diff --git a/camelot/utils.py b/camelot/utils.py
index 3e8ab96..2126fbb 100644
--- a/camelot/utils.py
+++ b/camelot/utils.py
@@ -353,7 +353,7 @@ def text_in_bbox(bbox, text):
     Returns
     -------
     t_bbox : list
-        List of PDFMiner text objects that lie inside table.
+        List of PDFMiner text objects that lie inside table, discarding the overlapping ones
 
     """
     lb = (bbox[0], bbox[1])
@@ -364,7 +364,97 @@ def text_in_bbox(bbox, text):
         if lb[0] - 2 <= (t.x0 + t.x1) / 2.0 <= rt[0] + 2
         and lb[1] - 2 <= (t.y0 + t.y1) / 2.0 <= rt[1] + 2
     ]
-    return t_bbox
+
+    # Avoid duplicate text by discarding overlapping boxes
+    rest = {t for t in t_bbox}
+    for ba in t_bbox:
+        for bb in rest.copy():
+            if ba == bb:
+                continue
+            if bbox_intersect(ba, bb):
+                # if the intersection is larger than 80% of ba's size, we keep the longest
+                if (bbox_intersection_area(ba, bb) / bbox_area(ba)) > 0.8:
+                    if bbox_longer(bb, ba):
+                        rest.discard(ba)
+    unique_boxes = list(rest)
+
+    return unique_boxes
+
+
+def bbox_intersection_area(ba, bb) -> float:
+    """Returns area of the intersection of the bounding boxes of two PDFMiner objects.
+
+    Parameters
+    ----------
+    ba : PDFMiner text object
+    bb : PDFMiner text object
+
+    Returns
+    -------
+    intersection_area : float
+        Area of the intersection of the bounding boxes of both objects
+
+    """
+    x_left = max(ba.x0, bb.x0)
+    y_top = min(ba.y1, bb.y1)
+    x_right = min(ba.x1, bb.x1)
+    y_bottom = max(ba.y0, bb.y0)
+
+    if x_right < x_left or y_bottom > y_top:
+        return 0.0
+
+    intersection_area = (x_right - x_left) * (y_top - y_bottom)
+    return intersection_area
+
+
+def bbox_area(bb) -> float:
+    """Returns area of the bounding box of a PDFMiner object.
+
+    Parameters
+    ----------
+    bb : PDFMiner text object
+
+    Returns
+    -------
+    area : float
+        Area of the bounding box of the object
+
+    """
+    return (bb.x1 - bb.x0) * (bb.y1 - bb.y0)
+
+
+def bbox_intersect(ba, bb) -> bool:
+    """Returns True if the bounding boxes of two PDFMiner objects intersect.
+
+    Parameters
+    ----------
+    ba : PDFMiner text object
+    bb : PDFMiner text object
+
+    Returns
+    -------
+    overlaps : bool
+        True if the bounding boxes intersect
+
+    """
+    return ba.x1 >= bb.x0 and bb.x1 >= ba.x0 and ba.y1 >= bb.y0 and bb.y1 >= ba.y0
+
+
+def bbox_longer(ba, bb) -> bool:
+    """Returns True if the bounding box of the first PDFMiner object is longer or equal to the second.
