ocrodeg - GitLite

KO | EN

gitlite — search

#javascript #react #ai #go #rust #awesome #kubernetes #awesome-list #vue #pytorch #mcp #ios #openai #open-source

ocrodeg

(★ 165)

document image degradation

파일 탐색기

최종 버전 다운로드 (.zip)

- __init__.py
- degrade.py
- README_10_0.png
- README_11_0.png
- README_12_0.png
- README_13_0.png
- README_14_0.png
- README_15_0.png
- README_16_0.png
- README_17_0.png
- README_17_1.png
- README_18_0.png
- README_19_0.png
- README_20_0.png
- README_21_0.png
- README_22_0.png
- README_23_0.png
- README_25_0.png
- README_25_1.png
- README_26_0.png
- README_26_1.png
- README_27_0.png
- README_28_0.png
- README_28_1.png
- README_29_0.png
- README_2_1.png
- README_30_1.png
- README_31_0.png
- README_31_1.png
- README_33_0.png
- README_34_1.png
- README_36_1.png
- README_38_1.png
- README_39_1.png
- README_4_0.png
- README_5_0.png
- README_6_0.png
- README_7_0.png
- README_8_0.png
- README_9_0.png
- W1P0.png
README.ipynb
README.md
requirements.txt
run-tests
setup.py
test-degrade.ipynb

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/NVlabs/ocrodeg

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd ocrodeg

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

jupyter notebook

브라우저에서 노트북(.ipynb) 파일들을 열람하고 실행할 수 있는 Jupyter 화면을 켭니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# ocrodeg

The `ocrodeg` package is a small Python library implementing document image degradation for data augmentation for handwriting recognition and OCR applications.

The following illustrates the kinds of degradations available from `ocrodeg`.

```python
%pylab inline
```

Populating the interactive namespace from numpy and matplotlib

```python
rc("image", cmap="gray", interpolation="bicubic")
figsize(10, 10)
import scipy.ndimage as ndi
import ocrodeg

image = imread("testdata/W1P0.png")
imshow(image)
```

<matplotlib.image.AxesImage at 0x7fabcc7ab390>

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_2_1.png)

# PAGE ROTATION

This is just for illustration; for large page rotations, you can just use `ndimage`.

```python
for i, angle in enumerate([0, 90, 180, 270]):
    subplot(2, 2, i+1)
    imshow(ndi.rotate(image, angle))
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_5_0.png)

# RANDOM GEOMETRIC TRANSFORMATIONS

`random_transform` generates random transformation parameters that work reasonably well for document image degradation. You can override the ranges used by each of these parameters by keyword arguments.

```python
ocrodeg.random_transform()
```

{'angle': -0.016783842893063807,
     'aniso': 0.805280370671964,
     'scale': 0.9709145529604223,
     'translation': (0.014319657859164045, 0.03676897986267606)}

Here are four samples generated by random transforms.

```python
for i in xrange(4):
    subplot(2, 2, i+1)
    imshow(ocrodeg.transform_image(image, **ocrodeg.random_transform()))
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_10_0.png)

You can use `transform_image` directly with the different parameters to get a feel for the ranges and effects of these parameters.

```python
for i, angle in enumerate([-2, -1, 0, 1]):
    subplot(2, 2, i+1)
    imshow(ocrodeg.transform_image(image, angle=angle*pi/180))
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_12_0.png)

```python
for i, angle in enumerate([-2, -1, 0, 1]):
    subplot(2, 2, i+1)
    imshow(ocrodeg.transform_image(image, angle=angle*pi/180)[1000:1500, 750:1250])
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_13_0.png)

```python
for i, aniso in enumerate([0.5, 1.0, 1.5, 2.0]):
    subplot(2, 2, i+1)
    imshow(ocrodeg.transform_image(image, aniso=aniso))
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_14_0.png)

```python
for i, aniso in enumerate([0.5, 1.0, 1.5, 2.0]):
    subplot(2, 2, i+1)
    imshow(ocrodeg.transform_image(image, aniso=aniso)[1000:1500, 750:1250])
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_15_0.png)

```python
for i, scale in enumerate([0.5, 0.9, 1.0, 2.0]):
    subplot(2, 2, i+1)
    imshow(ocrodeg.transform_image(image, scale=scale))
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_16_0.png)

