From 73b7c780abc9cccab32d391e0d835c4d13199412 Mon Sep 17 00:00:00 2001 From: vahidrezanezhad Date: Tue, 9 Mar 2021 08:20:33 -0500 Subject: [PATCH] Update eynollah.py reading order bug for documents with text regions less than 5: fixed --- qurator/eynollah/eynollah.py | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/qurator/eynollah/eynollah.py b/qurator/eynollah/eynollah.py index cb5b028..f8d8e9f 100644 --- a/qurator/eynollah/eynollah.py +++ b/qurator/eynollah/eynollah.py @@ -1672,10 +1672,17 @@ class Eynollah: cx_bigest_d_big, cy_biggest_d_big, _, _, _, _, _ = find_new_features_of_contours([contours_biggest_d]) cx_bigest_d, cy_biggest_d, _, _, _, _, _ = find_new_features_of_contours(contours_only_text_parent_d) try: - cx_bigest_d_last5 = cx_bigest_d[-5:] - cy_biggest_d_last5 = cy_biggest_d[-5:] - dists_d = [math.sqrt((cx_bigest_big[0] - cx_bigest_d_last5[j]) ** 2 + (cy_biggest_big[0] - cy_biggest_d_last5[j]) ** 2) for j in range(len(cy_biggest_d_last5))] - ind_largest = len(cx_bigest_d) -5 + np.argmin(dists_d) + if len(cx_bigest_d) >= 5: + cx_bigest_d_last5 = cx_bigest_d[-5:] + cy_biggest_d_last5 = cy_biggest_d[-5:] + dists_d = [math.sqrt((cx_bigest_big[0] - cx_bigest_d_last5[j]) ** 2 + (cy_biggest_big[0] - cy_biggest_d_last5[j]) ** 2) for j in range(len(cy_biggest_d_last5))] + ind_largest = len(cx_bigest_d) -5 + np.argmin(dists_d) + else: + cx_bigest_d_last5 = cx_bigest_d[-len(cx_bigest_d):] + cy_biggest_d_last5 = cy_biggest_d[-len(cx_bigest_d):] + dists_d = [math.sqrt((cx_bigest_big[0]-cx_bigest_d_last5[j])**2 + (cy_biggest_big[0]-cy_biggest_d_last5[j])**2) for j in range(len(cy_biggest_d_last5))] + ind_largest = len(cx_bigest_d) - len(cx_bigest_d) + np.argmin(dists_d) + cx_bigest_d_big[0] = cx_bigest_d[ind_largest] cy_biggest_d_big[0] = cy_biggest_d[ind_largest] except Exception as why: