备战美赛吧 matlab 2013a 照度不均匀校正

百年孤独

Correcting Nonuniform Illumination

This example shows how to correct nonuniform illumination in an image to make it easy to identify individual grains of rice in the image. You can then learn about the characteristics of the grains and easily compute statistics for all the grains in the image.

Step 1: Read Image

1. I = imread('rice.png');
   
2. imshow(I)
   

复制代码

Step 2: Use Morphological Opening to Estimate the Background

Notice that the background illumination is brighter in the center of the image than at the bottom. Use imopen to estimate the background illumination.

1. background = imopen(I,strel('disk',15));
   
2. 
   
3. % Display the Background Approximation as a Surface
   
4. figure, surf(double(background(1:8:end,1:8:end))),zlim([0 255]);
   
5. set(gca,'ydir','reverse');

复制代码

Step 3: Subtract the Background Image from the Original Image

1. I2 = I - background;
   
2. imshow(I2)

复制代码

Note that step 2 and step 3 together could be replaced by a single step using imtophat which first calculates the morphological opening and then subtracts it from the original image.

I2 = imtophat(I,strel('disk',15));

Step 4: Increase the Image Contrast

1. I3 = imadjust(I2);
   
2. imshow(I3);

复制代码

Step 5: Threshold the Image

Create a new binary image by thresholding the adjusted image. Remove background noise with bwareaopen.

1. level = graythresh(I3);
   
2. bw = im2bw(I3,level);
   
3. bw = bwareaopen(bw, 50);
   
4. imshow(bw)

复制代码

Step 6: Identify Objects in the Image

The function bwconncomp finds all the connected components (objects) in the binary image. The accuracy of your results depend on the size of the objects, the connectivity parameter (4,8,or arbitrary), and whether or not any objects are touching (in which case they may be labeled as one object). Some of the rice grains in bw are touching.

1. cc = bwconncomp(bw, 4)
   
2. cc =
   
3. 
   
4.     Connectivity: 4
   
5.        ImageSize: [256 256]
   
6.       NumObjects: 95
   
7.     PixelIdxList: {1x95 cell}

复制代码

Step 7: Examine One Object

Each distinct object is labeled with the same integer value. Show the grain that is the 50th connected component.

1. grain = false(size(bw));
   
2. grain(cc.PixelIdxList{50}) = true;
   
3. imshow(grain);
   

复制代码

Step 8: View All Objects

One way to visualize connected components is to create a label matrix and then display it as a pseudo-color indexed image.

Use labelmatrix to create a label matrix from the output of bwconncomp. Note that labelmatrix stores the label matrix in the smallest numeric class necessary for the number of objects.

1. labeled = labelmatrix(cc);
   
2. whos labeled

复制代码

Name           Size             Bytes  Class    Attributes

  labeled      256x256            65536  uint8              
In the pseudo-color image, the label identifying each object in the label matrix maps to a different color in the associated colormap matrix. Use label2rgb to choose the colormap, the background color, and how objects in the label matrix map to colors in the colormap.

2. RGB_label = label2rgb(labeled, @spring, 'c', 'shuffle');
   
3. imshow(RGB_label)

RGB_label = label2rgb(labeled, @spring, 'c', 'shuffle');<br /> imshow(RGB_label)

Step 9: Compute Area of Each Object

Each rice grain is one connected component in the cc structure. Use regionprops on cc to get the area.

1. graindata = regionprops(cc,'basic')

复制代码

graindata =

95x1 struct array with fields:

    Area
    Centroid
    BoundingBox

To find the area of the 50th component, use dot notation to access the Area field in the 50th element of graindata structure array.

1. graindata(50).Area

复制代码

ans =

   194

Step 10: Compute Area-based Statistics

Create a new vector allgrains, which holds the area measurement for each grain.

1. grain_areas = [graindata.Area];

复制代码

Find the grain with the smallest area.

1. [min_area, idx] = min(grain_areas)
   
2. grain = false(size(bw));
   
3. grain(cc.PixelIdxList{idx}) = true;
   
4. imshow(grain);

复制代码

min_area =

    61


idx =

    16



Step 11: Create Histogram of the Area

1. nbins = 20;
   
2. figure, hist(grain_areas,nbins)
   
3. title('Histogram of Rice Grain Area');

复制代码

百年孤独

Don't be afraid of English