How to use plantcv - 10 common examples

def test_plantcv_roi_from_binary_image():
    # Test cache directory
    cache_dir = os.path.join(TEST_TMPDIR, "test_plantcv_roi_from_binary_image")
    os.mkdir(cache_dir)
    # Read in test RGB image
    rgb_img = cv2.imread(os.path.join(TEST_DATA, TEST_INPUT_COLOR))
    # Create a binary image
    bin_img = np.zeros(np.shape(rgb_img)[0:2], dtype=np.uint8)
    cv2.rectangle(bin_img, (100, 100), (1000, 1000), 255, -1)
    # Test with debug = "print"
    pcv.params.debug = "print"
    pcv.params.debug_outdir = cache_dir
    _, _ = pcv.roi.from_binary_image(bin_img=bin_img, img=rgb_img)
    # Test with debug = "plot"
    pcv.params.debug = "plot"
    _, _ = pcv.roi.from_binary_image(bin_img=bin_img, img=rgb_img)
    # Test with debug = None
    pcv.params.debug = None
    roi_contour, roi_hierarchy = pcv.roi.from_binary_image(bin_img=bin_img, img=rgb_img)
    # Assert the contours and hierarchy lists contain only the ROI
    assert np.shape(roi_contour) == (1, 3600, 1, 2)

def main():
  # Get options
  args = options()
  
  # Read image (converting fmax and track to 8 bit just to create a mask, use 16-bit for all the math)
  mask, path, filename = pcv.readimage(args.fmax)
  #mask = cv2.imread(args.fmax)
  track = cv2.imread(args.track)
  
  mask1, mask2, mask3= cv2.split(mask)
  
  # Pipeline step
  device = 0
  
  # Mask pesky track autofluor
  device, track1= pcv.rgb2gray_hsv(track, 'v', device, args.debug)
  device, track_thresh = pcv.binary_threshold(track1, 0, 255, 'light', device, args.debug)
  device, track_inv=pcv.invert(track_thresh, device, args.debug)
  device, track_masked = pcv.apply_mask(mask1, track_inv, 'black', device, args.debug)
  
  # Threshold the Saturation image
  device, fmax_thresh = pcv.binary_threshold(track_masked, 20, 255, 'light', device, args.debug)

# Read image
    device = 0
    img = cv2.imread(args.image, flags=0)
    path, img_name = os.path.split(args.image)
    # Read in image which is average of average of backgrounds
    img_bkgrd = cv2.imread("/home/mgehan/LemnaTec/plantcv/masks/nir_tv/background_nir_z3500.png", flags=0)

    # NIR images for burnin2 are up-side down. This may be fixed in later experiments
    img =  ndimage.rotate(img, 0)
    img_bkgrd =  ndimage.rotate(img_bkgrd, 0)

    # Subtract the image from the image background to make the plant more prominent
    device, bkg_sub_img = pcv.image_subtract(img, img_bkgrd, device, args.debug)
    if args.debug:
        pcv.plot_hist(bkg_sub_img, 'bkg_sub_img')
    device, bkg_sub_thres_img = pcv.binary_threshold(bkg_sub_img, 150, 255, 'dark', device, args.debug)
    bkg_sub_thres_img = cv2.inRange(bkg_sub_img, 50, 190)
    if args.debug:
        cv2.imwrite('bkgrd_sub_thres.png', bkg_sub_thres_img)
    
    #device, bkg_sub_thres_img = pcv.binary_threshold_2_sided(img_bkgrd, 50, 190, device, args.debug)
    
    # if a region of interest is specified read it in
    roi = cv2.imread(args.roi)
    
    
    # Start by examining the distribution of pixel intensity values
    if args.debug:
      pcv.plot_hist(img, 'hist_img')
      
    # Will intensity transformation enhance your ability to isolate object of interest by thesholding?

# Read image
    device = 0
    img = cv2.imread(args.image, flags=0)
    path, img_name = os.path.split(args.image)
    # Read in image which is average of average of backgrounds
    img_bkgrd = cv2.imread("/home/mgehan/LemnaTec/plantcv/masks/nir_tv/background_nir_z3500.png", flags=0)

    # NIR images for burnin2 are up-side down. This may be fixed in later experiments
    img =  ndimage.rotate(img, 0)
    img_bkgrd =  ndimage.rotate(img_bkgrd, 0)

