New input format

Crop_image_main.py

@@ -7,45 +7,118 @@
 Contain functions to get the bounding box (bbox) from the metadata file
 and crop the fish out of the image from the bbox
 everything is wrap into a main function executable via
-python crop_main.py <image> <metadatafile> <output_crop>
+Crop_image_main.py image metadatafile output_crop
 """
 
-import os
 import sys
 import json
 import numpy as np
+import argparse
 from PIL import Image, ImageFile
-import pandas as pd
-from pathlib import Path
+import matplotlib.pyplot as plt
+
+# Some of the image are truncated and trigger an error the follow line solve the problem
 ImageFile.LOAD_TRUNCATED_IMAGES = True
 
 def get_bbox(metadata_file):
+    '''
+    From metadata.json (drexel_metadata_reformatter.py) extract the fish bounding box.
+    Version extracting from the reformat see (https://github.com/hdr-bgnn/drexel_metadata_formatter)
+
+    Parameters
+    ----------
+    metadata_file : string
+        location/name of the json file containing the metadata to be extracted.
+
+    Returns
+    -------
+    bbox : list
+        list containing the bbox around the fish [left, top, right, bottom].
+
+    '''
 
     f = open(metadata_file)
     data = json.load(f)
-    first_value = list(data.values())[0]
+    bbox = []
 
-    if first_value['has_fish']==True:
-
-        bbox = first_value['fish'][0]['bbox']
-    else: bbox =[]
+    if 'fish' in data:
+        if data['fish']['fish_num']>0:
+             bbox = data['fish']['bbox']
+             
     return bbox
 
+def Crop(image, bbox, increase=0.05):
+    '''
+    Crop the image using the bounding box, expected format [left,top,right,bottom] and adding
+    an increase in size vertically and horizontally.
+    The function will cut off the crop at the boundary of the image if it would otherwise exceed the 
+    image boundary
+
+    Parameters
+    ----------
+    image : PIL image format
+        DESCRIPTION. image imported using PIL.Image.open(image_file)
+    bbox : list
+        DESCRIPTION. list with bbox coordinate format [left,top,right,bottom]
+    increase : float, optional
+        DESCRIPTION. Fractional increase of the bounding box around the fish in each dimension. The default is 0.05 (5%).
+
+    Returns
+    -------
+    im1 : image PIL format
+        DESCRIPTION. Cropped image
+
+    '''
+
+    # 5% increase by default of the bbox, metadata bbox is very tight sometime too tight
+    # increase factor in each direction (width height)
+    factor = increase/2
+    left,top,right,bottom = bbox
+
+    #h_increase = int(abs((right-left)*factor))
+    #v_increase = int(abs((bottom-top)*factor))
+    h_increase = (right-left)*factor
+    v_increase = (bottom-top)*factor    
+    new_bbox = (left-h_increase, top-v_increase, right+h_increase, bottom+v_increase)
+
+    # cutoff the cropping to the original image boundary
+    image_limit = (0,0)+image.size
+    new_bbox_cutoff_1 = map(np.maximum, new_bbox[0:2], (0,0))
+    new_bbox_cutoff_2 = map(np.minimum, new_bbox[2:4], image.size)
+    new_bbox = tuple(new_bbox_cutoff_1) + tuple(new_bbox_cutoff_2)
+
+    im1 = image.crop(new_bbox) # bbox (left,top,right,bottom)
+    return im1
+
 def main(image_file, metadata_file, output_file, increase=0.05):
+    '''
+    Extract the fish bbox from the metadatafile.json and crop the fish and save the result in outputfile
+
+    Parameters
+    ----------
+    image_file : string
+        DESCRIPTION. filename location of the image .jpg
+    metadata_file : string
+        DESCRIPTION. filename location of the metadata file .json
+    output_file : string
+        DESCRIPTION. filename location where to save the cropped image
+    increase : float, optional
+        DESCRIPTION. Fractional increase of the size of the box around the fish in each dimension. The default is 0.05 (5%).
+
+    Returns
+    -------
+    None.
+
+    '''
+
 
     im = Image.open(image_file)
 
     bbox = get_bbox(metadata_file)
 
     if bbox:
-        # 5% increase by default of the bbox, metadata bbox is very tight sometime too tight
-        # increase factor in each direction
-        factor = increase/2
-        left,top,right,bottom = bbox
-        h_increase = int(abs((right-left)*factor))
-        v_increase = int(abs((bottom-top)*factor))
-        new_bbox = (left-h_increase, top-v_increase, right+h_increase, bottom+v_increase)
-        im1 = im.crop(new_bbox) # bbox (left,top,right,bottom)
+        # use the crop function
+        im1 = Crop(im, bbox, increase=increase)
 
     else:
         # if no bounding box detected
@@ -54,6 +127,19 @@ def main(image_file, metadata_file, output_file, increase=0.05):
 
     im1.save(output_file)
 
-if __name__ == '__main__':
+def argument_parser():
+    parser = argparse.ArgumentParser(description='Crop the fish image using bounding bbox from a metadata.json.')
+    parser.add_argument('input_image', help='Path of input original fish image. Format JPG image file.')
+    parser.add_argument('input_metadata', help='Path of input drexel_metadata_reformatted. Format JSON metadata file.')
+    parser.add_argument('output', help='Path of output cropped fish image. Format JPG image file.')
+    parser.add_argument('--increase', type=float, default=0.05, 
+                        help='size increase apply to the bounding box for cropping (in width and height).Default 0.05. Format float.')
+    return parser
+
 
-    main(sys.argv[1],sys.argv[2],sys.argv[3])
+if __name__ == '__main__':
+
+    parser = argument_parser()
+    args = parser.parse_args()
+    main(args.input_image, args.input_metadata, args.output, increase=args.increase)
+

README.md

@@ -1,35 +1,42 @@
 # Crop_image
-Small repository to store the "copping"step of the BGNN Fish project.
+Small repository to store the "cropping"step of the BGNN Fish project.
 
