From 59ed74438318af893d2cba552b0e28dbc2a9266c Mon Sep 17 00:00:00 2001 From: captin411 Date: Wed, 19 Oct 2022 17:19:02 -0700 Subject: face detection algo, configurability, reusability Try to move the crop in the direction of a face if it is present More internal configuration options for choosing weights of each of the algorithm's findings Move logic into its module --- modules/textual_inversion/autocrop.py | 216 ++++++++++++++++++++++++++++++++++ 1 file changed, 216 insertions(+) create mode 100644 modules/textual_inversion/autocrop.py (limited to 'modules/textual_inversion/autocrop.py') diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py new file mode 100644 index 00000000..f858a958 --- /dev/null +++ b/modules/textual_inversion/autocrop.py @@ -0,0 +1,216 @@ +import cv2 +from collections import defaultdict +from math import log, sqrt +import numpy as np +from PIL import Image, ImageDraw + +GREEN = "#0F0" +BLUE = "#00F" +RED = "#F00" + +def crop_image(im, settings): + """ Intelligently crop an image to the subject matter """ + if im.height > im.width: + im = im.resize((settings.crop_width, settings.crop_height * im.height // im.width)) + else: + im = im.resize((settings.crop_width * im.width // im.height, settings.crop_height)) + + focus = focal_point(im, settings) + + # take the focal point and turn it into crop coordinates that try to center over the focal + # point but then get adjusted back into the frame + y_half = int(settings.crop_height / 2) + x_half = int(settings.crop_width / 2) + + x1 = focus.x - x_half + if x1 < 0: + x1 = 0 + elif x1 + settings.crop_width > im.width: + x1 = im.width - settings.crop_width + + y1 = focus.y - y_half + if y1 < 0: + y1 = 0 + elif y1 + settings.crop_height > im.height: + y1 = im.height - settings.crop_height + + x2 = x1 + settings.crop_width + y2 = y1 + settings.crop_height + + crop = [x1, y1, x2, y2] + + if settings.annotate_image: + d = ImageDraw.Draw(im) + rect = list(crop) + rect[2] -= 1 + rect[3] -= 1 + d.rectangle(rect, outline=GREEN) + if settings.destop_view_image: + im.show() + + return im.crop(tuple(crop)) + +def focal_point(im, settings): + corner_points = image_corner_points(im, settings) + entropy_points = image_entropy_points(im, settings) + face_points = image_face_points(im, settings) + + total_points = len(corner_points) + len(entropy_points) + len(face_points) + + corner_weight = settings.corner_points_weight + entropy_weight = settings.entropy_points_weight + face_weight = settings.face_points_weight + + weight_pref_total = corner_weight + entropy_weight + face_weight + + # weight things + pois = [] + if weight_pref_total == 0 or total_points == 0: + return pois + + pois.extend( + [ PointOfInterest( p.x, p.y, weight=p.weight * ( (corner_weight/weight_pref_total) / (len(corner_points)/total_points) )) for p in corner_points ] + ) + pois.extend( + [ PointOfInterest( p.x, p.y, weight=p.weight * ( (entropy_weight/weight_pref_total) / (len(entropy_points)/total_points) )) for p in entropy_points ] + ) + pois.extend( + [ PointOfInterest( p.x, p.y, weight=p.weight * ( (face_weight/weight_pref_total) / (len(face_points)/total_points) )) for p in face_points ] + ) + + if settings.annotate_image: + d = ImageDraw.Draw(im) + + average_point = poi_average(pois, settings, im=im) + + if settings.annotate_image: + d.ellipse([average_point.x - 25, average_point.y - 25, average_point.x + 25, average_point.y + 25], outline=GREEN) + + return average_point + + +def image_face_points(im, settings): + np_im = np.array(im) + gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY) + classifier = cv2.CascadeClassifier(f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml') + + minsize = int(min(im.width, im.height) * 0.15) # at least N percent of the smallest side + faces = classifier.detectMultiScale(gray, scaleFactor=1.05, + minNeighbors=5, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE) + + if len(faces) == 0: + return [] + + rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces] + if settings.annotate_image: + for f in rects: + d = ImageDraw.Draw(im) + d.rectangle(f, outline=RED) + + return [PointOfInterest((r[0] +r[2]) // 2, (r[1] + r[3]) // 2) for r in rects] + + +def image_corner_points(im, settings): + grayscale = im.convert("L") + + # naive attempt at preventing focal points from collecting at watermarks near the bottom + gd = ImageDraw.Draw(grayscale) + gd.rectangle([0, im.height*.9, im.width, im.height], fill="#999") + + np_im = np.array(grayscale) + + points = cv2.goodFeaturesToTrack( + np_im, + maxCorners=100, + qualityLevel=0.04, + minDistance=min(grayscale.width, grayscale.height)*0.07, + useHarrisDetector=False, + ) + + if points is None: + return [] + + focal_points = [] + for point in points: + x, y = point.ravel() + focal_points.append(PointOfInterest(x, y)) + + return focal_points + + +def image_entropy_points(im, settings): + landscape = im.height < im.width + portrait = im.height > im.width + if landscape: + move_idx = [0, 2] + move_max = im.size[0] + elif