Auto color correct wrapper

docs/transform_auto_correct_color.md

@@ -0,0 +1,43 @@
+# Automatically detect a color card and color correct in one step
+
+Corrects the color of the input image based on the target color matrix using an affine transformation
+in the RGB space after automatic detection of a color card within the image. A one-step wrapper of
+[plantcv.transform.detect_color_card](transform_detect_color_card.md), [plantcv.transform.std_color_matrix](std_color_matrix.md),
+[plantcv.transform.get_color_matrix](get_color_matrix.md), and [plantcv.transform.affine_color_correction](transform_affine_color_correction.md).
+
+**plantcv.transform.auto_correct_color**(*rgb_img, label=None, \*\*kwargs*)
+
+**returns** corrected_img
+
+- **Parameters**
+    - rgb_img          - Input RGB image data containing a color card.
+    - label            - Optional label parameter, modifies the variable name of observations recorded. (default = `pcv.params.sample_label`)
+    - **kwargs         - Other keyword arguments passed to `cv2.adaptiveThreshold` and `cv2.circle`.
+        - adaptive_method  - Adaptive threhold method. 0 (mean) or 1 (Gaussian) (default = 1).
+        - block_size       - Size of a pixel neighborhood that is used to calculate a threshold value (default = 51). We suggest using 127 if using `adaptive_method=0`.
+        - radius           - Radius of circle to make the color card labeled mask (default = 20).
+        - min_size         - Minimum chip size for filtering objects after edge detection (default = 1000)
+- **Returns**
+    - corrected_img    - Color corrected image
+
+- **Example Use**
+    - Below
+
+```python
+
+from plantcv import plantcv as pcv
+
+rgb_img, imgpath, imgname = pcv.readimage(filename="top_view_plant.png")
+
+corrected_rgb = pcv.transform.auto_correct_color(rgb_img=old_card)
+```
+
+**Debug Image: automatically detected and masked the color card**
+
+![Screenshot](img/documentation_images/correct_color_imgs/auto_correct_color.png)
+
+**Corrected Image:**
+
+![Screenshot](img/documentation_images/transform_affine_color_corr/tobacco_leaves_corrected.jpg)
+
+**Source Code:** [Here](https://github.com/danforthcenter/plantcv/blob/main/plantcv/plantcv/transform/auto_correct_color.py)

docs/updating.md

@@ -1210,6 +1210,11 @@ pages for more details on the input and output variable types.
 * pre v3.0dev1: NA
 * post v3.0dev2: determinant, transformation_matrix = **plantcv.transform.calc_transformation_matrix**(*matrix_m, matrix_b*)
 
+#### plantcv.transform.auto_correct_color
+
+* pre v4.6: NA
+* post v4.6: corrected_img = **plantcv.transform.r**(*rgb_img, label=None, **kwargs*)
+
 #### plantcv.transform.correct_color
 
 * pre v3.0dev1: NA

mkdocs.yml

@@ -175,6 +175,7 @@ nav:
       - 'Transformation Methods':
           - 'Auto-Detect Color Card': transform_detect_color_card.md
           - 'Auto-Detect Color Card (old)': find_color_card.md
+          - 'Auto Correct Color': transform_auto_correct_color.md
           - 'Calibrate Camera': transform_calibrate_camera.md
           - 'Checkerboard Calibration': transform_checkerboard_calibration.md
           - 'Create Color Card Mask': create_color_card_mask.md

plantcv/plantcv/transform/__init__.py

@@ -19,9 +19,10 @@
 from plantcv.plantcv.transform.gamma_correct import gamma_correct
 from plantcv.plantcv.transform.checkerboard_calib import checkerboard_calib, calibrate_camera
 from plantcv.plantcv.transform.merge_images import merge_images
+from plantcv.plantcv.transform.auto_correct_color import auto_correct_color
 
 __all__ = ["get_color_matrix", "get_matrix_m", "calc_transformation_matrix", "apply_transformation_matrix",
            "save_matrix", "load_matrix", "correct_color", "create_color_card_mask", "quick_color_check",
            "find_color_card", "std_color_matrix", "affine_color_correction", "rescale", "nonuniform_illumination", "resize",
            "resize_factor", "warp", "rotate", "warp", "warp_align", "gamma_correct", "detect_color_card", "checkerboard_calib",
-           "calibrate_camera", "merge_images"]
+           "calibrate_camera", "merge_images", "auto_correct_color"]

plantcv/plantcv/transform/auto_correct_color.py

@@ -0,0 +1,40 @@
+# Automatically detect a color card and color correct to standard chip values
+
+from plantcv.plantcv import params
+from plantcv.plantcv.transform.detect_color_card import detect_color_card
+from plantcv.plantcv.transform.color_correction import get_color_matrix, std_color_matrix, affine_color_correction
+
+
+def auto_correct_color(rgb_img, label=None, **kwargs):
+    """Automatically detect a color card.
+    Parameters
+    ----------
+    rgb_img : numpy.ndarray
+        Input RGB image data containing a color card.
+    label : str, optional
+        modifies the variable name of observations recorded (default = pcv.params.sample_label).
+    **kwargs
+        Other keyword arguments passed to cv2.adaptiveThreshold and cv2.circle.
+        Valid keyword arguments:
+        adaptive_method: 0 (mean) or 1 (Gaussian) (default = 1)
+        block_size: int (default = 51)
+        radius: int (default = 20)
+        min_size: int (default = 1000)
+    Returns
+    -------
+    numpy.ndarray
+        Color corrected image
+    """
+    # Set lable to params.sample_label if None
+    if label is None:
+        label = params.sample_label
+
+    # Get keyword arguments and set defaults if not set
+    labeled_mask = detect_color_card(rgb_img=rgb_img, min_size=kwargs.get("min_size", 1000),
+                                     radius=kwargs.get("radius", 20),
+                                     adaptive_method=kwargs.get("adaptive_method", 1),
+                                     block_size=kwargs.get("block_size", 51))
+    _, card_matrix = get_color_matrix(rgb_img=rgb_img, mask=labeled_mask)
+    std_matrix = std_color_matrix(pos=3)
+    return affine_color_correction(rgb_img=rgb_img, source_matrix=card_matrix,
+                                   target_matrix=std_matrix)

tests/plantcv/transform/test_auto_correct_color.py

@@ -0,0 +1,11 @@
+"""Tests for auto_correct_color."""
+import cv2
+import numpy as np
+from plantcv.plantcv.transform import auto_correct_color
+
+def test_auto_correct_color(transform_test_data):
+    """Test for PlantCV."""
+    # Load rgb image
+    rgb_img = cv2.imread(transform_test_data.colorcard_img)
+    corrected_img = auto_correct_color(rgb_img=rgb_img)
+    assert np.shape(corrected_img) == np.shape(rgb_img) and np.sum(corrected_img) != np.sum(rgb_img)