Image Region filter how to only get mask for one area?

Very new to image processing, bascially I want to obtain each cell of a table image.

How can I only get the mask of one area in the image region analyzer? I want to use that to crop out one piece of the table image and run ocr on that, is there a better way to do this?

Answer 1

[Kevin Holly]

I would check Exclude Border

If you click the dropdown box under Export>Export Function

function [BW_out,properties] = filterRegions(BW_in)
%filterRegions  Filter BW image using auto-generated code from imageRegionAnalyzer app.
%  [BW_OUT,PROPERTIES] = filterRegions(BW_IN) filters binary image BW_IN
%  using auto-generated code from the imageRegionAnalyzer app. BW_OUT has
%  had all of the options and filtering selections that were specified in
%  imageRegionAnalyzer applied to it. The PROPERTIES structure contains the
%  attributes of BW_out that were visible in the app.

% Auto-generated by imageRegionAnalyzer app on 20-Jan-2022
%---------------------------------------------------------

BW_out = BW_in;

% Remove portions of the image that touch an outside edge.
BW_out = imclearborder(BW_out);

% Get properties.
properties = regionprops(BW_out, {'Area', 'Eccentricity', 'EquivDiameter', 'EulerNumber', 'MajorAxisLength', 'MinorAxisLength', 'Orientation', 'Perimeter'});

% Uncomment the following line to return the properties in a table.
% properties = struct2table(properties);
end

Now under the properities menu, I did not see an option to extract the region's Bounding Box nor Image when using regionprops. So, I am going to do it programmatically below.

I = imread('Capture.png');
grayscale_I = rgb2gray(I);
bw_I = imbinarize(grayscale_I);

imshow(bw_I)

% Remove portions of the image that touch an outside edge.
BW_out = imclearborder(bw_I);

% Get properties.
rp = regionprops(BW_out, {'Area', 'Centroid','BoundingBox','Image'})

rp = 75×1 struct array with fields:
    Area
    Centroid
    BoundingBox
    Image

Cellnumber = 1;

imshow(rp(Cellnumber).Image)

The image above is completely white as this is what the binary image looks like.

Below is an extra step to verfiy the region of interest was select correctly.

% Check to verify region location.

%preallocate
roi_image = zeros(size(BW_out));

% Display region of interest within scale of original image.
BoundingBox_Rows = round(rp(Cellnumber).BoundingBox(2)):round((rp(Cellnumber).BoundingBox(2)+rp(Cellnumber).BoundingBox(4))-1);
BoundingBox_Columns = round(rp(Cellnumber).BoundingBox(1)):round((rp(Cellnumber).BoundingBox(1)+rp(Cellnumber).BoundingBox(3)))-1;
roi_image(BoundingBox_Rows,BoundingBox_Columns) = rp(Cellnumber).Image;

imshow(roi_image)