+
+    Parameters
+    ----------
+    ba : PDFMiner text object
+    bb : PDFMiner text object
+
+    Returns
+    -------
+    longer : bool
+        True if the bounding box of the first object is longer or equal
+
+    """
+    return (ba.x1 - ba.x0) >= (bb.x1 - bb.x0)
 
 
 def merge_close_lines(ar, line_tol=2):
diff --git a/tests/data.py b/tests/data.py
index 7e53792..b2bf706 100755
--- a/tests/data.py
+++ b/tests/data.py
@@ -2798,3 +2798,51 @@ data_stream_layout_kwargs = [
     ["A.O.P Cornas", ""],
     ["Domaine Lionnet « Terre Brûlée » 2012", "15 €"],
 ]
+
+data_stream_duplicated_text = [
+    ['', '2012 BETTER VARIETIES Harvest Report for Minnesota Central  [ MNCE ]', '', '', '', '', '', '', '', '',
+     'ALL SEASON TEST'],
+    ['', 'Doug Toreen, Renville County, MN 55310          [ BIRD ISLAND ]', '', '', '', '', '', '', '', '',
+     '1.3 - 2.0 MAT. GROUP'],
+    ['PREV. CROP/HERB:', 'Corn / Surpass, Roundup', '', '', '', '', '', '', '', '', 'S2MNCE01'],
+    ['SOIL DESCRIPTION:', '', 'Canisteo clay loam, mod. well drained, non-irrigated', '', '', '', '', '', '', '', ''],
+    ['SOIL CONDITIONS:', '', 'High P, high K, 6.7 pH, 3.9% OM, Low SCN', '', '', '', '', '', '', '', '30" ROW SPACING'],
+    ['TILLAGE/CULTIVATION:', 'conventional w/ fall till', '', '', '', '', '', '', '', '', ''],
+    ['PEST MANAGEMENT:', 'Roundup twice', '', '', '', '', '', '', '', '', ''],
+    ['SEEDED - RATE:', 'May 15', '140 000 /A', '', '', '', '', '', '', 'TOP 30 for YIELD of 63 TESTED', ''],
+    ['HARVESTED - STAND:', 'Oct 3', '122 921 /A', '', '', '', '', '', '', 'AVERAGE of (3) REPLICATIONS', ''],
+    ['', '', '', '', 'SCN', 'Seed', 'Yield', 'Moisture', 'Lodging', 'Stand', 'Gross'],
+    ['Company/Brand', 'Product/Brand†', 'Technol.†', 'Mat.', 'Resist.', 'Trmt.†', 'Bu/A', '%', '%', '(x 1000)',
+     'Income'], ['Kruger', 'K2 1901', 'RR2Y', '1.9', 'R', 'Ac,PV', '56.4', '7.6', '0', '126.3', '$846'],
+    ['Stine', '19RA02 §', 'RR2Y', '1.9', 'R', 'CMB', '55.3', '7.6', '0', '120.0', '$830'],
+    ['Wensman', 'W 3190NR2', 'RR2Y', '1.9', 'R', 'Ac', '54.5', '7.6', '0', '119.5', '$818'],
+    ['Hefty', 'H17Y12', 'RR2Y', '1.7', 'MR', 'I', '53.7', '7.7', '0', '124.4', '$806'],
+    ['Dyna-Gro', 'S15RY53', 'RR2Y', '1.5', 'R', 'Ac', '53.6', '7.7', '0', '126.8', '$804'],
+    ['LG Seeds', 'C2050R2', 'RR2Y', '2.1', 'R', 'Ac', '53.6', '7.7', '0', '123.9', '$804'],
+    ['Titan Pro', '19M42', 'RR2Y', '1.9', 'R', 'CMB', '53.6', '7.7', '0', '121.0', '$804'],
+    ['Stine', '19RA02 (2) §', 'RR2Y', '1.9', 'R', 'CMB', '53.4', '7.7', '0', '123.9', '$801'],
+    ['Asgrow', 'AG1832 §', 'RR2Y', '1.8', 'MR', 'Ac,PV', '52.9', '7.7', '0', '122.0', '$794'],
+    ['Prairie Brand', 'PB-1566R2', 'RR2Y', '1.5', 'R', 'CMB', '52.8', '7.7', '0', '122.9', '$792'],
