
    Step2计算梯度强度和方向
    Step3非极大值抑制消除杂散响应
    Step4双阈值检测确定真实和潜在边缘
    Step5抑制孤立弱边缘完成边缘检测
    Table 1. Edge detection process by Canny algorithm
    算法图像高斯滤波中值滤波双边滤波引导滤波改进的引导滤波
    红外图像118.223220.568421.317622.025924.2705
    剪裁图像120.568423.315825.631527.016031.0563
    红外图像219.031221.165723.028724.963827.8652
    剪裁图像221.235725.064226.916328.215733.1066
    Lena图像24.130632.382335.568636.625240.1549
    Table 2. PSNR comparison of test image filtering results dB
    算法图像高斯滤波中值滤波双边滤波引导滤波改进的引导滤波
    红外图像156.8958.3760.5263.8669.01
    剪裁图像160.3661.9363.0465.2373.15
    红外图像258.6259.3861.0765.0471.52
    剪裁图像262.0764.5965.7668.3175.23
    Lena图像68.0268.9471.2375.3581.87
    Table 3. SSIM comparison of test image filtering results %
    Xin'gang WANG, Junwei TIAN, Yalin YU, Qin WANG, Jie ZHANG. Edge contour extraction of infrared face image based on improved Canny algorithm[J]. Journal of Applied Optics, 2023, 44(1): 61
    Download Citation