How to recognize negative numbers with OCR?

12 visualizaciones (últimos 30 días)
sasad games
sasad games el 27 de Feb. de 2021
Comentada: sasad games el 27 de Feb. de 2021
I am using the following code to recognize numbers in images and transform it to values. However, it only recognizes positive values. Can you please help me to modify the code in order to be able to identify positive and negative values? Thanks in advance.
clc
clear all
close all
%%
I=imread('N1.png');
I2=I(:,:,3);
I3=ind2rgb(I2,gray);
I4=imcomplement(I3);
N=Im_text(I4);
function [val] = Im_text(Original)
% Increase image size by 3x
my_image = imresize(Original, 3);
% Localize words
BW = imbinarize(rgb2gray(my_image));
BW1 = imdilate(BW,strel('disk',6));
s = regionprops(BW1,'BoundingBox');
bboxes = vertcat(s(:).BoundingBox);
% Sort boxes by image height
[~,ord] = sort(bboxes(:,2));
bboxes = bboxes(ord,:);
% Pre-process image to make letters thicker
BW = imdilate(BW,strel('disk',1));
% Call OCR and pass in location of words. Also, set TextLayout to 'word'
ocrResults = ocr(BW,bboxes,'CharacterSet','.0123456789','TextLayout','word');
words = {ocrResults(:).Text}';
words = deblank(words);
val=str2double(words);
end

Respuesta aceptada

Image Analyst
Image Analyst el 27 de Feb. de 2021
Editada: Image Analyst el 27 de Feb. de 2021
Can't you simply add a - to the CharacterSet? Then if the first character is a -, it's a negative number.
This works fine:
grayImage = imread('N1.png');
if ndims(grayImage) == 3
grayImage = rgb2gray(grayImage);
end
imshow(grayImage, 'InitialMagnification', 400);
axis('on', 'image');
N = Im_text(grayImage)
caption = sprintf('The number in here is %f', N);
title(caption, 'FontSize', 20);
%==================================================================================
function [val] = Im_text(Original)
% Increase image size by 3x
my_image = imresize(Original, 3);
ocrResults = ocr(my_image, 'CharacterSet', '-.0123456789', 'TextLayout', 'line')
words = {ocrResults(:).Text}';
words = deblank(words);
val = str2double(words);
end

Más respuestas (0)

Categorías

Más información sobre Computer Vision Toolbox en Help Center y File Exchange.

Etiquetas

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by