人脸检测并给出过滤器

Question

FDetect = vision.CascadeObjectDetector;

%// Read the input image

I = imread('face.jpg');

%// Returns Bounding Box values based on number of objects
BB = step(FDetect,I);

figure,
imshow(I); 
hold on
for i = 1:size(BB,1)
   rectangle('Position',BB(i,:),'LineWidth',2.5,'LineStyle','','EdgeColor','r');
end
title('Face Detection');
hold off;

过滤器：

E = imerode(I,strel('square',5));

figure, imshow(E);

我的问题是如何仅在IN矩形面区域中提供滤镜。

Answer 1

您需要仅提取图像中位于边界框内的区域，然后仅对该部分应用imerode操作。

边界框的形式为[x，y，width，height]。我们需要将其转换为像素。

%// Ensure that we are working with integers.
BB(k,:) = round(BB(k,:));

%// Sample all rows and columns within this bounding box
rows = BB(k,2):sum(BB(k,[2 4]))
cols = BB(k,1):sum(BB(k,[1 3]))

%// Apply the imerode operation on just these pixels
I(rows,cols) = imerode(I(rows,cols), strel('square', 5));