| | |
|---|
| | | import cv2 |
|---|
| | | import numpy as np |
|---|
| | | import pandas as pd |
|---|
| | | import imagehash as ih |
|---|
| | | import os |
|---|
| | | import sys |
|---|
| | | from operator import itemgetter |
|---|
| | | import math |
|---|
| | | import random |
|---|
| | | from PIL import Image |
|---|
| | | import fetch_data |
|---|
| | | import transform_data |
|---|
| | | |
|---|
| | | card_width = 315 |
|---|
| | | card_height = 440 |
|---|
| | | |
|---|
| | | |
|---|
| | | def calc_image_hashes(card_pool, save_to=None): |
|---|
| | | card_pool['art_hash'] = np.NaN |
|---|
| | | for ind, card_info in card_pool.iterrows(): |
|---|
| | | if ind % 100 == 0: |
|---|
| | | print(ind) |
|---|
| | | img_name = '%s/card_img/png/%s/%s_%s.png' % (transform_data.data_dir, card_info['set'], |
|---|
| | | card_info['collector_number'], |
|---|
| | | fetch_data.get_valid_filename(card_info['name'])) |
|---|
| | | card_img = cv2.imread(img_name) |
|---|
| | | if card_img is None: |
|---|
| | | fetch_data.fetch_card_image(card_info, |
|---|
| | | out_dir='%s/card_img/png/%s' % (transform_data.data_dir, card_info['set'])) |
|---|
| | | card_img = cv2.imread(img_name) |
|---|
| | | if card_img is None: |
|---|
| | | print('WARNING: card %s is not found!' % img_name) |
|---|
| | | img_art = Image.fromarray(card_img[121:580, 63:685]) |
|---|
| | | art_hash = ih.phash(img_art, hash_size=32, highfreq_factor=4) |
|---|
| | | card_pool.at[ind, 'art_hash'] = art_hash |
|---|
| | | img_card = Image.fromarray(card_img) |
|---|
| | | card_hash = ih.phash(img_card, hash_size=32, highfreq_factor=4) |
|---|
| | | card_pool.at[ind, 'card_hash'] = card_hash |
|---|
| | | card_pool = card_pool[['artist', 'border_color', 'collector_number', 'color_identity', 'colors', 'flavor_text', |
|---|
| | | 'image_uris', 'mana_cost', 'legalities', 'name', 'oracle_text', 'rarity', 'type_line', |
|---|
| | | 'set', 'set_name', 'power', 'toughness', 'art_hash', 'card_hash']] |
|---|
| | | if save_to is not None: |
|---|
| | | card_pool.to_pickle(save_to) |
|---|
| | | return card_pool |
|---|
| | | |
|---|
| | | ''' |
|---|
| | | df_list = [] |
|---|
| | | for set_name in fetch_data.all_set_list: |
|---|
| | | csv_name = '%s/csv/%s.csv' % (transform_data.data_dir, set_name) |
|---|
| | | df = fetch_data.load_all_cards_text(csv_name) |
|---|
| | | df_list.append(df) |
|---|
| | | #print(df) |
|---|
| | | card_pool = pd.concat(df_list) |
|---|
| | | card_pool.reset_index(drop=True, inplace=True) |
|---|
| | | card_pool.drop('Unnamed: 0', axis=1, inplace=True, errors='ignore') |
|---|
| | | card_pool = calc_image_hashes(card_pool, save_to='card_pool.pck') |
|---|
| | | ''' |
|---|
| | | #csv_name = '%s/csv/%s.csv' % (transform_data.data_dir, 'rtr') |
|---|
| | | #card_pool = fetch_data.load_all_cards_text(csv_name) |
|---|
| | | #card_pool = calc_image_hashes(card_pool) |
|---|
| | | card_pool = pd.read_pickle('card_pool.pck') |
|---|
| | | |
|---|
| | | |
|---|
| | | # Disclaimer: majority of the basic framework in this file is modified from the following tutorial: |
|---|
| | | # https://www.learnopencv.com/deep-learning-based-object-detection-using-yolov3-with-opencv-python-c/ |