portrait: + move_idx = [1, 3] + move_max = im.size[1] + else: + return [] + + e_max = 0 + crop_current = [0, 0, settings.crop_width, settings.crop_height] + crop_best = crop_current + while crop_current[move_idx[1]] < move_max: + crop = im.crop(tuple(crop_current)) + e = image_entropy(crop) + + if (e > e_max): + e_max = e + crop_best = list(crop_current) + + crop_current[move_idx[0]] += 4 + crop_current[move_idx[1]] += 4 + + x_mid = int(crop_best[0] + settings.crop_width/2) + y_mid = int(crop_best[1] + settings.crop_height/2) + + return [PointOfInterest(x_mid, y_mid)] + + +def image_entropy(im): + # greyscale image entropy + band = np.asarray(im.convert("1")) + hist, _ = np.histogram(band, bins=range(0, 256)) + hist = hist[hist > 0] + return -np.log2(hist / hist.sum()).sum() + + +def poi_average(pois, settings, im=None): + weight = 0.0 + x = 0.0 + y = 0.0 + for pois in pois: + if settings.annotate_image and im is not None: + w = 4 * 0.5 * sqrt(pois.weight) + d = ImageDraw.Draw(im) + d.ellipse([ + pois.x - w, pois.y - w, + pois.x + w, pois.y + w ], fill=BLUE) + weight += pois.weight + x += pois.x * pois.weight + y += pois.y * pois.weight + avg_x = round(x / weight) + avg_y = round(y / weight) + + return PointOfInterest(avg_x, avg_y) + + +class PointOfInterest: + def __init__(self, x, y, weight=1.0): + self.x = x + self.y = y + self.weight = weight + + +class Settings: + def __init__(self, crop_width=512, crop_height=512, corner_points_weight=0.5, entropy_points_weight=0.5, face_points_weight=0.5, annotate_image=False): + self.crop_width = crop_width + self.crop_height = crop_height + self.corner_points_weight = corner_points_weight + self.entropy_points_weight = entropy_points_weight + self.face_points_weight = entropy_points_weight + self.annotate_image = annotate_image + self.destop_view_image = False \ No newline at end of file -- cgit v1.2.3 From 0ddaf8d2028a7251e8c4ad93551a43b5d4700841 Mon Sep 17 00:00:00 2001 From: captin411 Date: Thu, 20 Oct 2022 00:34:55 -0700 Subject: improve face detection a lot --- modules/textual_inversion/autocrop.py | 99 ++++++++++++++++++++++------------- 1 file changed, 62 insertions(+), 37 deletions(-) (limited to 'modules/textual_inversion/autocrop.py') diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index f858a958..5a551c25 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -8,12 +8,18 @@ GREEN = "#0F0" BLUE = "#00F" RED = "#F00" + def crop_image(im, settings): """ Intelligently crop an image to the subject matter """ if im.height > im.width: im = im.resize((settings.crop_width, settings.crop_height * im.height // im.width)) - else: + elif im.width > im.height: im = im.resize((settings.crop_width * im.width // im.height, settings.crop_height)) + else: + im = im.resize((settings.crop_width, settings.crop_height)) + + if im.height == im.width: + return im focus = focal_point(im, settings) @@ -78,13 +84,18 @@ def focal_point(im, settings): [ PointOfInterest( p.x, p.y, weight=p.weight * ( (face_weight/weight_pref_total) / (len(face_points)/total_points) )) for p in face_points ] ) - if settings.annotate_image: - d = ImageDraw.Draw(im) - - average_point = poi_average(pois, settings, im=im) + average_point = poi_average(pois, settings) if settings.annotate_image: - d.ellipse([average_point.x - 25, average_point.y - 25, average_point.x + 25, average_point.y + 25], outline=GREEN) + d = ImageDraw.Draw(im) + for f in face_points: + d.rectangle(f.bounding(f.size), outline=RED) + for f in entropy_points: + d.rectangle(f.bounding(30), outline=BLUE) + for poi in pois: + w = max(4, 4 * 0.5 * sqrt(poi.weight)) + d.ellipse(poi.bounding(w), fill=BLUE) + d.ellipse(average_point.bounding(25), outline=GREEN) return average_point @@ -92,22 +103,32 @@ def focal_point(im, settings): def image_face_points(im, settings): np_im = np.array(im) gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY) - classifier = cv2.CascadeClassifier(f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml') - - minsize = int(min(im.width, im.height) * 0.15) # at least N percent of the smallest side - faces = classifier.detectMultiScale(gray, scaleFactor=1.05, - minNeighbors=5, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE) - if len(faces) == 0: - return [] - - rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces] - if settings.annotate_image: - for f in rects: - d = ImageDraw.Draw(im) - d.rectangle(f, outline=RED) - - return [PointOfInterest((r[0] +r[2]) // 2, (r[1] + r[3]) // 2) for r in rects] + tries = [ + [ f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01 ], + [ f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05 ] + ] + + for t in tries: + # print(t[0]) + classifier = cv2.CascadeClassifier(t[0]) + minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side + try: + faces = classifier.detectMultiScale(gray, scaleFactor=1.1, + minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE) + except: + continue + + if len(faces) > 0: + rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces] + return [PointOfInterest((r[0] +r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0]-r[2])) for r in rects] + return [] def image_corner_points(im, settings): @@ -132,8 +153,8 @@ def image_corner_points(im, settings): focal_points = [] for point in points: - x, y = point.ravel() - focal_points.append(PointOfInterest(x, y)) + x, y = point.ravel() + focal_points.append(PointOfInterest(x, y, size=4)) return focal_points @@ -167,31 +188,26 @@ def image_entropy_points(im, settings): x_mid = int(crop_best[0] + settings.crop_width/2) y_mid = int(crop_best[1] + settings.crop_height/2) - return [PointOfInterest(x_mid, y_mid)] + return [PointOfInterest(x_mid, y_mid, size=25)] def image_entropy(im): # greyscale image entropy - band = np.asarray(im.convert("1")) + # band = np.asarray(im.convert("L")) + band = np.asarray(im.convert("1"), dtype=np.uint8) hist, _ = np.histogram(band, bins=range(0, 256)) hist = hist[hist > 0] return -np.log2(hist / hist.sum()).sum() -def poi_average(pois, settings, im=None): +def poi_average(pois, settings): weight = 0.0 x = 0.0 y = 0.0 - for pois in pois: - if settings.annotate_image and im is not None: - w = 4 * 0.5 * sqrt(pois.weight) - d = ImageDraw.Draw(im) - d.ellipse([ - pois.x - w, pois.y - w, - pois.x + w, pois.y + w ], fill=BLUE) - weight += pois.weight - x += pois.x * pois.weight - y += pois.y * pois.weight + for poi in pois: + weight += poi.weight + x += poi.x * poi.weight + y += poi.y * poi.weight avg_x = round(x / weight) avg_y = round(y / weight) @@ -199,10 +215,19 @@ def poi_average(pois, settings, im=None): class PointOfInterest: - def __init__(self, x, y, weight=1.0): + def __init__(self, x, y, weight=1.0, size=10): self.x = x self.y = y self.weight = weight + self.size = size + + def bounding(self, size): + return [ + self.x - size//2, + self.y - size//2, + self.x + size//2, + self.y + size//2 + ] class Settings: -- cgit v1.2.3 From 1be5933ba21a3badec42b7b2753d626f849b609d Mon Sep 17 00:00:00 2001 From: captin411 Date: Sun, 23 Oct 2022 04:11:07 -0700 Subject: auto cropping now works with non square crops --- modules/textual_inversion/autocrop.py | 509 ++++++++++++++++++---------------- 1 file changed, 269 insertions(+), 240 deletions(-) (limited to 'modules/textual_inversion/autocrop.py') diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index 5a551c25..b2f9241c 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -1,241 +1,270 @@ -import cv2 -from collections import defaultdict -from math import log, sqrt -import numpy as np -from PIL import Image, ImageDraw - -GREEN = "#0F0" -BLUE = "#00F" -RED = "#F00" - - -def crop_image(im, settings): - """ Intelligently crop an image to the subject matter """ - if im.height > im.width: - im = im.resize((settings.crop_width, settings.crop_height * im.height // im.width)) - elif im.width > im.height: - im = im.resize((settings.crop_width * im.width // im.height, settings.crop_height)) - else: - im = im.resize((settings.crop_width, settings.crop_height)) - - if im.height == im.width: - return im - - focus = focal_point(im, settings) - - # take the focal point and turn it into crop coordinates that try to center over the focal - # point but then get adjusted back into the frame - y_half = int(settings.crop_height / 2) - x_half = int(settings.crop_width / 2) - - x1 = focus.x - x_half - if x1 < 0: - x1 = 0 - elif x1 + settings.crop_width > im.width: - x1 = im.width - settings.crop_width - - y1 = focus.y - y_half - if y1 < 0: - y1 = 0 - elif y1 + settings.crop_height > im.height: - y1 = im.height - settings.crop_height - - x2 = x1 + settings.crop_width - y2 = y1 + settings.crop_height - - crop = [x1, y1, x2, y2] - - if settings.annotate_image: - d = ImageDraw.Draw(im) - rect = list(crop) - rect[2] -= 1 - rect[3] -= 1 - d.rectangle(rect, outline=GREEN) - if settings.destop_view_image: - im.show() - - return im.crop(tuple(crop)) - -def focal_point(im, settings): - corner_points = image_corner_points(im, settings) - entropy_points = image_entropy_points(im, settings) - face_points = image_face_points(im, settings) - - total_points = len(corner_points) + len(entropy_points) + len(face_points) - - corner_weight = settings.corner_points_weight - entropy_weight = settings.entropy_points_weight - face_weight = settings.face_points_weight - - weight_pref_total = corner_weight + entropy_weight + face_weight - - # weight things - pois = [] - if weight_pref_total == 0 or total_points == 0: - return pois - - pois.extend( - [ PointOfInterest( p.x, p.y, weight=p.weight * ( (corner_weight/weight_pref_total) / (len(corner_points)/total_points) )) for p in corner_points ] - ) - pois.extend( - [ PointOfInterest( p.x, p.y, weight=p.weight * ( (entropy_weight/weight_pref_total) / (len(entropy_points)/total_points) )) for p in entropy_points ] - ) - pois.extend( - [ PointOfInterest( p.x, p.y, weight=p.weight * ( (face_weight/weight_pref_total) / (len(face_points)/total_points) )) for p in face_points ] - ) - - average_point = poi_average(pois, settings) - - if settings.annotate_image: - d = ImageDraw.Draw(im) - for f in face_points: - d.rectangle(f.bounding(f.size), outline=RED) - for f in entropy_points: - d.rectangle(f.bounding(30), outline=BLUE) - for poi in pois: - w = max(4, 4 * 0.5 * sqrt(poi.weight)) - d.ellipse(poi.bounding(w), fill=BLUE) - d.ellipse(average_point.bounding(25), outline=GREEN) - - return average_point - - -def image_face_points(im, settings): - np_im = np.array(im) - gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY) - - tries = [ - [ f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01 ], - [ f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05 ] - ] - - for t in tries: - # print(t[0]) - classifier = cv2.CascadeClassifier(t[0]) - minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side - try: - faces = classifier.detectMultiScale(gray, scaleFactor=1.1, - minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE) - except: - continue - - if len(faces) > 0: - rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces] - return [PointOfInterest((r[0] +r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0]-r[2])) for r in rects] - return [] - - -def image_corner_points(im, settings): - grayscale = im.convert("L") - - # naive attempt at preventing focal points from collecting at watermarks near the bottom - gd = ImageDraw.Draw(grayscale) - gd.rectangle([0, im.height*.9, im.width, im.height], fill="#999") - - np_im = np.array(grayscale) - - points = cv2.goodFeaturesToTrack( - np_im, - maxCorners=100, - qualityLevel=0.04, - minDistance=min(grayscale.width, grayscale.height)*0.07, - useHarrisDetector=False, - ) - - if points is None: - return [] - - focal_points = [] - for point in points: - x, y = point.ravel() - focal_points.append(PointOfInterest(x, y, size=4)) - - return focal_points - - -def image_entropy_points(im, settings): - landscape = im.height < im.width - portrait = im.height > im.width - if landscape: - move_idx = [0, 2] - move_max = im.size[0] - elif portrait: - move_idx = [1, 3] - move_max = im.size[1] - else: - return [] - - e_max = 0 - crop_current = [0, 0, settings.crop_width, settings.crop_height] - crop_best = crop_current - while crop_current[move_idx[1]] < move_max: - crop = im.crop(tuple(crop_current)) - e = image_entropy(crop) - - if (e > e_max): - e_max = e - crop_best = list(crop_current) - - crop_current[move_idx[0]] += 4 - crop_current[move_idx[1]] += 4 - - x_mid = int(crop_best[0] + settings.crop_width/2) - y_mid = int(crop_best[1] + settings.crop_height/2) - - return [PointOfInterest(x_mid, y_mid, size=25)] - - -def image_entropy(im): - # greyscale image entropy - # band = np.asarray(im.convert("L")) - band = np.asarray(im.convert("1"), dtype=np.uint8) - hist, _ = np.histogram(band, bins=range(0, 256)) - hist = hist[hist > 0] - return -np.log2(hist / hist.sum()).sum() - - -def poi_average(pois, settings): - weight = 0.0 - x = 0.0 - y = 0.0 - for poi in pois: - weight += poi.weight - x += poi.x * poi.weight - y += poi.y * poi.weight - avg_x = round(x / weight) - avg_y = round(y / weight) - - return PointOfInterest(avg_x, avg_y) - - -class PointOfInterest: - def __init__(self, x, y, weight=1.0, size=10): - self.x = x - self.y = y - self.weight = weight - self.size = size - - def bounding(self, size): - return [ - self.x - size//2, - self.y - size//2, - self.x + size//2, - self.y + size//2 - ] - - -class Settings: - def __init__(self, crop_width=512, crop_height=512, corner_points_weight=0.5, entropy_points_weight=0.5, face_points_weight=0.5, annotate_image=False): - self.crop_width = crop_width - self.crop_height = crop_height - self.corner_points_weight = corner_points_weight - self.entropy_points_weight = entropy_points_weight - self.face_points_weight = entropy_points_weight - self.annotate_image = annotate_image +import cv2 +from collections import defaultdict +from math import log, sqrt +import numpy as np +from PIL import Image, ImageDraw + +GREEN = "#0F0" +BLUE = "#00F" +RED = "#F00" + + +def crop_image(im, settings): + """ Intelligently crop an image to the subject matter """ + + scale_by = 1 + if is_landscape(im.width, im.height): + scale_by = settings.crop_height / im.height + elif is_portrait(im.width, im.height): + scale_by = settings.crop_width / im.width + elif is_square(im.width, im.height): + if is_square(settings.crop_width, settings.crop_height): + scale_by = settings.crop_width / im.width + elif is_landscape(settings.crop_width, settings.crop_height): + scale_by = settings.crop_width / im.width + elif is_portrait(settings.crop_width, settings.crop_height): + scale_by = settings.crop_height / im.height + + im = im.resize((int(im.width * scale_by), int(im.height * scale_by))) + + if im.width == settings.crop_width and im.height == settings.crop_height: + if settings.annotate_image: + d = ImageDraw.Draw(im) + rect = [0, 0, im.width, im.height] + rect[2] -= 1 + rect[3] -= 1 + d.rectangle(rect, outline=GREEN) + if settings.destop_view_image: + im.show() + return im + + focus = focal_point(im, settings) + + # take the focal point and turn it into crop coordinates that try to center over the focal + # point but then get adjusted back into the frame + y_half = int(settings.crop_height / 2) + x_half = int(settings.crop_width / 2) + + x1 = focus.x - x_half + if x1 < 0: + x1 = 0 + elif x1 + settings.crop_width > im.width: + x1 = im.width - settings.crop_width + + y1 = focus.y - y_half + if y1 < 0: + y1 = 0 + elif y1 + settings.crop_height > im.height: + y1 = im.height - settings.crop_height + + x2 = x1 + settings.crop_width + y2 = y1 + settings.crop_height + + crop = [x1, y1, x2, y2] + + if settings.annotate_image: + d = ImageDraw.Draw(im) + rect = list(crop) + rect[2] -= 1 + rect[3] -= 1 + d.rectangle(rect, outline=GREEN) + if settings.destop_view_image: + im.show() + + return im.crop(tuple(crop)) + +def focal_point(im, settings): + corner_points = image_corner_points(im, settings) + entropy_points = image_entropy_points(im, settings) + face_points = image_face_points(im, settings) + + total_points = len(corner_points) + len(entropy_points) + len(face_points) + + corner_weight = settings.corner_points_weight + entropy_weight = settings.entropy_points_weight + face_weight = settings.face_points_weight + + weight_pref_total = corner_weight + entropy_weight + face_weight + + # weight things + pois = [] + if weight_pref_total == 0 or total_points == 0: + return pois + + pois.extend( + [ PointOfInterest( p.x, p.y, weight=p.weight * ( (corner_weight/weight_pref_total) / (len(corner_points)/total_points) )) for p in corner_points ] + ) + pois.extend( + [ PointOfInterest( p.x, p.y, weight=p.weight * ( (entropy_weight/weight_pref_total) / (len(entropy_points)/total_points) )) for p in entropy_points ] + ) + pois.extend( + [ PointOfInterest( p.x, p.y, weight=p.weight * ( (face_weight/weight_pref_total) / (len(face_points)/total_points) )) for p in face_points ] + ) + + average_point = poi_average(pois, settings) + + if settings.annotate_image: + d = ImageDraw.Draw(im) + for f in face_points: + d.rectangle(f.bounding(f.size), outline=RED) + for f in entropy_points: + d.rectangle(f.bounding(30), outline=BLUE) + for poi in pois: + w = max(4, 4 * 0.5 * sqrt(poi.weight)) + d.ellipse(poi.bounding(w), fill=BLUE) + d.ellipse(average_point.bounding(25), outline=GREEN) + + return average_point + + +def image_face_points(im, settings): + np_im = np.array(im) + gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY) + + tries = [ + [ f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01 ], + [ f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05 ] + ] + + for t in tries: + # print(t[0]) + classifier = cv2.CascadeClassifier(t[0]) + minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side + try: + faces = classifier.detectMultiScale(gray, scaleFactor=1.1, + minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE) + except: + continue + + if len(faces) > 0: + rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces] + return [PointOfInterest((r[0] +r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0]-r[2])) for r in rects] + return [] + + +def image_corner_points(im, settings): + grayscale = im.convert("L") + + # naive attempt at preventing focal points from collecting at watermarks near the bottom + gd = ImageDraw.Draw(grayscale) + gd.rectangle([0, im.height*.9, im.width, im.height], fill="#999") + + np_im = np.array(grayscale) + + points = cv2.goodFeaturesToTrack( + np_im, + maxCorners=100, + qualityLevel=0.04, + minDistance=min(grayscale.width, grayscale.height)*0.07, + useHarrisDetector=False, + ) + + if points is None: + return [] + + focal_points = [] + for point in points: + x, y = point.ravel() + focal_points.append(PointOfInterest(x, y, size=4)) + + return focal_points + + +def image_entropy_points(im, settings): + landscape = im.height < im.width + portrait = im.height > im.width + if landscape: + move_idx = [0, 2] + move_max = im.size[0] + elif portrait: + move_idx = [1, 3] + move_max = im.size[1] + else: + return [] + + e_max = 0 + crop_current = [0, 0, settings.crop_width, settings.crop_height] + crop_best = crop_current + while crop_current[move_idx[1]] < move_max: + crop = im.crop(tuple(crop_current)) + e = image_entropy(crop) + + if (e > e_max): + e_max = e + crop_best = list(crop_current) + + crop_current[move_idx[0]] += 4 + crop_current[move_idx[1]] += 4 + + x_mid = int(crop_best[0] + settings.crop_width/2) + y_mid = int(crop_best[1] + settings.crop_height/2) + + return [PointOfInterest(x_mid, y_mid, size=25)] + + +def image_entropy(im): + # greyscale image entropy + # band = np.asarray(im.convert("L")) + band = np.asarray(im.convert("1"), dtype=np.uint8) + hist, _ = np.histogram(band, bins=range(0, 256)) + hist = hist[hist > 0] + return -np.log2(hist / hist.sum()).sum() + + +def poi_average(pois, settings): + weight = 0.0 + x = 0.0 + y = 0.0 + for poi in pois: + weight += poi.weight + x += poi.x * poi.weight + y += poi.y * poi.weight + avg_x = round(x / weight) + avg_y = round(y / weight) + + return PointOfInterest(avg_x, avg_y) + + +def