added image cropping tool

crop_specimens.py

@@ -0,0 +1,144 @@
+# a digital cake knife in the spirit of Hannah Höch
+# cuts out composable contours from the herbarium scans
+import glob
+import os.path
+import sqlite3
+
+import cv2
+import numpy as np
+from PIL import Image
+
+BLUR = 3
+CANNY_THRESH_1 = 200
+CANNY_THRESH_2 = 250
+MASK_DILATE_ITER = 40
+MASK_ERODE_ITER = 40
+MASK_COLOR = (0.0,0.0,1.0) # In BGR format
+
+src_imgs = glob.glob("specimen_img_raw/*")
+
+db = sqlite3.connect("ratios.db")
+dbc = db.cursor()
+
+for src in src_imgs:
+    img_color = cv2.imread(src)
+    scalar = float(1000.0 / img_color.shape[1])
+    new_height = int(scalar * img_color.shape[0])
+    img_color = cv2.resize(img_color, (1000, new_height))
+    img_gray = cv2.imread(src, flags=cv2.IMREAD_GRAYSCALE)
+    img_gray = cv2.resize(img_gray, (1000, new_height))
+
+    # add some white around the edges so we have some space to rotate
+    img_color = cv2.copyMakeBorder(img_color,10,10,10,10,cv2.BORDER_CONSTANT, value=[255, 255, 255])
+    img_gray = cv2.copyMakeBorder(img_gray,10,10,10,10,cv2.BORDER_CONSTANT, value=[255])
+    blurred = cv2.GaussianBlur(img_gray, (9, 9), 0)
+
+    aperture = 5  # default is 3 but 5 or 7 are more sensitive
+
+    # most of this is ganked directly from this https://stackoverflow.com/questions/29313667/how-do-i-remove-the-background-from-this-kind-of-image
+
+    #-- Edge detection -------------------------------------------------------------------
+    edges = cv2.Canny(blurred, CANNY_THRESH_1, CANNY_THRESH_2, apertureSize=aperture)
+    edges = cv2.dilate(edges, None)
+    edges = cv2.erode(edges, None)
+
+    #-- Find contours in edges, sort by area ---------------------------------------------
+    contour_info = []
+    contours, _ = cv2.findContours(edges, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
+    for c in contours:
+        contour_info.append((
+            c,
+            cv2.isContourConvex(c),
+            cv2.contourArea(c),
+        ))
+    contour_info = sorted(contour_info, key=lambda c: c[2], reverse=True)
+
+    # filter out the accidental box contours - should be less than 85% of pixels
+    img_area = img_color.shape[0] * img_color.shape[1]
+    for cont in contour_info:
+        max_contour = cont
+        pixel_ratio = max_contour[2] / img_area
+        if pixel_ratio < 0.85:
+            test_img = img_color.copy()
+            c_rect = cv2.minAreaRect(max_contour[0])
+            box = cv2.boxPoints(c_rect)
+            box = np.int0(box)
+            cv2.drawContours(test_img, [max_contour[0]], -1, (255, 0, 0, 20), 3)
+            cv2.drawContours(test_img, [box], -1, (0, 255, 0), 3)
+            cv2.imwrite("test.png", test_img)
+            test_viewer = Image.open("test.png")
+            test_viewer.show()
+            if input("contour ok (y/n)?") == "y":
+                test_viewer.close()
+                break
+            test_viewer.close()
+
+    #-- Create empty mask, draw filled polygon on it corresponding to largest contour ----
+    # Mask is black, polygon is white
+    mask = np.zeros(edges.shape)
+    cv2.fillConvexPoly(mask, max_contour[0], (255))
+
+    #-- Smooth mask, then blur it --------------------------------------------------------
+    mask = cv2.dilate(mask, None, iterations=MASK_DILATE_ITER)
+    mask = cv2.erode(mask, None, iterations=MASK_ERODE_ITER)
+    mask = cv2.GaussianBlur(mask, (BLUR, BLUR), 0)
+    mask_stack = np.dstack([mask]*3)    # Create 3-channel alpha mask
+
+    #-- Blend masked img into MASK_COLOR background --------------------------------------
+    mask_stack = mask_stack.astype('float32') / 255.0          # Use float matrices,
+    img_color = img_color.astype('float32') / 255.0                 #  for easy blending
+
+    # split image into channels
+    try:
+        c_red, c_green, c_blue = cv2.split(img_color)
+    except ValueError:
+        print("seems to be greyscale already...")
+        img_color = cv2.cvtColor(img_color, cv2.COLOR_GRAY2BGR)
+        c_red, c_green, c_blue = cv2.split(img_color)
+
+    # merge with mask got on one of a previous steps
+    img_a = cv2.merge((c_red, c_green, c_blue, mask.astype('float32') / 255.0))
+
+    # find bounding minimum bounding rect as that's what we want to rotate & save
+    rect = cv2.minAreaRect(max_contour[0])
+    box = cv2.boxPoints(rect)
+    box = np.int0(box)
+
+    width = int(rect[1][0])
+    height = int(rect[1][1])
+
+    # set up a new destination exactly the size of our ROI
+    src_pts = box.astype("float32")
+    dst_pts = np.array([[0, height-1],
+                        [0, 0],
+                        [width-1, 0],
+                        [width-1, height-1]], dtype="float32")
+
+    # now rotate using warp which is more efficient and preserves pixels
+    M = cv2.getPerspectiveTransform(src_pts, dst_pts)
+    warped = cv2.warpPerspective(img_a, M, (width, height))
+
+    # save to disk
+    basename, ext = os.path.splitext(os.path.basename(src))
+    out_path = os.path.join("specimen_cutout", basename + ".png")
+    print("saving cropped cutout", out_path)
+    cv2.imwrite(out_path, warped*255)
+
+    # add to database
+    if height > width:
+        ratio = float(height) / width
+    else:
+        ratio = float(width) / height
+
+    try:
+        dbc.execute("INSERT INTO images VALUES (?, ?, ?, ?)", (ratio, width, height, out_path))
+    except sqlite3.IntegrityError as err:
+        print(err)
+        print("Trying db update instead.")
+        dbc.execute("UPDATE images SET (ratio, width, height) = (?, ?, ?) WHERE img_path = ?", 
+                    (ratio, width, height, out_path))
+
+
+db.commit()
+db.close()
+

image_fetch.py

@@ -20,7 +20,7 @@ def find_image(rdf_doc):
             return obj
 
 
-with open("barcode_cleaned.csv") as bcfile:
+with open("belgian_colony_data_all.csv") as bcfile:
     for line in bcfile:
         barcode = line.split(",")[0]