    # Subtract the image from the image background to make the plant more prominent
    device, bkg_sub_img = pcv.image_subtract(img, img_bkgrd, device, args.debug)
    if args.debug:
        pcv.plot_hist(bkg_sub_img, 'bkg_sub_img')
    device, bkg_sub_thres_img = pcv.binary_threshold(bkg_sub_img, 150, 255, 'dark', device, args.debug)
    bkg_sub_thres_img = cv2.inRange(bkg_sub_img, 50, 190)
    if args.debug:
        cv2.imwrite('bkgrd_sub_thres.png', bkg_sub_thres_img)
    
    #device, bkg_sub_thres_img = pcv.binary_threshold_2_sided(img_bkgrd, 50, 190, device, args.debug)
    
    # if a region of interest is specified read it in
    roi = cv2.imread(args.roi)
    
    
    # Start by examining the distribution of pixel intensity values
    if args.debug:
      pcv.plot_hist(img, 'hist_img')
      
    # Will intensity transformation enhance your ability to isolate object of interest by thesholding?

def read_data(filename):
    """Read hyperspectral image data from file.

        Inputs:
        filename = name of image file

        Returns:
        spectral_array    = image object as numpy array

        :param filename: str
        :return spectral_array: __main__.Spectral_data
        """
    # Store debug mode
    debug = params.debug
    params.debug = None

    # Initialize dictionary
    header_dict = {}

    headername = filename + ".hdr"

    with open(headername, "r") as f:
        # Replace characters for easier parsing
        hdata = f.read()
        hdata = hdata.replace(",\n", ",")
        hdata = hdata.replace("\n,", ",")
        hdata = hdata.replace("{\n", "{")
        hdata = hdata.replace("\n}", "}")
        hdata = hdata.replace(" \n ", "")
        hdata = hdata.replace(";", "")
    hdata = hdata.split("\n")

device, brass_masked = pcv.apply_mask(masked, brass_inv, 'white', device, debug)

    # Further mask soil and car
    device, masked_a = pcv.rgb2gray_lab(brass_masked, 'a', device, debug)
    device, soil_car1 = pcv.binary_threshold(masked_a, 128, 255, 'dark', device, debug)
    device, soil_car2 = pcv.binary_threshold(masked_a, 128, 255, 'light', device, debug)
    device, soil_car = pcv.logical_or(soil_car1, soil_car2, device, debug)
    device, soil_masked = pcv.apply_mask(brass_masked, soil_car, 'white', device, debug)

    # Convert RGB to LAB and extract the Green-Magenta and Blue-Yellow channels
    device, soil_a = pcv.rgb2gray_lab(soil_masked, 'a', device, debug)
    device, soil_b = pcv.rgb2gray_lab(soil_masked, 'b', device, debug)

    # Threshold the green-magenta and blue images
    device, soila_thresh = pcv.binary_threshold(soil_a, 124, 255, 'dark', device, debug)
    device, soilb_thresh = pcv.binary_threshold(soil_b, 148, 255, 'light', device, debug)

    # Join the thresholded saturation and blue-yellow images (OR)
    device, soil_ab = pcv.logical_or(soila_thresh, soilb_thresh, device, debug)
    device, soil_ab_cnt = pcv.logical_or(soila_thresh, soilb_thresh, device, debug)

    # Fill small objects
    device, soil_cnt = pcv.fill(soil_ab, soil_ab_cnt, 300, device, debug)

    # Apply mask (for vis images, mask_color=white)
    device, masked2 = pcv.apply_mask(soil_masked, soil_cnt, 'white', device, debug)