+    ['Channel', '1901R2', 'RR2Y', '1.9', 'R', 'Ac,PV', '52.8', '7.6', '0', '123.4', '$791'],
+    ['Titan Pro', '20M1', 'RR2Y', '2.0', 'R', 'Am', '52.5', '7.5', '0', '124.4', '$788'],
+    ['Kruger', 'K2-2002', 'RR2Y', '2.0', 'R', 'Ac,PV', '52.4', '7.9', '0', '125.4', '$786'],
+    ['Channel', '1700R2', 'RR2Y', '1.7', 'R', 'Ac,PV', '52.3', '7.9', '0', '123.9', '$784'],
+    ['Hefty', 'H16Y11', 'RR2Y', '1.6', 'MR', 'I', '51.4', '7.6', '0', '123.9', '$771'],
+    ['Anderson', '162R2Y', 'RR2Y', '1.6', 'R', 'None', '51.3', '7.5', '0', '119.5', '$770'],
+    ['Titan Pro', '15M22', 'RR2Y', '1.5', 'R', 'CMB', '51.3', '7.8', '0', '125.4', '$769'],
+    ['Dairyland', 'DSR-1710R2Y', 'RR2Y', '1.7', 'R', 'CMB', '51.3', '7.7', '0', '122.0', '$769'],
+    ['Hefty', 'H20R3', 'RR2Y', '2.0', 'MR', 'I', '50.5', '8.2', '0', '121.0', '$757'],
+    ['Prairie Brand', 'PB 1743R2', 'RR2Y', '1.7', 'R', 'CMB', '50.2', '7.7', '0', '125.8', '$752'],
+    ['Gold Country', '1741', 'RR2Y', '1.7', 'R', 'Ac', '50.1', '7.8', '0', '123.9', '$751'],
+    ['Trelay', '20RR43', 'RR2Y', '2.0', 'R', 'Ac,Ex', '49.9', '7.6', '0', '127.8', '$749'],
+    ['Hefty', 'H14R3', 'RR2Y', '1.4', 'MR', 'I', '49.7', '7.7', '0', '122.9', '$746'],
+    ['Prairie Brand', 'PB-2099NRR2', 'RR2Y', '2.0', 'R', 'CMB', '49.6', '7.8', '0', '126.3', '$743'],
+    ['Wensman', 'W 3174NR2', 'RR2Y', '1.7', 'R', 'Ac', '49.3', '7.6', '0', '122.5', '$740'],
+    ['Kruger', 'K2 1602', 'RR2Y', '1.6', 'R', 'Ac,PV', '48.7', '7.6', '0', '125.4', '$731'],
+    ['NK Brand', 'S18-C2 §', 'RR2Y', '1.8', 'R', 'CMB', '48.7', '7.7', '0', '126.8', '$731'],
+    ['Kruger', 'K2 1902', 'RR2Y', '1.9', 'R', 'Ac,PV', '48.7', '7.5', '0', '124.4', '$730'],
+    ['Prairie Brand', 'PB-1823R2', 'RR2Y', '1.8', 'R', 'None', '48.5', '7.6', '0', '121.0', '$727'],
+    ['Gold Country', '1541', 'RR2Y', '1.5', 'R', 'Ac', '48.4', '7.6', '0', '110.4', '$726'],
+    ['', '', '', '', '', 'Test Average  =', '47.6', '7.7', '0', '122.9', '$713'],
+    ['', '', '', '', '', 'LSD (0.10)  =', '5.7', '0.3', 'ns', '37.8', '566.4']
+]
diff --git a/tests/files/birdisland.pdf b/tests/files/birdisland.pdf
new file mode 100644
index 0000000..1501158
Binary files /dev/null and b/tests/files/birdisland.pdf differ
diff --git a/tests/test_common.py b/tests/test_common.py
index 6fadc9d..cb9a968 100644
--- a/tests/test_common.py
+++ b/tests/test_common.py
@@ -314,3 +314,11 @@ def test_version_generation_with_prerelease_revision():
         generate_version(version, prerelease=prerelease, revision=revision)
         == "0.7.3-alpha.2"
     )
+
+
+def test_stream_duplicated_text():
+    df = pd.DataFrame(data_stream_duplicated_text)
+
+    filename = os.path.join(testdir, "birdisland.pdf")
+    tables = camelot.read_pdf(filename, flavor="stream")
+    assert_frame_equal(df, tables[0].df)