Tune fallback for speed and filter low-confidence OCR noise

smoke_signal_tab.py

@@ -727,21 +727,21 @@ try:
 except Exception:
     SS_RENDER_DPI_SURYA = 300
 try:
-    SS_RENDER_DPI_FALLBACK = max(72, int(os.environ.get("SS_RENDER_DPI_FALLBACK", "200")))
+    SS_RENDER_DPI_FALLBACK = max(72, int(os.environ.get("SS_RENDER_DPI_FALLBACK", "180")))
 except Exception:
-    SS_RENDER_DPI_FALLBACK = 200
+    SS_RENDER_DPI_FALLBACK = 180
 try:
-    SS_TESSERACT_WORKERS = max(1, int(os.environ.get("SS_TESSERACT_WORKERS", "2")))
+    SS_TESSERACT_WORKERS = max(1, int(os.environ.get("SS_TESSERACT_WORKERS", "3")))
 except Exception:
-    SS_TESSERACT_WORKERS = 2
+    SS_TESSERACT_WORKERS = 3
 try:
-    SS_TESSERACT_TIMEOUT_SEC = max(1, int(os.environ.get("SS_TESSERACT_TIMEOUT_SEC", "18")))
+    SS_TESSERACT_TIMEOUT_SEC = max(1, int(os.environ.get("SS_TESSERACT_TIMEOUT_SEC", "10")))
 except Exception:
-    SS_TESSERACT_TIMEOUT_SEC = 18
+    SS_TESSERACT_TIMEOUT_SEC = 10
 try:
-    SS_TESSERACT_PSM = max(1, int(os.environ.get("SS_TESSERACT_PSM", "6")))
+    SS_TESSERACT_PSM = max(1, int(os.environ.get("SS_TESSERACT_PSM", "11")))
 except Exception:
-    SS_TESSERACT_PSM = 6
+    SS_TESSERACT_PSM = 11
 
 
 def _load_surya_runtime():
@@ -946,6 +946,16 @@ def _run_tesseract_batch(images):
                 word_count += wc
 
             avg_conf = round(conf_weighted / max(word_count, 1), 4) if regions else 0.0
+            # Filter obvious OCR noise from illustration texture (common in no-text pages).
+            full_text = " ".join(r["text"] for r in regions).strip()
+            letters = sum(1 for c in full_text if c.isalpha())
+            printable = sum(1 for c in full_text if c.isprintable() and not c.isspace())
+            alpha_ratio = (letters / printable) if printable else 0.0
+            tokens = [t for t in full_text.split() if t]
+            avg_token_len = (sum(len(t) for t in tokens) / len(tokens)) if tokens else 0.0
+            if regions and avg_conf <= 0.42 and alpha_ratio < 0.62 and avg_token_len < 3.2:
+                return {"regions": [], "confidence": 0.0, "method": "tesseract-noise-filtered"}
+
             return {"regions": regions, "confidence": avg_conf, "method": "tesseract"}
         except RuntimeError as e:
             return {"regions": [], "confidence": 0.0, "method": f"error-tesseract-timeout ({e})"}