42、图像的清晰度计算
自动对焦要求相机根据拍摄环境和场景的变化,通过相机内部的微型驱动马达,自动调节相机镜头和CCD之间的距离,保证像平面正好投影到CCD的成像表面上。这时候物体的成像比较清晰,图像细节信息丰富。相机自动对焦的过程,其实就是对成像清晰度评价的过程。对焦不准确会造成图像模糊,在高精度视觉测量和视觉定位等应用中会带来误差。
工业相机上用的变焦镜头需要人为去调节到最清晰一个状态,以下分别提供方差法、拉普拉斯能量函数法、能量梯度函数法、Brenner函数法的评判来找到最清晰的图像。
主函数
*使用halcon自带的图片
*实现了五种评价函数,
*选择算子的Method值,可以观察不同评价函数的效果。
read_image (Image, 'pcb_focus/pcb_focus_telecentric_106')
dev_update_off ()
dev_close_window ()
dev_open_window_fit_image (Image, 0, 0, 752, 480, WindowHandle)
set_display_font (WindowHandle, 16, 'mono', 'true', 'false')
dev_set_color ('lime green')
dev_set_line_width (3)
Ret:=[]
get_image_size(Image, Width, Height)
for Index := 1 to 121 by 1
read_image (Image, 'pcb_focus/pcb_focus_telecentric_'+Index$'03d')
****自定义的评判函数,返回一个数值来表示这个图像的清晰度,越高表示越清晰
evaluate_definition (Image, 'Brenner', Value)
dev_display (Image)
Ret:=[Ret,Value]
endfor
*使用直方图显示清晰度结果
VMax:=max(Ret)
VMin:=min(Ret)
GRet := 100*(Ret-VMin)/(VMax-VMin)
gen_region_histo(Region, Ret, 255, 255, 1)
*找到峰值对应的那张图,确实是最清晰的那张。
qxd:=find(Ret, max(Ret))
read_image (GoodImage, 'pcb_focus/pcb_focus_telecentric_'+qxd$'03d')
dev_display (GoodImage)
dev_display (Region)
自定义的评判函数
evaluate_definition(Image : : Method : Value)
scale_image_max(Image, Image)
get_image_size(Image, Width, Height)
if(Method = 'Deviation')
*方差法
region_to_mean (Image, Image, ImageMean)
convert_image_type (ImageMean, ImageMean, 'real')
convert_image_type (Image, Image, 'real')
sub_image(Image, ImageMean, ImageSub, 1, 0)
mult_image(ImageSub, ImageSub, ImageResult, 1, 0)
intensity(ImageResult, ImageResult, Value, Deviation)
elseif(Method = 'laplace')
*拉普拉斯能量函数
laplace (Image, ImageLaplace4, 'signed', 3, 'n_4')
laplace (Image, ImageLaplace8, 'signed', 3, 'n_8')
add_image(ImageLaplace4,ImageLaplace4,ImageResult1, 1, 0)
add_image(ImageLaplace4,ImageResult1,ImageResult1, 1, 0)
add_image(ImageLaplace8,ImageResult1,ImageResult1, 1, 0)
mult_image(ImageResult1, ImageResult1, ImageResult, 1, 0)
intensity(ImageResult, ImageResult, Value, Deviation)
elseif(Method = 'energy')
*能量梯度函数
crop_part(Image, ImagePart00, 0, 0, Width-1, Height-1)
crop_part(Image, ImagePart01, 0, 1, Width-1, Height-1)
crop_part(Image, ImagePart10, 1, 0, Width-1, Height-1)
convert_image_type (ImagePart00, ImagePart00, 'real')
convert_image_type (ImagePart10, ImagePart10, 'real')
convert_image_type (ImagePart01, ImagePart01, 'real')
sub_image(ImagePart10, ImagePart00, ImageSub1, 1, 0)
mult_image(ImageSub1, ImageSub1, ImageResult1, 1, 0)
sub_image(ImagePart01, ImagePart00, ImageSub2, 1, 0)
mult_image(ImageSub2, ImageSub2, ImageResult2, 1, 0)
add_image(ImageResult1, ImageResult2, ImageResult, 1, 0)
intensity(ImageResult, ImageResult, Value, Deviation)
elseif(Method = 'Brenner')
*Brenner函数法
crop_part(Image, ImagePart00, 0, 0, Width, Height-2)
convert_image_type (ImagePart00, ImagePart00, 'real')
crop_part(Image, ImagePart20, 2, 0, Width, Height-2)
convert_image_type (ImagePart20, ImagePart20, 'real')
sub_image(ImagePart20, ImagePart00, ImageSub, 1, 0)
mult_image(ImageSub, ImageSub, ImageResult, 1, 0)
intensity(ImageResult, ImageResult, Value, Deviation)
elseif(Method = 'Tenegrad')
*Tenegrad函数法
sobel_amp (Image, EdgeAmplitude, 'sum_sqrt', 3)
min_max_gray(EdgeAmplitude, EdgeAmplitude, 0, Min, Max, Range)
threshold(EdgeAmplitude, Region1, 11.8, 255)
region_to_bin(Region1, BinImage, 1, 0, Width, Height)
mult_image(EdgeAmplitude, BinImage, ImageResult4, 1, 0)
mult_image(ImageResult4, ImageResult4, ImageResult, 1, 0)
intensity(ImageResult, ImageResult, Value, Deviation)
elseif(Method = '2')
elseif(Method = '3')
endif
return ()