|---|
| | | |
|---|
| | | |
|---|
| | | # www.pyimagesearch.com/2014/08/25/4-point-opencv-getperspective-transform-example/ |
|---|
| | | def order_points(pts): |
|---|
| | | # initialzie a list of coordinates that will be ordered |
|---|
| | | # such that the first entry in the list is the top-left, |
|---|
| | | # the second entry is the top-right, the third is the |
|---|
| | | # bottom-right, and the fourth is the bottom-left |
|---|
| | | rect = np.zeros((4, 2), dtype="float32") |
|---|
| | | |
|---|
| | | # the top-left point will have the smallest sum, whereas |
|---|
| | | # the bottom-right point will have the largest sum |
|---|
| | | s = pts.sum(axis=1) |
|---|
| | | rect[0] = pts[np.argmin(s)] |
|---|
| | | rect[2] = pts[np.argmax(s)] |
|---|
| | | |
|---|
| | | # now, compute the difference between the points, the |
|---|
| | | # top-right point will have the smallest difference, |
|---|
| | | # whereas the bottom-left will have the largest difference |
|---|
| | | diff = np.diff(pts, axis=1) |
|---|
| | | rect[1] = pts[np.argmin(diff)] |
|---|
| | | rect[3] = pts[np.argmax(diff)] |
|---|
| | | |
|---|
| | | # return the ordered coordinates |
|---|
| | | return rect |
|---|
| | | |
|---|
| | | |
|---|
| | | def four_point_transform(image, pts): |
|---|
| | | # obtain a consistent order of the points and unpack them |
|---|
| | | # individually |
|---|
| | | rect = order_points(pts) |
|---|
| | | (tl, tr, br, bl) = rect |
|---|
| | | |
|---|
| | | # compute the width of the new image, which will be the |
|---|
| | | # maximum distance between bottom-right and bottom-left |
|---|
| | | # x-coordiates or the top-right and top-left x-coordinates |
|---|
| | | widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2)) |
|---|
| | | widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2)) |
|---|
| | | maxWidth = max(int(widthA), int(widthB)) |
|---|
| | | |
|---|
| | | # compute the height of the new image, which will be the |
|---|
| | | # maximum distance between the top-right and bottom-right |
|---|
| | | # y-coordinates or the top-left and bottom-left y-coordinates |
|---|
| | | heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2)) |
|---|
| | | heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2)) |
|---|
| | | maxHeight = max(int(heightA), int(heightB)) |
|---|
| | | |
|---|
| | | # now that we have the dimensions of the new image, construct |
|---|
| | | # the set of destination points to obtain a "birds eye view", |
|---|
| | | # (i.e. top-down view) of the image, again specifying points |
|---|
| | | # in the top-left, top-right, bottom-right, and bottom-left |
|---|
| | | # order |
|---|
| | | dst = np.array([ |
|---|
| | | [0, 0], |
|---|
| | | [maxWidth - 1, 0], |
|---|
| | | [maxWidth - 1, maxHeight - 1], |
|---|
| | | [0, maxHeight - 1]], dtype="float32") |
|---|
| | | |
|---|
| | | # compute the perspective transform matrix and then apply it |
|---|
| | | M = cv2.getPerspectiveTransform(rect, dst) |
|---|
| | | warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight)) |
|---|
| | | |
|---|
| | | # If the image is horizontally long, rotate it by 90 |