is_landscape(w, h): + return w > h + + +def is_portrait(w, h): + return h > w + + +def is_square(w, h): + return w == h + + +class PointOfInterest: + def __init__(self, x, y, weight=1.0, size=10): + self.x = x + self.y = y + self.weight = weight + self.size = size + + def bounding(self, size): + return [ + self.x - size//2, + self.y - size//2, + self.x + size//2, + self.y + size//2 + ] + + +class Settings: + def __init__(self, crop_width=512, crop_height=512, corner_points_weight=0.5, entropy_points_weight=0.5, face_points_weight=0.5, annotate_image=False): + self.crop_width = crop_width + self.crop_height = crop_height + self.corner_points_weight = corner_points_weight + self.entropy_points_weight = entropy_points_weight + self.face_points_weight = entropy_points_weight + self.annotate_image = annotate_image self.destop_view_image = False \ No newline at end of file -- cgit v1.2.3 From 3e6c2420c1177e9e79f2b566a5a7795b7416e34a Mon Sep 17 00:00:00 2001 From: captin411 Date: Tue, 25 Oct 2022 13:10:58 -0700 Subject: improve debug markers, fix algo weighting --- modules/textual_inversion/autocrop.py | 207 +++++++++++++++++++++------------- 1 file changed, 129 insertions(+), 78 deletions(-) (limited to 'modules/textual_inversion/autocrop.py') diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index b2f9241c..caaf18c8 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -1,4 +1,5 @@ import cv2 +import os from collections import defaultdict from math import log, sqrt import numpy as np @@ -26,19 +27,9 @@ def crop_image(im, settings): scale_by = settings.crop_height / im.height im = im.resize((int(im.width * scale_by), int(im.height * scale_by))) + im_debug = im.copy() - if im.width == settings.crop_width and im.height == settings.crop_height: - if settings.annotate_image: - d = ImageDraw.Draw(im) - rect = [0, 0, im.width, im.height] - rect[2] -= 1 - rect[3] -= 1 - d.rectangle(rect, outline=GREEN) - if settings.destop_view_image: - im.show() - return im - - focus = focal_point(im, settings) + focus = focal_point(im_debug, settings) # take the focal point and turn it into crop coordinates that try to center over the focal # point but then get adjusted back into the frame @@ -62,89 +53,143 @@ def crop_image(im, settings): crop = [x1, y1, x2, y2] + results = [] + + results.append(im.crop(tuple(crop))) + if settings.annotate_image: - d = ImageDraw.Draw(im) + d = ImageDraw.Draw(im_debug) rect = list(crop) rect[2] -= 1 rect[3] -= 1 d.rectangle(rect, outline=GREEN) + results.append(im_debug) if settings.destop_view_image: - im.show() + im_debug.show() - return im.crop(tuple(crop)) + return results def focal_point(im, settings): corner_points = image_corner_points(im, settings) entropy_points = image_entropy_points(im, settings) face_points = image_face_points(im, settings) - total_points = len(corner_points) + len(entropy_points) + len(face_points) - - corner_weight = settings.corner_points_weight - entropy_weight = settings.entropy_points_weight - face_weight = settings.face_points_weight - - weight_pref_total = corner_weight + entropy_weight + face_weight - - # weight things pois = [] - if weight_pref_total == 0 or total_points == 0: - return pois - pois.extend( - [ PointOfInterest( p.x, p.y, weight=p.weight * ( (corner_weight/weight_pref_total) / (len(corner_points)/total_points) )) for p in corner_points ] - ) - pois.extend( - [ PointOfInterest( p.x, p.y, weight=p.weight * ( (entropy_weight/weight_pref_total) / (len(entropy_points)/total_points) )) for p in entropy_points ] - ) - pois.extend( - [ PointOfInterest( p.x, p.y, weight=p.weight * ( (face_weight/weight_pref_total) / (len(face_points)/total_points) )) for p in face_points ] - ) + weight_pref_total = 0 + if len(corner_points) > 0: + weight_pref_total += settings.corner_points_weight + if len(entropy_points) > 0: + weight_pref_total += settings.entropy_points_weight + if len(face_points) > 0: + weight_pref_total += settings.face_points_weight + + corner_centroid = None + if len(corner_points) > 0: + corner_centroid = centroid(corner_points) + corner_centroid.weight = settings.corner_points_weight / weight_pref_total + pois.append(corner_centroid) + + entropy_centroid = None + if len(entropy_points) > 0: + entropy_centroid = centroid(entropy_points) + entropy_centroid.weight = settings.entropy_points_weight / weight_pref_total + pois.append(entropy_centroid) + + face_centroid = None + if len(face_points) > 0: + face_centroid = centroid(face_points) + face_centroid.weight = settings.face_points_weight / weight_pref_total + pois.append(face_centroid) average_point = poi_average(pois, settings) if settings.annotate_image: d = ImageDraw.Draw(im) - for f in face_points: - d.rectangle(f.bounding(f.size), outline=RED) - for f in entropy_points: - d.rectangle(f.bounding(30), outline=BLUE) - for poi in pois: - w = max(4, 4 * 0.5 * sqrt(poi.weight)) - d.ellipse(poi.bounding(w), fill=BLUE) - d.ellipse(average_point.bounding(25), outline=GREEN) + max_size = min(im.width, im.height) * 0.07 + if corner_centroid is not None: + color = BLUE + box = corner_centroid.bounding(max_size * corner_centroid.weight) + d.text((box[0], box[1]-15), "Edge: %.02f" % corner_centroid.weight, fill=color) + d.ellipse(box, outline=color) + if len(corner_points) > 1: + for f in corner_points: + d.rectangle(f.bounding(4), outline=color) + if entropy_centroid is not None: + color = "#ff0" + box = entropy_centroid.bounding(max_size * entropy_centroid.weight) + d.text((box[0], box[1]-15), "Entropy: %.02f" % entropy_centroid.weight, fill=color) + d.ellipse(box, outline=color) + if len(entropy_points) > 1: + for f in entropy_points: + d.rectangle(f.bounding(4), outline=color) + if face_centroid is not None: + color = RED + box = face_centroid.bounding(max_size * face_centroid.weight) + d.text((box[0], box[1]-15), "Face: %.02f" % face_centroid.weight, fill=color) + d.ellipse(box, outline=color) + if len(face_points) > 1: + for f in face_points: + d.rectangle(f.bounding(4), outline=color) + + d.ellipse(average_point.bounding(max_size), outline=GREEN) return average_point def image_face_points(im, settings): - np_im = np.array(im) - gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY) - - tries = [ - [ f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01 ], - [ f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05 ] - ] - - for t in tries: - # print(t[0]) - classifier = cv2.CascadeClassifier(t[0]) - minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side - try: - faces = classifier.detectMultiScale(gray, scaleFactor=1.1, - minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE) - except: - continue - - if len(faces) > 0: - rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces] - return [PointOfInterest((r[0] +r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0]-r[2])) for r in rects] + if settings.dnn_model_path is not None: + detector = cv2.FaceDetectorYN.create( + settings.dnn_model_path, + "", + (im.width, im.height), + 0.8, # score threshold + 0.3, # nms threshold + 5000 # keep top k before nms + ) + faces = detector.detect(np.array(im)) + results = [] + if faces[1] is not None: + for face in faces[1]: + x = face[0] + y = face[1] + w = face[2] + h = face[3] + results.append( + PointOfInterest( + int(x + (w * 0.5)), # face focus left/right is center + int(y + (h * 0)), # face focus up/down is close to the top of the head + size = w, + weight = 1/len(faces[1]) + ) + ) + return results + else: + np_im = np.array(im) + gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY) + + tries = [ + [ f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01 ], + [ f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05 ], + [ f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05 ] + ] + for t in tries: + classifier = cv2.CascadeClassifier(t[0]) + minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side + try: + faces = classifier.detectMultiScale(gray, scaleFactor=1.1, + minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE) + except: + continue + + if len(faces) > 0: + rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces] + return [PointOfInterest((r[0] +r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0]-r[2]), weight=1/len(rects)) for r in rects] return [] @@ -161,7 +206,7 @@ def image_corner_points(im, settings): np_im, maxCorners=100, qualityLevel=0.04, - minDistance=min(grayscale.width, grayscale.height)*0.07, + minDistance=min(grayscale.width, grayscale.height)*0.03, useHarrisDetector=False, ) @@ -171,7 +216,7 @@ def image_corner_points(im, settings): focal_points = [] for point in points: x, y = point.ravel() - focal_points.append(PointOfInterest(x, y, size=4)) + focal_points.append(PointOfInterest(x, y, size=4, weight=1/len(points))) return focal_points @@ -205,17 +250,22 @@ def image_entropy_points(im, settings): x_mid = int(crop_best[0] + settings.crop_width/2) y_mid = int(crop_best[1] + settings.crop_height/2) - return [PointOfInterest(x_mid, y_mid, size=25)] + return [PointOfInterest(x_mid, y_mid, size=25, weight=1.0)] def image_entropy(im): # greyscale image entropy - # band = np.asarray(im.convert("L")) - band = np.asarray(im.convert("1"), dtype=np.uint8) + band = np.asarray(im.convert("L")) + # band = np.asarray(im.convert("1"), dtype=np.uint8) hist, _ = np.histogram(band, bins=range(0, 256)) hist = hist[hist > 0] return -np.log2(hist / hist.sum()).sum() +def centroid(pois): + x = [poi.x for poi in pois] + y = [poi.y for poi in pois] + return PointOfInterest(sum(x)/len(pois), sum(y)/len(pois)) + def poi_average(pois, settings): weight = 0.0 @@ -260,11 +310,12 @@ class PointOfInterest: class Settings: - def __init__(self, crop_width=512, crop_height=512, corner_points_weight=0.5, entropy_points_weight=0.5, face_points_weight=0.5, annotate_image=False): + def __init__(self, crop_width=512, crop_height=512, corner_points_weight=0.5, entropy_points_weight=0.5, face_points_weight=0.5, annotate_image=False, dnn_model_path=None): self.crop_width = crop_width self.crop_height = crop_height