    # Identify objects
    device, id_objects, obj_hierarchy = pcv.find_objects(masked2, soil_cnt, device, debug)

    # Define ROI
    device, roi1, roi_hierarchy = pcv.define_roi(img, 'rectangle', device, None, 'default', debug, True, 600, 450, -600,

device, masked_b1 = pcv.rgb2gray_lab(masked3, 'b', device, args.debug)
  device, maskeda_thresh1 = pcv.binary_threshold(masked_a1, 110, 255, 'dark', device, args.debug)
  device, maskedb_thresh1 = pcv.binary_threshold(masked_b1, 200, 255, 'light', device, args.debug)
  device, ab1 = pcv.logical_or(maskeda_thresh1, maskedb_thresh1, device, args.debug)
  device, ab_cnt1 = pcv.logical_or(maskeda_thresh1, maskedb_thresh1, device, args.debug)
  device, ab_fill1 = pcv.fill(ab1, ab_cnt1, 300, device, args.debug)

  
  device, roi2, roi_hierarchy2= pcv.define_roi(masked2,'rectangle', device, None, 'default', args.debug,True, 1900, 0,0,0)
  device, id_objects2,obj_hierarchy2 = pcv.find_objects(masked2, ab_fill, device, args.debug)
  device,roi_objects2, hierarchy2, kept_mask2, obj_area2 = pcv.roi_objects(masked2,'cutto',roi2,roi_hierarchy2,id_objects2,obj_hierarchy2,device, args.debug)
  device, masked4 = pcv.apply_mask(masked2, kept_mask2, 'white', device, args.debug)
  device, masked_a2 = pcv.rgb2gray_lab(masked4, 'a', device, args.debug)
  device, masked_b2 = pcv.rgb2gray_lab(masked4, 'b', device, args.debug)
  device, maskeda_thresh2 = pcv.binary_threshold(masked_a2, 122, 255, 'dark', device, args.debug)
  device, maskedb_thresh2 = pcv.binary_threshold(masked_b2, 170, 255, 'light', device, args.debug)
  device, ab2 = pcv.logical_or(maskeda_thresh2, maskedb_thresh2, device, args.debug)
  device, ab_cnt2 = pcv.logical_or(maskeda_thresh2, maskedb_thresh2, device, args.debug)
  device, ab_fill2 = pcv.fill(ab2, ab_cnt2, 200, device, args.debug)
  
  device, ab_cnt3 = pcv.logical_or(ab_fill1, ab_fill2, device, args.debug)
  device, masked3 = pcv.apply_mask(masked2, ab_cnt3, 'white', device, args.debug)
  
  # Identify objects
  device, id_objects3,obj_hierarchy3 = pcv.find_objects(masked2, ab_fill, device, args.debug)

  # Define ROI
  device, roi3, roi_hierarchy3= pcv.define_roi(masked2,'rectangle', device, None, 'default', args.debug,True, 500, 0,-450,-750)
 
  # Decide which objects to keep and combine with objects overlapping with black bars
  device,roi_objects3, hierarchy3, kept_mask3, obj_area1 = pcv.roi_objects(img,'cutto',roi3,roi_hierarchy3,id_objects3,obj_hierarchy3,device, args.debug)
  device, kept_mask4_1 = pcv.logical_or(ab_cnt3, kept_mask3, device, args.debug)

device, brass_mask1 = pcv.rgb2gray_hsv(brass_mask, 'v', device, args.debug)
  device, brass_thresh = pcv.binary_threshold(brass_mask1, 0, 255, 'light', device, args.debug)
  device, brass_inv=pcv.invert(brass_thresh, device, args.debug)
  device, brass_masked = pcv.apply_mask(masked, brass_inv, 'white', device, args.debug)
  
  # Further mask soil and car
  device, masked_a = pcv.rgb2gray_lab(brass_masked, 'a', device, args.debug)
  device, soil_car = pcv.binary_threshold(masked_a, 128, 255, 'dark', device, args.debug)
  device, soil_masked = pcv.apply_mask(brass_masked, soil_car, 'white', device, args.debug)
  
  # Convert RGB to LAB and extract the Green-Magenta and Blue-Yellow channels
  device, soil_a = pcv.rgb2gray_lab(soil_masked, 'a', device, args.debug)
  device, soil_b = pcv.rgb2gray_lab(soil_masked, 'b', device, args.debug)
  
  # Threshold the green-magenta and blue images
  device, soila_thresh = pcv.binary_threshold(soil_a, 118, 255, 'dark', device, args.debug)
  device, soilb_thresh = pcv.binary_threshold(soil_b, 155, 255, 'light', device, args.debug)

  # Join the thresholded saturation and blue-yellow images (OR)
  device, soil_ab = pcv.logical_or(soila_thresh, soilb_thresh, device, args.debug)
  device, soil_ab_cnt = pcv.logical_or(soila_thresh, soilb_thresh, device, args.debug)