|---|
| | | if maxWidth > maxHeight: |
|---|
| | | center = (maxHeight / 2, maxHeight / 2) |
|---|
| | | M_rot = cv2.getRotationMatrix2D(center, 270, 1.0) |
|---|
| | | warped = cv2.warpAffine(warped, M_rot, (maxHeight, maxWidth)) |
|---|
| | | |
|---|
| | | # return the warped image |
|---|
| | | return warped |
|---|
| | | |
|---|
| | | |
|---|
| | | # Get the names of the output layers |
|---|
| | | def get_outputs_names(net): |
|---|
| | | # Get the names of all the layers in the network |
|---|
| | |
|---|
| | | frame_height = frame.shape[0] |
|---|
| | | frame_width = frame.shape[1] |
|---|
| | | |
|---|
| | | |
|---|
| | | # Scan through all the bounding boxes output from the network and keep only the |
|---|
| | | # ones with high confidence scores. Assign the box's class label as the class with the highest score. |
|---|
| | | class_ids = [] |
|---|
| | |
|---|
| | | |
|---|
| | | |
|---|
| | | def remove_glare(img): |
|---|
| | | """ |
|---|
| | | Inspired from: |
|---|
| | | http://www.amphident.de/en/blog/preprocessing-for-automatic-pattern-identification-in-wildlife-removing-glare.html |
|---|
| | | The idea is to find area that has low saturation but high value, which is what a glare usually look like. |
|---|
| | | """ |
|---|
| | | img_hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV) |
|---|
| | | _, s, v = cv2.split(img_hsv) |
|---|
| | | non_sat = (s < 32) * 255 # Find all pixels that are not very saturated |
|---|
| | |
|---|
| | | # Set all brightness values, where the pixels are still saturated to 0. |
|---|
| | | v[non_sat == 0] = 0 |
|---|
| | | # filter out very bright pixels. |
|---|
| | | glare = (v > 240) * 255 |
|---|
| | | glare = (v > 200) * 255 |
|---|
| | | |
|---|
| | | # Slightly increase the area for each pixel |
|---|
| | | glare = cv2.dilate(glare.astype(np.uint8), disk) |
|---|
| | | #glare = cv2.dilate(glare.astype(np.uint8), disk); |
|---|
| | | |
|---|
| | | #corrected = cv2.inpaint(img, glare, 7, cv2.INPAINT_TELEA) |
|---|
| | | glare_reduced = np.ones((img.shape[0], img.shape[1], 3), dtype=np.uint8) * 200 |
|---|
| | | glare = cv2.cvtColor(glare, cv2.COLOR_GRAY2BGR) |
|---|
| | | corrected = np.where(glare, glare_reduced, img) |
|---|
| | | return corrected |
|---|
| | | |
|---|
| | | |
|---|
| | | def find_card(img, thresh_c=5, kernel_size=(3, 3), size_ratio=0.3): |
|---|
| | | # Typical pre-processing - grayscale, blurring, thresholding |
|---|
| | | img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) |
|---|
| | | img_blur = cv2.medianBlur(img_gray, 5) |
|---|
| | | img_thresh = cv2.adaptiveThreshold(img_blur, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 5, thresh_c) |
|---|
| | | |
|---|
| | | # Dilute the image, then erode them to remove minor noises |
|---|
| | | kernel = np.ones(kernel_size, np.uint8) |
|---|
| | | img_dilate = cv2.dilate(img_thresh, kernel, iterations=1) |
|---|
| | | img_erode = cv2.erode(img_dilate, kernel, iterations=1) |
|---|
| | | |
|---|
| | | # Find the contour |
|---|
| | | #img_contour = img_erode.copy() |
|---|
| | | _, cnts, hier = cv2.findContours(img_erode, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) |
|---|