 This repo is linked to main BGNN Fish project rpo [BGNN_Snakemake](https://github.com/hdr-bgnn/BGNN_Snakemake) that encompasses a complete analysis workflow. It contained the code for the "Cropping" part [see here](https://github.com/hdr-bgnn/BGNN_Snakemake/blob/main/Picture_for_Documentation/Workflow_stage_1.png). It is easier to understand the purpose this code and its application if you are familar with BGNN_Snakemake repo.
 
 ## 1 - Short description
 
-  + We use raw fish image [available at Tulane](http://www.tubri.org/HDR/INHS/) and Metadata json file generated by [Drexel_metadata generator] (https://github.com/hdr-bgnn/drexel_metadata) to crop the fish out of a more complexe image.
-  + The metadata json file contained the bounding box of the fish which use to crop the fish [here is an exmaple](https://github.com/hdr-bgnn/Crop_image/blob/main/Test_data/INHS_FISH_000742_cropped.jpg). We increase the size of the bounding box around the fish by 10% increase in case the bounding box (from the metadata) would truncate the edge of the fish. The Cropped image will be used later by a segmentation algorithm such as [trait_segmenation](https://github.com/hdr-bgnn/BGNN-trait-segmentation)
+  + We use raw fish image [available at Tulane](http://www.tubri.org/HDR/INHS/) and Metadata json file generated by [Drexel_metadata](https://github.com/hdr-bgnn/drexel_metadata) and reformatted by [Drexel_metadata_formatter](https://github.com/hdr-bgnn/drexel_metadata_formatter) to crop the fish out of a more complexe image.
 
 **input**
-![original fish image](https://github.com/hdr-bgnn/Crop_image/blob/main/Test_data/INHS_FISH_000742.jpg)
+![original fish image](Test_data/INHS_FISH_000742.jpg)
 
 **Cropped output**
-![Cropped fish image](https://github.com/hdr-bgnn/Crop_image/blob/main/Test_data/INHS_FISH_000742_cropped.jpg)
+![Cropped fish image](Test_data/INHS_FISH_000742_cropped.jpg)
 
 ## 2 - Usage
 
-Input : 
-  + fish image .jpg [see INHS_FISH_000742.jpg](https://github.com/hdr-bgnn/Crop_image/blob/main/Test_data/INHS_FISH_000742.jpg)
-  + Metadata.json [see INHS_FISH_000742.json](https://github.com/hdr-bgnn/Crop_image/blob/main/Test_data/INHS_FISH_000742.json)
+Input example : 
+  + fish image .jpg [see INHS_FISH_000742.jpg](Test_data/INHS_FISH_000742.jpg)
+  + Metadata.json [see INHS_FISH_000742.json](Test_data/INHS_FISH_000742.json)
 
 Ouput :
-  + Cropped image .jpg [see INHS_FISH_000742_cropped.jpg](https://github.com/hdr-bgnn/Crop_image/blob/main/Test_data/INHS_FISH_000742_cropped.jpg)
+  + Cropped image .jpg [see INHS_FISH_000742_cropped.jpg]Test_data/INHS_FISH_000742_cropped.jpg)
 
 Usage in python
 you need the environment define by crop_env.yml. I suggest to use anaconda or miniconda as environment manager
 
 ```
-python Crop_image_main.py INHS_FISH_000742.jpg INHS_FISH_000742.json INHS_FISH_000742_cropped.jpg
+Crop_image_main.py [-h] [--increase] input_image imput_metadata output
 ```
 
+Example using the Test_data with 10% increase in size
+
+```
+Crop_image_main.py INHS_FISH_000742.jpg INHS_FISH_000742.json INHS_FISH_000742_cropped.jpg --increase 0.10
+```
+
+The `--increase` parameter defines the fractional increase of the bounding box from the original metadata size in each direction (10% in this example). The default value in 0.05.
+
 ## 3 - Container and test
 
 The container can be download here:
@@ -50,7 +57,7 @@ The usage can be display like this:
 singularity run crop_image_0.0.2.sif
 ```
 
-To execute the code on the [test data](https://github.com/hdr-bgnn/Crop_image/blob/main/Test_data/), run the following
+To execute the code on the test images [test data](Test_data/), run the following
 
 ```
 singularity exec crop_image_0.0.2.sif Crop_image_main.py Test_data/INHS_FISH_000742.jpg Test_data/INHS_FISH_000742.json Test_data/INHS_FISH_000742_cropped_test.jpg