self.corner_points_weight = corner_points_weight self.entropy_points_weight = entropy_points_weight - self.face_points_weight = entropy_points_weight + self.face_points_weight = face_points_weight self.annotate_image = annotate_image - self.destop_view_image = False \ No newline at end of file + self.destop_view_image = False + self.dnn_model_path = dnn_model_path \ No newline at end of file -- cgit v1.2.3 From 54f0c1482427a5b3f2248b97be55878e742cbcb1 Mon Sep 17 00:00:00 2001 From: captin411 Date: Tue, 25 Oct 2022 16:14:13 -0700 Subject: download better face detection module dynamically --- modules/textual_inversion/autocrop.py | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'modules/textual_inversion/autocrop.py') diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index caaf18c8..01a92b12 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -1,4 +1,5 @@ import cv2 +import requests import os from collections import defaultdict from math import log, sqrt @@ -293,6 +294,25 @@ def is_square(w, h): return w == h +def download_and_cache_models(dirname): + download_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true' + model_file_name = 'face_detection_yunet.onnx' + + if not os.path.exists(dirname): + os.makedirs(dirname) + + cache_file = os.path.join(dirname, model_file_name) + if not os.path.exists(cache_file): + print(f"downloading face detection model from '{download_url}' to '{cache_file}'") + response = requests.get(download_url) + with open(cache_file, "wb") as f: + f.write(response.content) + + if os.path.exists(cache_file): + return cache_file + return None + + class PointOfInterest: def __init__(self, x, y, weight=1.0, size=10): self.x = x -- cgit v1.2.3 From df0c5ea29d7f0c682ac81f184f3e482a6450d018 Mon Sep 17 00:00:00 2001 From: captin411 Date: Tue, 25 Oct 2022 17:06:59 -0700 Subject: update default weights --- modules/textual_inversion/autocrop.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'modules/textual_inversion/autocrop.py') diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index 01a92b12..9859974a 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -71,9 +71,9 @@ def crop_image(im, settings): return results def focal_point(im, settings): - corner_points = image_corner_points(im, settings) - entropy_points = image_entropy_points(im, settings) - face_points = image_face_points(im, settings) + corner_points = image_corner_points(im, settings) if settings.corner_points_weight > 0 else [] + entropy_points = image_entropy_points(im, settings) if settings.entropy_points_weight > 0 else [] + face_points = image_face_points(im, settings) if settings.face_points_weight > 0 else [] pois = [] @@ -144,7 +144,7 @@ def image_face_points(im, settings): settings.dnn_model_path, "", (im.width, im.height), - 0.8, # score threshold + 0.9, # score threshold 0.3, # nms threshold 5000 # keep top k before nms ) @@ -159,7 +159,7 @@ def image_face_points(im, settings): results.append( PointOfInterest( int(x + (w * 0.5)), # face focus left/right is center - int(y + (h * 0)), # face focus up/down is close to the top of the head + int(y + (h * 0.33)), # face focus up/down is close to the top of the head size = w, weight = 1/len(faces[1]) ) @@ -207,7 +207,7 @@ def image_corner_points(im, settings): np_im, maxCorners=100, qualityLevel=0.04, - minDistance=min(grayscale.width, grayscale.height)*0.03, + minDistance=min(grayscale.width, grayscale.height)*0.06, useHarrisDetector=False, ) @@ -256,8 +256,8 @@ def image_entropy_points(im, settings): def image_entropy(im): # greyscale image entropy - band = np.asarray(im.convert("L")) - # band = np.asarray(im.convert("1"), dtype=np.uint8) + # band = np.asarray(im.convert("L")) + band = np.asarray(im.convert("1"), dtype=np.uint8) hist, _ = np.histogram(band, bins=range(0, 256)) hist = hist[hist > 0] return -np.log2(hist / hist.sum()).sum() -- cgit v1.2.3 From 119a945ef7569128eb7d6772468ffc5567c2e161 Mon Sep 17 00:00:00 2001 From: PhytoEpidemic <64293310+PhytoEpidemic@users.noreply.github.com> Date: Fri, 2 Dec 2022 12:16:29 -0600 Subject: Fix divide by 0 error Fix of the edge case 0 weight that occasionally will pop up in some specific situations. This was crashing the script. --- modules/textual_inversion/autocrop.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'modules/textual_inversion/autocrop.py') diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index 9859974a..68e1103c 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -276,8 +276,8 @@ def poi_average(pois, settings): weight += poi.weight x += poi.x * poi.weight y += poi.y * poi.weight - avg_x = round(x / weight) - avg_y = round(y / weight) + avg_x = round(weight and x / weight) + avg_y = round(weight and y / weight) return PointOfInterest(avg_x, avg_y) @@ -338,4 +338,4 @@ class Settings: self.face_points_weight = face_points_weight self.annotate_image = annotate_image self.destop_view_image = False - self.dnn_model_path = dnn_model_path \ No newline at end of file + self.dnn_model_path = dnn_model_path -- cgit v1.2.3