Is there a way to make the word in the image clearer?
조회 수: 5 (최근 30일)
이전 댓글 표시
w = 20;
h = 20;
blankImage= 255*ones(w,h,3,'uint8');
position_x = (w+1)/2;
position_y = (h+1)/2;
font_start = 10;
font_end = 16;
num_fontsA = font_start:2:font_end;
numImagesA = length(num_fontsA)
A = cell(1, numImagesA);
for i=1:numImagesA
for font_size = num_fontsA(i)
img= insertText(blankImage,[position_x position_y],'A','Font','Times New Roman','FontSize',font_size,'TextColor','black','BoxColor','w','BoxOpacity',0,'AnchorPoint','Center');
img= rgb2gray(img);
A{i} = img;
subplot(2,2,i);
imshow(A{i});
axis on;
title("A with font size " + font_size);
end
end
I get this "A" with different font size, but it seems a little blur from the edge since I need to OCR on it later on after applying different standard deviation of normal noise.Did I need to make the word clearer first before doing next step? My next step is separate the A with the background ,then need to identify which pixel belongs to A or background which I will ask in another post.Thank you.
댓글 수: 0
채택된 답변
Image Analyst
2021년 5월 9일
편집: Image Analyst
2021년 5월 9일
Simply use images with more resolution - more elements. A 20x20 image is too small to get good resolution of a binary image made from lines.
% Demo by Image Analyst.
clc; % Clear command window.
clear; % Delete all variables.
close all; % Close all figure windows except those created by imtool.
workspace; % Make sure the workspace panel is showing.
w = 200;
h = 200;
blankImage= 255*ones(w,h,3,'uint8');
position_x = (w+1)/2;
position_y = (h+1)/2;
font_start = 50;
font_end = 200;
num_fontsA = round(linspace(font_start, font_end, 4))
numImagesA = length(num_fontsA)
A = cell(1, numImagesA);
for i=1:numImagesA
for font_size = num_fontsA(i)
img= insertText(blankImage,[position_x position_y],'A','Font','Times New Roman','FontSize',font_size,'TextColor','black','BoxColor','w','BoxOpacity',0,'AnchorPoint','Center');
img= rgb2gray(img);
A{i} = img;
subplot(2,2,i);
imshow(A{i});
axis on;
title("A with font size " + font_size);
end
end
추가 답변 (0개)
참고 항목
카테고리
Help Center 및 File Exchange에서 Computer Vision Toolbox에 대해 자세히 알아보기
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!