import cv2 as cv import numpy as np import h5py as h5 db = None def init(path): ''' initializes the database, must be called before any use ''' global db db = h5.File(path, 'r') def needs_init(): ''' checks if the database has been initialized ''' if db is None: print('db is none, please use init(path_to_db) first!') return db is None # Extract letter from a bounding box def extract_bb(img, bb): ''' extracts a bounding box/letter from the given image ''' # Get the bounding box rect = cv.minAreaRect(bb.astype(np.float32).transpose()) # will be useful later, map center and size to ints center, size = tuple(map(int, rect[0])), tuple(map(int, rect[1])) # Calculate rotation matrix and rotate the image rot_matrix = cv.getRotationMatrix2D(center, rect[2], 1) rot_img = cv.warpAffine(img, rot_matrix, (img.shape[1], img.shape[0])) # bounding box is now axis aligned, and we can crop it print(size) cropped = cv.getRectSubPix(rot_img, size, center) return cropped def get_img(index): ''' gets image from database ''' if needs_init(): return None names = list(db['data'].keys()) im = names[index] return db['data'][im][:] def get_attrs(index): ''' gets attribute dict from the database ''' if needs_init(): return None names = list(db['data'].keys()) im = names[index] return db['data'][im].attrs def get_avg_color(img, mask): ''' gets avg color from an image that is underneath a mask, img and mask needs to be of same size(in x,y) but img can have any third dimension size it want(usually 3 for rgb or 1 for grayscale) ''' sx, sy, sw = img.shape mx, my = mask.shape if sx != mx or sy != my: print('Image and mask shape doesnt match!') return None avg = np.array(sw, dtype=np.float32) count = 0.0 for x in range(sx): for y in range(sy): m = mas[x, y] avg += img[x, y] * m count += m avg /= count return avg