mypkg1xz

Image kernel.


Keywords
convolutional-neural-networks, python3
License
MIT
Install
pip install mypkg1xz==0.0.1

Documentation

imgkernel

license Documentation Status

An image kernel is a small matrix used to apply effects like the ones you might find in Photoshop or Gimp, such as blurring, sharpening, outlining or embossing. They're also used in machine learning for 'feature extraction', a technique for determining the most important portions of an image.

安装

pip install imgkernel

使用

import imgkernel
import matplotlib.pyplot as plt
%matplotlib inline

def show2imgs(img1, img2, title=None):
    fig = plt.figure(figsize=(10, 5))

    if title is not None:
        fig.suptitle(title)

    plt.subplot(121)
    plt.axis('off')
    plt.imshow(img1)

    plt.subplot(122)
    plt.axis('off')
    plt.imshow(img2)

    plt.show()

imgpath = 'image.jpeg'

1. 鲜明

show2imgs(*imgkernel.identity(imgpath, gray=False, iden=1.6), 'imgkernel.identity()')

2. 模糊

show2imgs(*imgkernel.blur(imgpath, gray=False), 'imgkernel.blur()')

3. 锐利

show2imgs(*imgkernel.sharpen(imgpath, gray=False, inner=1.7,  edge=-0.08), 'imgkernel.sharpen()')

4. 浮雕

show2imgs(*imgkernel.emboss(imgpath, gray=False), 'imgkernel.emboss()')

5. 轮廓线

show2imgs(*imgkernel.outline(imgpath, gray=False, inner=8.9, outer=-1.29), 'imgkernel.outline()')

6. 边沿检测

6.1 上边沿

show2imgs(*imgkernel.sobel(imgpath, gray=False, direction='top', base=0.03), 'imgkernel.sobel(top)')

6.2 下边沿

show2imgs(*imgkernel.sobel(imgpath, gray=False, direction='bottom', base=0.03), 'imgkernel.sobel(bottom)')

6.3 左边沿

show2imgs(*imgkernel.sobel(imgpath, gray=False, direction='left', base=0.03), 'imgkernel.sobel(left)')

6.4 右边沿

show2imgs(*imgkernel.sobel(imgpath, gray=False, direction='right', base=0.03), 'imgkernel.sobel(right)')