```python
for i, scale in enumerate([0.5, 0.9, 1.0, 2.0]):
    subplot(2, 2, i+1)
    h, w = image.shape
    imshow(ocrodeg.transform_image(image, scale=scale)[h//2-200:h//2+200, w//3-200:w//3+200])
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_17_0.png)

# RANDOM DISTORTIONS

Pages often also have a small degree of warping. This can be modeled by random distortions. Very small and noisy random distortions also model ink spread, while large 1D random distortions model paper curl.

```python
for i, sigma in enumerate([1.0, 2.0, 5.0, 20.0]):
    subplot(2, 2, i+1)
    noise = ocrodeg.bounded_gaussian_noise(image.shape, sigma, 5.0)
    distorted = ocrodeg.distort_with_noise(image, noise)
    h, w = image.shape
    imshow(distorted[h//2-200:h//2+200, w//3-200:w//3+200])
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_20_0.png)

# RULED SURFACE DISTORTIONS

```python
for i, mag in enumerate([5.0, 20.0, 100.0, 200.0]):
    subplot(2, 2, i+1)
    noise = ocrodeg.noise_distort1d(image.shape, magnitude=mag)
    distorted = ocrodeg.distort_with_noise(image, noise)
    h, w = image.shape
    imshow(distorted[:1500])
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_22_0.png)

# BLUR, THRESHOLDING, NOISE

There are a range of utilities for modeling imaging artifacts: blurring, noise, inkspread.

```python
patch = image[1900:2156, 1000:1256]
imshow(patch)
```

<matplotlib.image.AxesImage at 0x7fabc88c7e10>

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_25_1.png)

```python
for i, s in enumerate([0, 1, 2, 4]):
    subplot(2, 2, i+1)
    blurred = ndi.gaussian_filter(patch, s)
    imshow(blurred)
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_26_0.png)

```python
for i, s in enumerate([0, 1, 2, 4]):
    subplot(2, 2, i+1)
    blurred = ndi.gaussian_filter(patch, s)
    thresholded = 1.0*(blurred>0.5)
    imshow(thresholded)
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_27_0.png)

```python
reload(ocrodeg)
for i, s in enumerate([0.0, 1.0, 2.0, 4.0]):
    subplot(2, 2, i+1)
    blurred = ocrodeg.binary_blur(patch, s)
    imshow(blurred)

```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_28_0.png)

```python
for i, s in enumerate([0.0, 0.1, 0.2, 0.3]):
    subplot(2, 2, i+1)
    blurred = ocrodeg.binary_blur(patch, 2.0, noise=s)
    imshow(blurred)
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_29_0.png)

# MULTISCALE NOISE

```python
reload(ocrodeg)
for i in range(4):
    noisy = ocrodeg.make_multiscale_noise_uniform((512, 512))
    subplot(2, 2, i+1); imshow(noisy, vmin=0, vmax=1)
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_31_0.png)

# RANDOM BLOBS

```python
for i, s in enumerate([2, 5, 10, 20]):
    subplot(2, 2, i+1)
    imshow(ocrodeg.random_blobs(patch.shape, 3e-4, s))
```

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_33_0.png)

```python
reload(ocrodeg)
blotched = ocrodeg.random_blotches(patch, 3e-4, 1e-4)
#blotched = minimum(maximum(patch, ocrodeg.random_blobs(patch.shape, 30, 10)), 1-ocrodeg.random_blobs(patch.shape, 15, 8))
subplot(121); imshow(patch); subplot(122); imshow(blotched)
```

<matplotlib.image.AxesImage at 0x7fabc8a35490>

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_34_1.png)

# FIBROUS NOISE

```python
imshow(ocrodeg.make_fibrous_image((256, 256), 700, 300, 0.01))
```

<matplotlib.image.AxesImage at 0x7fabc8852450>

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_36_1.png)

# FOREGROUND / BACKGROUND SELECTION

```python
subplot(121); imshow(patch); subplot(122); imshow(ocrodeg.printlike_multiscale(patch))
```

<matplotlib.image.AxesImage at 0x7fabc8676d90>

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_38_1.png)

```python
subplot(121); imshow(patch); subplot(122); imshow(ocrodeg.printlike_fibrous(patch))
```

<matplotlib.image.AxesImage at 0x7fabc8d1b250>

![png](https://raw.githubusercontent.com/NVlabs/ocrodeg/master/README_files/README_39_1.png)