| commit | author | age | ||
| 9efc18 | 1 | import cv2 |
| SP | 2 | import numpy as np |
| 762a5e | 3 | from skimage import morphology, img_as_ubyte |
| 02e0f7 | 4 | from sklearn import svm |
| SP | 5 | from sklearn.externals import joblib |
| 6 | ||
| 9efc18 | 7 | |
| SP | 8 | """ |
| 9 | (1) The text is an array of chars (in row-major order) where | |
| 10 | * each char can be one of the following: | |
| 11 | * 'x': hit | |
| 12 | * 'o': miss | |
| 13 | * ' ': don't-care | |
| 14 | * (2) When the origin falls on a hit or miss, use an upper case | |
| 15 | * char (e.g., 'X' or 'O') to indicate it. When the origin | |
| 16 | * falls on a don't-care, indicate this with a 'C'. | |
| 17 | * The string must have exactly one origin specified. | |
| 18 | * (3) The advantage of this method is that the text can be input | |
| 19 | * in a format that shows the 2D layout of the Sel; e.g., | |
| 20 | ||
| 21 | ||
| 22 | :::: AND :::: | |
| 23 | ||
| 24 | ||
| 25 | (10) The sequence string is formatted as follows: | |
| 26 | * ~ An arbitrary number of operations, each separated | |
| 27 | * by a '+' character. White space is ignored. | |
| 28 | * ~ Each operation begins with a case-independent character | |
| 29 | * specifying the operation: | |
| 30 | * d or D (dilation) | |
| 31 | * e or E (erosion) | |
| 32 | * o or O (opening) | |
| 33 | * c or C (closing) | |
| 34 | * r or R (rank binary reduction) | |
| 35 | * x or X (replicative binary expansion) | |
| 36 | * b or B (add a border of 0 pixels of this size) | |
| 37 | * ~ The args to the morphological operations are bricks of hits, | |
| 38 | * and are formatted as a.b, where a and b are horizontal and | |
| 39 | * vertical dimensions, rsp. | |
| 40 | * ~ The args to the reduction are a sequence of up to 4 integers, | |
| 41 | * each from 1 to 4. | |
| 42 | * ~ The arg to the expansion is a power of two, in the set | |
| 43 | * {2, 4, 8, 16}. | |
| 44 | * (11) An example valid sequence is: | |
| 45 | * "b32 + o1.3 + C3.1 + r23 + e2.2 + D3.2 + X4" | |
| 46 | * In this example, the following operation sequence is carried out: | |
| 47 | * * b32: Add a 32 pixel border around the input image | |
| 48 | * * o1.3: Opening with vert sel of length 3 (e.g., 1 x 3) | |
| 49 | * * C3.1: Closing with horiz sel of length 3 (e.g., 3 x 1) | |
| 50 | * * r23: Two successive 2x2 reductions with rank 2 in the first | |
| 51 | * and rank 3 in the second. The result is a 4x reduced pix. | |
| 52 | * * e2.2: Erosion with a 2x2 sel (origin will be at x,y: 0,0) | |
| 53 | * * d3.2: Dilation with a 3x2 sel (origin will be at x,y: 1,0) | |
| 54 | * * X4: 4x replicative expansion, back to original resolution | |
| 55 | ||
| 56 | """ | |
| 57 | ||
| 58 | ||
| 59 | def kernel(x, y): | |
| 60 | return np.ones((x, y), np.uint8) | |
| 61 | ||
| 62 | ||
| 762a5e | 63 | def segment_by_contours(image, sorted_ctrs, classifier): |
| SP | 64 | sid_no = "" |
| 65 | for i, ctr in enumerate(sorted_ctrs): | |
| 66 | # Get bounding box | |
| 67 | x, y, w, h = cv2.boundingRect(ctr) | |
| 68 | # Getting ROI | |
| 69 | if w < h / 2: | |
| 70 | sid_no = sid_no + "1" | |
| 71 | continue | |
| 72 | roi = image[y : y + h, x : x + w] | |
| 73 | roi = img_as_ubyte(roi < 128) | |
| 74 | roi = cv2.resize(roi, (32, 32)) | |
| 75 | ||
| 76 | # cv2.rectangle(image,(x,y),( x + w, y + h ),(0,255,0),2) | |
| 77 | cv2.imwrite("sid_no_{}.png".format(i), roi) | |
| 78 | sid_no = sid_no + str(classifier.predict(roi.reshape(1, -1) / 255.0)[0]) | |
| 79 | return sid_no | |
| 80 | ||
| 81 | ||
| 82 | def getSID(image, classifier, sid_mask): | |
| 83 | image = 255 - image | |
| 84 | image = img_as_ubyte(image > 100) | |
| 9efc18 | 85 | cv2.imwrite("enSID0.png", image) |
| SP | 86 | # Remove noise |
| 762a5e | 87 | image = cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel(2, 2), iterations=1) |
| 9efc18 | 88 | # Closing. Connect non connected parts |
| 02e0f7 | 89 | image = cv2.morphologyEx(image, cv2.MORPH_CLOSE, kernel(5, 3), iterations=4) |
| 9efc18 | 90 | # Again noise removal after closing |
| 02e0f7 | 91 | |
| 762a5e | 92 | image = cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel(8, 8), iterations=1) |
| 9efc18 | 93 | # Skeletonization |
| 762a5e | 94 | image = img_as_ubyte(morphology.thin(image > 128)) |
| SP | 95 | cv2.imwrite("enSID1.png", image) |
| 9efc18 | 96 | # Stub removal (might not be necessary if thinning instead of skeletonize is used above |
| SP | 97 | # Making lines stronger |
| 98 | image = cv2.morphologyEx(image, cv2.MORPH_DILATE, kernel(5, 5), iterations=1) | |
| 99 | ||
| 100 | image = cv2.morphologyEx(image, cv2.MORPH_CLOSE, kernel(10, 10)) | |
| 101 | # Thining again | |
| 762a5e | 102 | image = img_as_ubyte(morphology.skeletonize(image > 0.5)) |
| 9efc18 | 103 | image = cv2.morphologyEx(image, cv2.MORPH_DILATE, kernel(10, 10)) |
| 02e0f7 | 104 | |
| 762a5e | 105 | im2, ctrs, hier = cv2.findContours( |
| SP | 106 | image.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE |
| 107 | ) | |
| 02e0f7 | 108 | sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0]) |
| SP | 109 | |
| 762a5e | 110 | sid_no = "" |
| SP | 111 | sid_len = 0 |
| 112 | if sid_mask is not None: | |
| 113 | if len(sid_mask)==len(sorted_ctrs): | |
| 114 | sid_no=segment_by_contours(image,sorted_ctrs,classifier) | |
| 115 | else: | |
| 116 | print("Ooops have to find another way") | |
| 02e0f7 | 117 | print(sid_no) |
| 762a5e | 118 | return sid_no |