| | | if len(cnts) == 0: |
|---|
| | | print('no contours') |
|---|
| | | return [] |
|---|
| | | #img_contour = cv2.cvtColor(img_contour, cv2.COLOR_GRAY2BGR) |
|---|
| | | #img_contour = cv2.drawContours(img_contour, cnts, -1, (0, 255, 0), 1) |
|---|
| | | #cv2.imshow('test', img_contour) |
|---|
| | | |
|---|
| | | # For each contours detected, check if they are large enough and are rectangle |
|---|
| | | cnts_rect = [] |
|---|
| | | ind_sort = sorted(range(len(cnts)), key=lambda i: cv2.contourArea(cnts[i]), reverse=True) |
|---|
| | | for i in range(len(cnts)): |
|---|
| | | size = cv2.contourArea(cnts[ind_sort[i]]) |
|---|
| | | peri = cv2.arcLength(cnts[ind_sort[i]], True) |
|---|
| | | approx = cv2.approxPolyDP(cnts[ind_sort[i]], 0.04 * peri, True) |
|---|
| | | if size > img.shape[0] * img.shape[1] * size_ratio and len(approx) == 4: |
|---|
| | | cnts_rect.append(approx) |
|---|
| | | |
|---|
| | | return cnts_rect |
|---|
| | | |
|---|
| | | |
|---|
| | | def detect_frame(net, classes, img, thresh_conf=0.5, thresh_nms=0.4, in_dim=(416, 416), display=True, out_path=None): |
|---|
| | | img_copy = img.copy() |
|---|
| | | # Create a 4D blob from a frame. |
|---|
| | |
|---|
| | | if out_path is not None: |
|---|
| | | cv2.imwrite(out_path, img.astype(np.uint8)) |
|---|
| | | if display: |
|---|
| | | no_glare = remove_glare(img_copy) |
|---|
| | | img_concat = np.concatenate((img, no_glare), axis=1) |
|---|
| | | cv2.imshow('result', img_concat) |
|---|
| | | |
|---|
| | | #no_glare = remove_glare(img_copy) |
|---|
| | | #img_concat = np.concatenate((img, no_glare), axis=1) |
|---|
| | | cv2.imshow('result', img) |
|---|
| | | ''' |
|---|
| | | for i in range(len(obj_list)): |
|---|
| | | class_id, confidence, box = obj_list[i] |
|---|
| | | left, top, width, height = box |
|---|
| | | img_snip = img[max(0, top):min(img.shape[0], top + height), max(0, left):min(img.shape[1], left + width)] |
|---|
| | | #cv2.imshow('feature#%d' % i, img_snip) |
|---|
| | | img_hsv = cv2.cvtColor(img_snip, cv2.COLOR_BGR2HSV) |
|---|
| | | h, s, v = cv2.split(img_hsv) |
|---|
| | | #h = cv2.cvtColor(h, cv2.COLOR_GRAY2BGR) |
|---|
| | | s = cv2.cvtColor(s, cv2.COLOR_GRAY2BGR) |
|---|
| | | v = cv2.cvtColor(v, cv2.COLOR_GRAY2BGR) |
|---|
| | | img_concat = np.concatenate((img_snip, s, v), axis=1) |
|---|
| | | cv2.imshow('feature#%d - hsv' % i, img_concat) |
|---|
| | | img_snip = img_copy[max(0, top):min(img.shape[0], top + height), |
|---|
| | | max(0, left):min(img.shape[1], left + width)] |
|---|
| | | img_thresh, img_dilate, img_canny, img_hough = find_card(img_snip) |
|---|
| | | img_concat = np.concatenate((img_snip, img_thresh, img_dilate, img_canny, img_hough), axis=1) |
|---|
| | | cv2.imshow('feature#%d' % i, img_concat) |
|---|
| | | ''' |
|---|
| | | cv2.waitKey(0) |
|---|
| | | cv2.destroyAllWindows() |
|---|
| | |
|---|
| | | img = frame.copy() |
|---|
| | | obj_list = detect_frame(net, classes, frame, thresh_conf=thresh_conf, thresh_nms=thresh_nms, in_dim=in_dim, |
|---|
| | | display=False, out_path=None) |
|---|
| | | #cnts_rect = find_card(img) |
|---|
| | | max_num_obj = max(max_num_obj, len(obj_list)) |
|---|
| | | if display: |
|---|
| | | no_glare = remove_glare(img) |
|---|
| | | img_concat = np.concatenate((frame, no_glare), axis=1) |
|---|
| | | cv2.imshow('result', img_concat) |
|---|
| | | ''' |
|---|
| | | img_result = frame.copy() |
|---|
| | | #img_result = cv2.drawContours(img_result, cnts_rect, -1, (0, 255, 0), 2) |
|---|
| | | #for i in range(len(cnts_rect)): |
|---|
| | | # pts = np.float32([p[0] for p in cnts_rect[i]]) |
|---|
| | | # img_warp = four_point_transform(img, pts) |
|---|
| | | # cv2.imshow('card#%d' % i, img_warp) |
|---|
| | | #for i in range(len(cnts_rect), max_num_obj): |
|---|
| | | # cv2.imshow('card#%d' % i, np.zeros((1, 1), dtype=np.uint8)) |
|---|
| | | #no_glare = remove_glare(img) |
|---|
| | | #img_thresh, img_erode, img_contour = find_card(no_glare) |
|---|
| | | #img_concat = np.concatenate((no_glare, img_contour), axis=1) |
|---|
| | | |
|---|
| | | for i in range(len(obj_list)): |
|---|
| | | class_id, confidence, box = obj_list[i] |
|---|
| | | left, top, width, height = box |
|---|
| | | img_snip = img[max(0, top):min(img.shape[0], top + height), |
|---|
| | | max(0, left):min(img.shape[1], left + width)] |
|---|
| | | # cv2.imshow('feature#%d' % i, img_snip) |
|---|
| | | img_hsv = cv2.cvtColor(img_snip, cv2.COLOR_BGR2HSV) |
|---|
| | | h, s, v = cv2.split(img_hsv) |
|---|
| | | # h = cv2.cvtColor(h, cv2.COLOR_GRAY2BGR) |
|---|
| | | s = cv2.cvtColor(s, cv2.COLOR_GRAY2BGR) |
|---|
| | | v = cv2.cvtColor(v, cv2.COLOR_GRAY2BGR) |
|---|
| | | img_concat = np.concatenate((img_snip, s, v), axis=1) |
|---|
| | | cv2.imshow('feature#%d - hsv' % i, img_concat) |
|---|
| | | offset_ratio = 0.1 |
|---|
| | | x1 = max(0, int(left - offset_ratio * width)) |
|---|
| | | x2 = min(img.shape[1], int(left + (1 + offset_ratio) * width)) |
|---|
| | | y1 = max(0, int(top - offset_ratio * height)) |
|---|
| | | y2 = min(img.shape[0], int(top + (1 + offset_ratio) * height)) |
|---|
| | | img_snip = img[y1:y2, x1:x2] |
|---|
| | | cnts = find_card(img_snip) |
|---|
| | | if len(cnts) > 0: |
|---|
| | | cnt = cnts[-1] |
|---|
| | | pts = np.float32([p[0] for p in cnt]) |
|---|
| | | img_warp = four_point_transform(img_snip, pts) |
|---|
| | | img_warp = cv2.resize(img_warp, (card_width, card_height)) |
|---|
| | | ''' |
|---|
| | | img_art = img_warp[47:249, 22:294] |
|---|
| | | img_art = Image.fromarray(img_art.astype('uint8'), 'RGB') |
|---|
| | | art_hash = ih.phash(img_art, hash_size=32, highfreq_factor=4) |
|---|
| | | card_pool['hash_diff'] = card_pool['art_hash'] - art_hash |
|---|
| | | min_cards = card_pool[card_pool['hash_diff'] == min(card_pool['hash_diff'])] |
|---|
| | | guttersnipe = card_pool[card_pool['name'] == 'Cyclonic Rift'] |
|---|
| | | diff = guttersnipe['art_hash'] - art_hash |
|---|
| | | print(diff) |
|---|
| | | card_name = min_cards.iloc[0]['name'] |
|---|
| | | #print(min_cards.iloc[0]['name'], min_cards.iloc[0]['hash_diff']) |
|---|
| | | ''' |
|---|
| | | img_card = Image.fromarray(img_warp.astype('uint8'), 'RGB') |
|---|
| | | card_hash = ih.phash(img_card, hash_size=32, highfreq_factor=4) |
|---|
| | | card_pool['hash_diff'] = card_pool['card_hash'] - card_hash |
|---|
| | | min_cards = card_pool[card_pool['hash_diff'] == min(card_pool['hash_diff'])] |
|---|
| | | card_name = min_cards.iloc[0]['name'] |
|---|
| | | hash_diff = min_cards.iloc[0]['hash_diff'] |
|---|
| | | #guttersnipe = card_pool[card_pool['name'] == 'Cyclonic Rift'] |
|---|
| | | #diff = guttersnipe['card_hash'] - card_hash |
|---|
| | | #print(diff) |
|---|
| | | #img_thresh, img_dilate, img_contour = find_card(img_snip) |
|---|
| | | #img_concat = np.concatenate((img_snip, img_contour), axis=1) |
|---|
| | | cv2.rectangle(img_warp, (22, 47), (294, 249), (0, 255, 0), 2) |
|---|
| | | cv2.putText(img_warp, card_name + ', ' + str(hash_diff), (0, 50), |
|---|
| | | cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2) |
|---|
| | | cv2.imshow('card#%d' % i, img_warp) |
|---|
| | | else: |
|---|
| | | cv2.imshow('card#%d' % i, np.zeros((1, 1), dtype=np.uint8)) |
|---|
| | | for i in range(len(obj_list), max_num_obj): |
|---|
| | | cv2.imshow('feature#%d - hsv' % i, np.zeros((1, 1), dtype=np.uint8)) |
|---|
| | | ''' |
|---|
| | | cv2.imshow('card#%d' % i, np.zeros((1, 1), dtype=np.uint8)) |
|---|
| | | cv2.imshow('result', img_result) |
|---|
| | | #if len(obj_list) > 0: |
|---|
| | | #cv2.waitKey(0) |
|---|
| | | # cv2.waitKey(0) |
|---|
| | | |
|---|
| | | |
|---|
| | | if out_path is not None: |
|---|
| | | vid_writer.write(frame.astype(np.uint8)) |
|---|
| | | cv2.waitKey(1) |
|---|
| | |
|---|
| | | |
|---|
| | | def main(): |
|---|
| | | # Specify paths for all necessary files |
|---|
| | | test_path = os.path.abspath('../data/test18.jpg') |
|---|
| | | test_path = os.path.abspath('test_file/test4.mp4') |
|---|
| | | #weight_path = 'backup/tiny_yolo_10_39500.weights' |
|---|
| | | #cfg_path = 'cfg/tiny_yolo_10.cfg' |
|---|
| | | #class_path = "data/obj_10.names" |
|---|
| | | weight_path = 'weights/second_general/tiny_yolo_final.weights' |
|---|
| | | cfg_path = 'cfg/tiny_yolo.cfg' |
|---|
| | | class_path = "data/obj.names" |
|---|
| | | class_path = 'data/obj.names' |
|---|
| | | out_dir = 'out' |
|---|
| | | if not os.path.isfile(test_path): |
|---|
| | | print('The test file %s doesn\'t exist!' % os.path.abspath(test_path)) |
|---|
| | |
|---|
| | | print('The class file %s doesn\'t exist!' % os.path.abspath(test_path)) |
|---|
| | | return |
|---|
| | | |
|---|
| | | thresh_conf = 0.01 |
|---|
| | | thresh_nms = 0.8 |
|---|
| | | |
|---|
| | | # Setup |
|---|
| | | # Read class names from text file |
|---|
| | | with open(class_path, 'r') as f: |
|---|
| | |
|---|
| | | |
|---|
| | | if test_ext in ['jpg', 'jpeg', 'bmp', 'png', 'tiff']: |
|---|
| | | img = cv2.imread(test_path) |
|---|
| | | detect_frame(net, classes, img, out_path=out_path) |
|---|
| | | detect_frame(net, classes, img, out_path=out_path, thresh_conf=thresh_conf, thresh_nms=thresh_nms) |
|---|
| | | else: |
|---|
| | | capture = cv2.VideoCapture(test_path) |
|---|
| | | detect_video(net, classes, capture, out_path=out_path) |
|---|
| | | capture = cv2.VideoCapture(0) |
|---|
| | | detect_video(net, classes, capture, out_path=out_path, thresh_conf=thresh_conf, thresh_nms=thresh_nms) |
|---|
| | | capture.release() |
|---|
| | | pass |
|---|
| | | |
|---|
