### Uninstall and reinstall boxdetect

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-autoconfig.ipynb

This code snippet first uninstalls the boxdetect library and then reinstalls it. This is often done to ensure a clean installation or to get the latest version.

```python
import sys
! {sys.executable} -m pip uninstall boxdetect -y
```

--------------------------------

### Configure pipelines

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-pipelines.ipynb

Sets up the configuration for the box detection pipelines, including width, height, scaling factors, and aspect ratio ranges.

```python
from boxdetect import config

cfg = config.PipelinesConfig()

# important to adjust these values to match the size of boxes on your image
cfg.width_range = (30, 50)
cfg.height_range = (30, 35)

# the more scaling factors the more accurate the results but also it takes more time to processing
# too small scaling factor may cause false positives
# too big scaling factor will take a lot of processing time
cfg.scaling_factors = [1.0]

# w/h ratio range for boxes/rectangles filtering
cfg.wh_ratio_range = (0.5, 1.8)

# range of groups sizes to be returned
cfg.group_size_range = (1, 100)

# for this image we will use rectangles as a kernel for morphological transformations
cfg.morph_kernels_type = 'rectangles'  # 'lines'

# num of iterations when running dilation tranformation (to engance the image)
cfg.dilation_iterations = 0
```

--------------------------------

### Get boxes using the pipeline

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-pipelines.ipynb

Uses the `get_boxes` pipeline to detect rectangular boxes and group them.

```python
from boxdetect.pipelines import get_boxes

rects, grouping_rects, image, output_image = get_boxes(
    file_path, cfg=cfg, plot=False)
```

--------------------------------

### Load image and display

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-pipelines.ipynb

Loads an image using OpenCV and displays it using Matplotlib.

```python
import cv2
import matplotlib.pyplot as plt
%matplotlib inline

file_path = '../images/form_example1.png'

input_image = cv2.imread(file_path)
plt.figure(figsize=(15, 15))
plt.axis('off')
plt.imshow(input_image)
plt.show()
```

--------------------------------

### Initialize PipelinesConfig and autoconfigure from VoTT

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-autoconfig.ipynb

This code snippet initializes the PipelinesConfig object and configures it by reading annotations from a specified VoTT directory. It targets annotations with the class tag 'box'.

```python
from boxdetect import config

cfg = config.PipelinesConfig()

cfg.autoconfigure_from_vott(
    vott_dir="../tests/data/autoconfig_simple", class_tags=["box"])
```

--------------------------------

### Load image and display it

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-autoconfig.ipynb

This code snippet loads an image using OpenCV and displays it using Matplotlib. It sets up the plot to be a specific size and turns off the axes for a cleaner display.

```python
import cv2
import matplotlib.pyplot as plt
%matplotlib inline

file_path = '../tests/data/autoconfig_simple/dummy_example.png'

input_image = cv2.imread(file_path)
plt.figure(figsize=(15, 15))
plt.axis('off')
plt.imshow(input_image)
plt.show()
```

--------------------------------

### Autoconfigure pipelines with specific box sizes

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-autoconfig.ipynb

This code snippet demonstrates how to use the `autoconfigure` method from `boxdetect.config` to set up the configuration for detecting checkboxes. It takes a list of tuples, where each tuple represents the height and width of the checkboxes to search for.

```python
from boxdetect import config

cfg = config.PipelinesConfig()

# The values I'm providing below is a list of box sizes I'm interested in and want to focus on
# [(h, w), (h, w), ...]
cfg.autoconfigure([(46, 46), (44, 43)])
```

--------------------------------

### Get checkboxes using the configured pipeline

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-autoconfig.ipynb

This code snippet uses the `get_checkboxes` function from the `boxdetect.pipelines` module to detect checkboxes in a given file path, using the previously configured `cfg` object. It includes parameters for pixel threshold, plotting, and verbosity.

```python
from boxdetect.pipelines import get_checkboxes

checkboxes = get_checkboxes(
    file_path, cfg=cfg, px_threshold=0.1, plot=False, verbose=True)
```

--------------------------------

### Install BoxDetect from GitHub

Source: https://github.com/karolzak/boxdetect/blob/master/README.md

Installs the BoxDetect package directly from its GitHub repository.

```bash
pip install git+https://github.com/karolzak/boxdetect
```

--------------------------------

### Process image and get checkboxes with adjusted config

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-pipelines.ipynb

This code snippet uses the `get_checkboxes` function with the previously adjusted configuration and a `px_threshold` to detect checkboxes and determine if they are checked.

```python
from boxdetect.pipelines import get_checkboxes

# px_threshold set to 0.1 is basically saying that every checkbox
# with more than 10% of white pixels inside should be considered as checked
checkboxes = get_checkboxes(
    file_path, cfg=cfg, px_threshold=0.1, plot=False, verbose=True)

```

--------------------------------

### Get checkboxes using the get_checkboxes pipeline

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-autoconfig.ipynb

This code snippet uses the `get_checkboxes` pipeline from `boxdetect.pipelines` to detect checkboxes in an image based on the provided configuration (`cfg`). The `plot=False` argument indicates that the results should not be plotted directly.

```python
from boxdetect.pipelines import get_checkboxes

checkboxes = get_checkboxes(file_path, cfg=cfg, plot=False)
```

--------------------------------

### Install BoxDetect from PyPI

Source: https://github.com/karolzak/boxdetect/blob/master/README.md

Installs the BoxDetect package from the Python Package Index (PyPI).

```bash
pip install boxdetect
```

--------------------------------

### Adjust configuration for a new image

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-pipelines.ipynb

This code demonstrates how to adjust the `PipelinesConfig` parameters such as `width_range`, `height_range`, `scaling_factors`, and `wh_ratio_range` to optimize checkbox detection for a specific image.

```python
from boxdetect import config

cfg = config.PipelinesConfig()

# important to adjust these values to match the size of boxes on your image
cfg.width_range = (40,60)
cfg.height_range = (40,60)

# the more scaling factors the more accurate the results but also it takes more time to processing
# too small scaling factor may cause false positives
# too big scaling factor will take a lot of processing time
cfg.scaling_factors = [0.5]

# w/h ratio range for boxes/rectangles filtering
cfg.wh_ratio_range = (0.5, 1.5)

# num of iterations when running dilation tranformation (to engance the image)
cfg.dilation_iterations = 0

```

--------------------------------

### Display individual grouped boxes

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-pipelines.ipynb

Iterates through the grouped boxes and displays each cropped box individually.

```python
import cv2

org_img = cv2.imread(file_path)

for rect in grouping_rects:
    x1 = rect[0]
    x2 = x1 + rect[2]
    y1 = rect[1]
    y2 = y1 + rect[3]
    plt.figure(figsize=(10,1))
    plt.imshow(org_img[y1:y2, x1:x2])
    plt.show()
```

--------------------------------

### Display image with detected boxes

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-pipelines.ipynb

Draws the detected boxes (green) and grouped boxes (red) on the image and displays it.

```python
from boxdetect.img_proc import draw_rects, get_image
import matplotlib.pyplot as plt
%matplotlib inline

out_img = draw_rects(get_image(file_path), rects, thickness=3)

plt.figure(figsize=(15,20))
plt.imshow(out_img)
plt.show()
```

--------------------------------

### Display image with detected boxes

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-autoconfig.ipynb

This code snippet draws rectangles around the detected checkboxes on the original image and then displays the resulting image using Matplotlib.

```python
from boxdetect.img_proc import draw_rects, get_image
import matplotlib.pyplot as plt
%matplotlib inline

out_img = draw_rects(get_image(file_path), checkboxes[:,0], thickness=3)

plt.figure(figsize=(15,20))
plt.imshow(out_img)
plt.show()
```

--------------------------------

### Load autoreload extension and set up path

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-autoconfig.ipynb

This code snippet loads the autoreload extension for Jupyter notebooks, which automatically reloads modules before executing code. It also appends the parent directory to sys.path to allow importing local modules.

```python
%load_ext autoreload
%autoreload 2

import sys
sys.path.append("../.")
```

--------------------------------

### Load and display an image for checkbox detection

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-pipelines.ipynb

This code snippet loads an image using OpenCV and displays it using Matplotlib, preparing for subsequent checkbox detection.

```python
import cv2
import matplotlib.pyplot as plt
%matplotlib inline

file_path = '../tests/data/dummy_example2.png'

input_image = cv2.imread(file_path)
plt.figure(figsize=(7, 7))
plt.axis('off')
plt.imshow(input_image)
plt.show()

```

--------------------------------

### Print checkbox details and display crops

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-autoconfig.ipynb

This code snippet iterates through the detected checkboxes, printing their bounding rectangle coordinates, the result of the `contains_pixels` check, and displaying a cropped image of each checkbox.

```python
print("Output object type: ", type(checkboxes))
for checkbox in checkboxes:
    print("Checkbox bounding rectangle (x,y,width,height): ", checkbox[0])
    print("Result of `contains_pixels` for the checkbox: ", checkbox[1])
    print("Display the cropout of checkbox:")
    plt.figure(figsize=(1,1))
    plt.imshow(checkbox[2])
    plt.show()
```

--------------------------------

### Detect checkboxes and recognize if marked

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-pipelines.ipynb

This code snippet shows how to use the `get_checkboxes` function to process an image and identify checkboxes, determining if they are checked based on pixel density.

```python
from boxdetect.pipelines import get_checkboxes

file_path = '../images/form_example1.png'

checkboxes = get_checkboxes(
    file_path, cfg=cfg, px_threshold=0.1, plot=False, verbose=True)

```

--------------------------------

### Inspect the results of checkbox detection

Source: https://github.com/karolzak/boxdetect/blob/master/notebooks/get-started-pipelines.ipynb

This code iterates through the detected checkboxes, printing their bounding box coordinates, whether they contain pixels (indicating they are checked), and displaying a cropout of each checkbox.

```python
print("Output object type: ", type(checkboxes))
for checkbox in checkboxes:
    print("Checkbox bounding rectangle (x,y,width,height): ", checkbox[0])
    print("Result of `contains_pixels` for the checkbox: ", checkbox[1])
    print("Display the cropout of checkbox:")
    plt.figure(figsize=(1,1))
    plt.imshow(checkbox[2])
    plt.show()

```

--------------------------------

### Using `boxdetect.pipelines.get_checkboxes` to retrieve and recognize just the checkboxes

Source: https://github.com/karolzak/boxdetect/blob/master/README.md

This code example shows how to use the `get_checkboxes` function to retrieve and recognize only checkboxes from an image. It assumes the config is already adjusted and demonstrates setting `px_threshold` and `verbose` parameters.

```python
from boxdetect.pipelines import get_checkboxes

checkboxes = get_checkboxes(
    file_path, cfg=cfg, px_threshold=0.1, plot=False, verbose=True)
```

```python
print("Output object type: ", type(checkboxes))
for checkbox in checkboxes:
    print("Checkbox bounding rectangle (x,y,width,height): ", checkbox[0])
    print("Result of `contains_pixels` for the checkbox: ", checkbox[1])
    print("Display the cropout of checkbox:")
    plt.figure(figsize=(1,1))
    plt.imshow(checkbox[2])
    plt.show()
```

--------------------------------

### Saving and loading configuration to/from YAML

Source: https://github.com/karolzak/boxdetect/blob/master/README.md

Demonstrates how to save a `PipelinesConfig` object to a YAML file and load it back.

```python
from boxdetect import config

cfg = config.PipelinesConfig()
cfg.morph_kernels_thickness = 10
cfg.save_yaml('test_cfg.yaml')

cfg2.load_yaml('test_cfg.yaml')
```

--------------------------------

### Autoconfiguring from VoTT annotations

Source: https://github.com/karolzak/boxdetect/blob/master/README.md

This snippet shows how to use `autoconfigure_from_vott` to set up configuration parameters based on ground truth annotations from VoTT.

```python
from boxdetect import config

cfg = config.PipelinesConfig()

cfg.autoconfigure_from_vott(
    vott_dir="../tests/data/autoconfig_simple", class_tags=["box"])
```

```python
from boxdetect.pipelines import get_checkboxes

checkboxes = get_checkboxes(file_path, cfg=cfg, plot=False)
```

--------------------------------

### Using `boxdetect.config.PipelinesConfig.autoconfigure`

Source: https://github.com/karolzak/boxdetect/blob/master/README.md

This snippet illustrates how to use the `autoconfigure` method of `PipelinesConfig` to automatically set configuration parameters based on a provided list of box sizes.

```python
from boxdetect import config

cfg = config.PipelinesConfig()

# The values I'm providing below is a list of box sizes I'm interested in and want to focus on
# [(h, w), (h, w), ...]
cfg.autoconfigure([(46, 46), (44, 43)])
```

```python
from boxdetect.pipelines import get_checkboxes

checkboxes = get_checkboxes(file_path, cfg=cfg, plot=False)
```

--------------------------------

### Detect character boxes and group them together

Source: https://github.com/karolzak/boxdetect/blob/master/README.md

This snippet shows how to configure and use the `get_boxes` pipeline to detect and group character boxes from an image. It includes setting up `PipelinesConfig` with parameters like `width_range`, `height_range`, `scaling_factors`, `wh_ratio_range`, `group_size_range`, and `dilation_iterations`.

```python
from boxdetect import config

file_name = 'form_example1.png'

cfg = config.PipelinesConfig()

# important to adjust these values to match the size of boxes on your image
cfg.width_range = (30,55)
cfg.height_range = (25,40)

# the more scaling factors the more accurate the results but also it takes more time to processing
# too small scaling factor may cause false positives
# too big scaling factor will take a lot of processing time
cfg.scaling_factors = [0.7]

# w/h ratio range for boxes/rectangles filtering
cfg.wh_ratio_range = (0.5, 1.7)

# group_size_range starting from 2 will skip all the groups
# with a single box detected inside (like checkboxes)
cfg.group_size_range = (2, 100)

# num of iterations when running dilation tranformation (to engance the image)
cfg.dilation_iterations = 0
```

```python
from boxdetect.pipelines import get_boxes

rects, grouping_rects, image, output_image = get_boxes(
    file_name, cfg=cfg, plot=False)
```

```python
print(grouping_rects)

OUT:
# (x, y, w, h)
[(276, 276, 1221, 33),
 (324, 466, 430, 33),
 (384, 884, 442, 33),
 (985, 952, 410, 32),
 (779, 1052, 156, 33),
 (253, 1256, 445, 33)]
```

```python
import matplotlib.pyplot as plt

plt.figure(figsize=(20,20))
plt.imshow(output_image)
plt.show()
```

--------------------------------

### Highlighting just the checkboxes

Source: https://github.com/karolzak/boxdetect/blob/master/README.md

This snippet demonstrates how to modify the `PipelinesConfig` to specifically highlight only checkboxes by adjusting the `group_size_range` parameter.

```python
# limit down the grouping algorithm to just singular boxes (e.g. checkboxes)
cfg.group_size_range = (1, 1)
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.