Created
March 30, 2018 18:23
-
-
Save the-invisible-man/3319edde306d30aab16a7ac437ce1595 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import cv2 | |
| import pytesseract | |
| import numpy as np | |
| from pprint import pprint | |
| from PIL import Image | |
| img = cv2.imread('/Users/cgranados/Code/terravision/img/floor.png') | |
| grey = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) | |
| hsv = img | |
| thresh_map = [ | |
| { | |
| 'name': 'Kitchen', | |
| 'colors': {'low': [95, 199, 212], 'high': [115, 219, 292]}, | |
| 'max_area': 0 | |
| }, | |
| { | |
| 'name': 'AV Room', | |
| 'colors': {'low': [], 'high': []}, | |
| 'max_area': 0 | |
| }, | |
| { | |
| 'name': 'Restroom', | |
| 'colors': {'low': [], 'high': []}, | |
| 'max_area': 0 | |
| }, | |
| { | |
| 'name': 'Private Office', | |
| 'colors': {'low': [], 'high': []}, | |
| 'max_area': 0 | |
| } | |
| ] | |
| # HSV value 42, 58, 100 | |
| # Declare lower bound and upper bound for color | |
| lower_bound = np.array(thresh_map[0]['colors']['low']) | |
| upper_bound = np.array(thresh_map[0]['colors']['high']) | |
| # lower_bound = np.array([245, 245, 197]) | |
| # upper_bound = np.array([265, 265, 277]) | |
| # Create mask with pixels found in range of upper and lower bound | |
| mask = cv2.inRange(hsv, lower_bound, upper_bound) | |
| # If area of interest if larger than we expect de-noise with erosion. | |
| kernel = np.ones((11, 11), np.uint8) | |
| erosion = cv2.erode(mask, kernel, iterations=1) | |
| # Dilate to so we can recover the area on the larger image | |
| kernel = np.ones((8, 8), np.uint8) | |
| dilation = cv2.dilate(erosion, kernel, iterations=2) | |
| # kernel = np.ones((1, 9), np.uint8) | |
| # dilation = cv2.dilate(dilation, kernel, iterations=1) | |
| # res = cv2.bitwise_and(img, img, mask=dilation) | |
| # | |
| # cv2.imshow('res', res) | |
| # | |
| # cv2.waitKey(0) | |
| ret, thresh = cv2.threshold(grey, 127, 255, 0) | |
| _, contours, hierarchy = cv2.findContours(dilation, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) | |
| cnt = contours[0] | |
| x, y, w, h = cv2.boundingRect(cnt) | |
| crop = img[y:y+h, x:x+w] | |
| cv2.imshow('original', img) | |
| cv2.waitKey(0) | |
| cv2.imshow('dialated', dilation) | |
| cv2.waitKey(0) | |
| cv2.imshow("final", crop) | |
| cv2.waitKey(0) | |
| test_mask = cv2.inRange(crop, np.array([50, 50, 50]), np.array([130, 130, 130])) | |
| cv2.imshow('masked text', test_mask) | |
| cv2.waitKey(0) | |
| cv2.destroyAllWindows() | |
| r = "/Users/cgranados/Code/terravision/img/floor_extracted.png" | |
| cv2.imwrite(r, crop) | |
| text = pytesseract.image_to_string(Image.open(r)) | |
| print "text found:" + text | |
| cv2.destroyAllWindows() | |
| exit() | |
| cnt = contours[0] | |
| M = cv2.moments(cnt) | |
| height, width, channels = img.shape | |
| new_mask = np.zeros((height, width), np.uint8) | |
| points = np.array(contours) | |
| # cv2.fillPoly(new_mask, pts=np.int32([points]), color=(255, 255, 255)) | |
| for c in contours: | |
| # Find the minimum bounding box without accounting for orientation | |
| x, y, w, h = cv2.boundingRect(c) | |
| # Draw rectangle on binary mask | |
| cv2.rectangle(new_mask, (x, y), (x+w, y+h), (255, 255, 255), -1) | |
| # box = [[(x, y), (x + w, y + h)] for x, y, w, h in cv2.boundingRect(c)] | |
| # Isolate area of interest with mask | |
| res = cv2.bitwise_and(img, img, mask=new_mask) | |
| cv2.imshow('res', res) | |
| crop = img[y:y+h,x:x+w] | |
| cv2.waitKey(0) | |
| # cv2.drawContours(new_mask, box, ) | |
| # epsilon = 10 * cv2.arcLength(cnt, True) | |
| # approx = cv2.approxPolyDP(cnt, epsilon, True) | |
| # | |
| # hull = cv2.convexHull(cnt) | |
| # | |
| # pprint(hull) | |
| # | |
| # pprint(cnt) | |
| # | |
| # exit(0) | |
| # cv2.drawContours(img, [hull], 0, (0, 255, 0), 3) | |
| # | |
| # cv2.imshow('draw', img) | |
| # | |
| # cv2.waitKey(0) | |
| # | |
| # cv2.destroyAllWindows() | |
| cv2.imshow('original', img) | |
| cv2.waitKey(0) | |
| # | |
| # cv2.imshow('found', mask) | |
| # | |
| # cv2.waitKey(0) | |
| # | |
| # cv2.imshow('eroded', erosion) | |
| # | |
| # cv2.waitKey(0) | |
| # | |
| cv2.imshow('dialated', dilation) | |
| cv2.waitKey(0) | |
| cv2.imshow("new mask", new_mask) | |
| cv2.waitKey(0) | |
| cv2.destroyAllWindows() | |
| # remove the background | |
| # def remove_background(matrix, color, treshhold, exact=False): | |
| # ''' | |
| # Slow as a dog but acceptable for now. Runs at a X*Y complexity. | |
| # :param matrix: | |
| # :return: matrix | |
| # ''' | |
| # for y in matrix: | |
| # for x in y: | |
| # if x >= | |
| # Algorithm | |
| # Declare lower bound and upper bound for color | |
| # Create mask with pixels found in range of upper and lower bound, returns bitwise | |
| # If area of interest if larger than we expect de-noise with erosion. | |
| # Dilate to so we can recover the area on the larger image | |
| # Find contours in the shape | |
| # Get convex hull to simplify into square | |
| # Use result (contours) to draw a new square binary image | |
| # Use binary image as mask on the original image, we now have the isolated room | |
| # Get it's coordinates on a 2D plane. | |
| # Find the shape's midpoint coordinate. (this is part of the info we want to return) | |
| # Crop out all black from the image so we only have the room in the matrix (and we deal with a smaller matrix) | |
| # Perform optical character recognition on isolated room image. | |
| # Refine OCR because it won't be perfect: | |
| # - Iterate through space delimited tokens and try for exact matches against a dictionary of expected words. | |
| # - If no exact match then use trie data structure with indexed rooms for characters until we find a match. | |
| # Each time starting from the next character if no match found. | |
| # | |
| # Output: | |
| # - Coordinates of hull (square that surrounds the room) in 2D space, coordinates | |
| # - Coordinate of midpoint in 2D space. | |
| # OCR refining algorithm. | |
| # grab token and see if it's exact match. | |
| # otherwise use trie structure and grab stream from start to end. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment