将labelme 生成的.json文件进行可视化的代码+label.png 对比度处理的matlab代码

labelme_to_dataset 指令的代码实现:

show.py文件

#!E:\Anaconda3\python.exe

import argparse
import json
import os
import os.path as osp import PIL.Image
import yaml from labelme import utils def main():
parser = argparse.ArgumentParser()
parser.add_argument('json_file')
args = parser.parse_args() json_file = args.json_file out_dir = osp.basename(json_file).replace('.', '_')
out_dir = osp.join(osp.dirname(json_file), out_dir)
os.mkdir(out_dir) data = json.load(open(json_file)) img = utils.img_b64_to_array(data['imageData'])
lbl, lbl_names = utils.labelme_shapes_to_label(img.shape, data['shapes']) lbl_viz = utils.draw_label(lbl, img, lbl_names) PIL.Image.fromarray(img).save(osp.join(out_dir, 'img.png'))
PIL.Image.fromarray(lbl).save(osp.join(out_dir, 'label.png'))
PIL.Image.fromarray(lbl_viz).save(osp.join(out_dir, 'label_viz.png')) info = dict(label_names=lbl_names) with open(osp.join(out_dir, 'info.yaml'), 'w') as f:
yaml.safe_dump(info, f, default_flow_style=False) print('wrote data to %s' % out_dir) if __name__ == '__main__':
main() 调整label.png对比度matlab代码
clc;
close all;
clear all; src_img = imread('C:\\Users\\Fourmi\\Desktop\\5_json\\label.png'); figure (1)
subplot(321),imshow(src_img),title('原图像');%显示原始图像
subplot(322),imhist(src_img),title('原图像直方图');%显示原始图像直方图 matlab_eq=histeq(src_img); %利用matlab的函数直方图均衡化
subplot(323),imshow(matlab_eq),title('matlab直方图均衡化原图像');%显示原始图像
subplot(324),imhist(matlab_eq),title('matlab均衡化后的直方图');%显示原始图像直方图 dst_img=myHE(src_img); %利用自己写的函数直方图均衡化
subplot(325),imshow(dst_img),title('手写均衡化效果');%显示原始图像
imwrite(dst_img,'C:\Users\Fourmi\Desktop\result5.png')
subplot(326),imhist(dst_img),title('手写均衡化直方图');%显示原始图像直方图

myHe.m 文件

function dst_img=myHE(src_img)  

[height,width] = size(src_img);
dst_img=uint8(zeros(height,width));
%进行像素灰度统计;
NumPixel = zeros(1,256);%统计各灰度数目,共256个灰度级
for i = 1:height
for j = 1: width
NumPixel(src_img(i,j) + 1) = NumPixel(src_img(i,j) + 1) + 1;%对应灰度值像素点数量增加一
end
end
%计算灰度分布密度
ProbPixel = zeros(1,256);
for i = 1:256
ProbPixel(i) = NumPixel(i) / (height * width * 1.0);
end
%计算累计直方图分布
CumuPixel = zeros(1,256);
for i = 1:256
if i == 1
CumuPixel(i) = ProbPixel(i);
else
CumuPixel(i) = CumuPixel(i - 1) + ProbPixel(i);
end
end % 指定范围进行均衡化
% pixel_max=max(max(I));
% pixel_min=min(min(I));
pixel_max=255;
pixel_min=0;
%对灰度值进行映射(均衡化)
for i = 1:height
for j = 1: width
dst_img(i,j) = CumuPixel(src_img(i,j)+1)*(pixel_max-pixel_min)+pixel_min;
end
end
return;

上一篇:ubuntu用su切换,输入密码提示认证失败解决办法


下一篇:Python生成pyc文件