  # Fill small objects
  device, soil_fill = pcv.fill(soil_ab, soil_ab_cnt, 75, device, args.debug)

  # Median Filter
  device, soil_mblur = pcv.median_blur(soil_fill, 5, device, args.debug)
  device, soil_cnt = pcv.median_blur(soil_fill, 5, device, args.debug)
  
  # Apply mask (for vis images, mask_color=white)
  device, masked2 = pcv.apply_mask(soil_masked, soil_cnt, 'white', device, args.debug)

# Threshold the Saturation image
  device, s_thresh = pcv.binary_threshold(s, 36, 255, 'light', device, args.debug)
  
  # Median Filter
  device, s_mblur = pcv.median_blur(s_thresh, 5, device, args.debug)
  device, s_cnt = pcv.median_blur(s_thresh, 5, device, args.debug)
  
  # Fill small objects
  device, s_fill = pcv.fill(s_mblur, s_cnt, 0, device, args.debug)
  
  # Convert RGB to LAB and extract the Blue channel
  device, b = pcv.rgb2gray_lab(img, 'b', device, args.debug)
  
  # Threshold the blue image
  device, b_thresh = pcv.binary_threshold(b, 138, 255, 'light', device, args.debug)
  device, b_cnt = pcv.binary_threshold(b, 138, 255, 'light', device, args.debug)
  
  # Fill small objects
  device, b_fill = pcv.fill(b_thresh, b_cnt, 150, device, args.debug)
  
  # Join the thresholded saturation and blue-yellow images
  device, bs = pcv.logical_and(s_fill, b_fill, device, args.debug)
  
  # Apply Mask (for vis images, mask_color=white)
  device, masked = pcv.apply_mask(img, bs, 'white', device, args.debug)
  
  # Convert RGB to LAB and extract the Green-Magenta and Blue-Yellow channels
  device, masked_a = pcv.rgb2gray_lab(masked, 'a', device, args.debug)
  device, masked_b = pcv.rgb2gray_lab(masked, 'b', device, args.debug)
  
  # Threshold the green-magenta and blue images
  device, maskeda_thresh = pcv.binary_threshold(masked_a, 122, 255, 'dark', device, args.debug)

device, brass_masked = pcv.apply_mask(masked, brass_inv, 'white', device, args.debug)
  
  # Further mask soil and car
  device, masked_a = pcv.rgb2gray_lab(brass_masked, 'a', device, args.debug)
  device, soil_car1 = pcv.binary_threshold(masked_a, 128, 255, 'dark', device, args.debug)
  device, soil_car2 = pcv.binary_threshold(masked_a, 128, 255, 'light', device, args.debug)
  device, soil_car=pcv.logical_or(soil_car1, soil_car2,device, args.debug)
  device, soil_masked = pcv.apply_mask(brass_masked, soil_car, 'white', device, args.debug)
  
  # Convert RGB to LAB and extract the Green-Magenta and Blue-Yellow channels
  device, soil_a = pcv.rgb2gray_lab(soil_masked, 'a', device, args.debug)
  device, soil_b = pcv.rgb2gray_lab(soil_masked, 'b', device, args.debug)
  
  # Threshold the green-magenta and blue images
  device, soila_thresh = pcv.binary_threshold(soil_a, 124, 255, 'dark', device, args.debug)
  device, soilb_thresh = pcv.binary_threshold(soil_b, 148, 255, 'light', device, args.debug)

  # Join the thresholded saturation and blue-yellow images (OR)
  device, soil_ab = pcv.logical_or(soila_thresh, soilb_thresh, device, args.debug)
  device, soil_ab_cnt = pcv.logical_or(soila_thresh, soilb_thresh, device, args.debug)

  # Fill small objects
  device, soil_cnt = pcv.fill(soil_ab, soil_ab_cnt, 150, device, args.debug)

  # Median Filter
  #device, soil_mblur = pcv.median_blur(soil_fill, 5, device, args.debug)
  #device, soil_cnt = pcv.median_blur(soil_fill, 5, device, args.debug)
  
  # Apply mask (for vis images, mask_color=white)
  device, masked2 = pcv.apply_mask(soil_masked, soil_cnt, 'white', device, args.debug)
  
  # Identify objects