From 4248ca000f76b25816446c42e66c26bdbfacafa6 Mon Sep 17 00:00:00 2001
From: Benjamin Kiessling <mittagessen@l.unchti.me>
Date: Wed, 6 Mar 2024 17:26:32 +0100
Subject: [PATCH] Filter out very small regions in segmenter

---
 kraken/lib/segmentation.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kraken/lib/segmentation.py b/kraken/lib/segmentation.py
index 87870562a..abff7abd5 100644
--- a/kraken/lib/segmentation.py
+++ b/kraken/lib/segmentation.py
@@ -352,10 +352,13 @@ def vectorize_regions(im: np.ndarray, threshold: float = 0.5):
         [[x0, y0, ... xn, yn], [xm, ym, ..., xk, yk], ... ]
         A list of lists containing the region polygons.
     """
+    print(f'shape: {im.shape} {im.max()}')
     bin = im > threshold
     labelled = label(bin)
     boundaries = []
     for x in regionprops(labelled):
+        if x.area < 32:
+            continue
         boundary = boundary_tracing(x)
         if len(boundary) > 2:
             boundaries.append(geom.Polygon(boundary))