update

README.md

@@ -5,7 +5,7 @@ Python 3.6-compatible Flask service that accepts an image and returns detected t
 ## Features
 - Accepts JPEG/PNG/WebP/BMP/TIFF/GIF (first frame) via multipart or base64 JSON.
 - Optional Google Coral EdgeTPU detection for scene context (loaded once at start).
-- EAST text detector (OpenCV DNN) when model exists; otherwise whole-image fallback.
+- EAST text detector (OpenCV DNN) when model exists; otherwise OpenCV contour-based text-region fallback.
 - OCR via `pytesseract` with per-block confidences; configurable languages.
 - Auto-selects `rus` or `eng` (via Tesseract OSD script detection) before full OCR when `OCR_LANG=eng+rus`.
 - If OCR result is empty, retries with fallback language/full-frame pass to improve recall.
@@ -109,6 +109,7 @@ Example JSON response (fields may vary):
     "latency_ms": 123,
     "coral_used": true,
     "east_used": true,
+    "text_locator": "east",
     "ocr_lang": "eng",
     "ocr_lang_requested": "eng+rus",
     "ocr_lang_strategy": "auto_script",
@@ -120,6 +121,6 @@ Example JSON response (fields may vary):
 
 ## Notes
 - If Coral is absent or fails, the service still returns OCR with `coral_used=false`.
-- If EAST model is missing, the whole image is passed to OCR to avoid empty results.
+- If EAST model is missing, service first tries OpenCV contour text regions and only then full-image OCR.
 - Keep images under `MAX_IMAGE_MB` (413 returned otherwise).
 - Optimize Tesseract languages to those you need to speed up OCR.

app.py

@@ -279,6 +279,14 @@ def image2text():
         coral_used = False
 
     boxes, east_used = txt_detector.detect(img_rgb)
+    h, w = img_rgb.shape[:2]
+    text_locator = "east" if east_used else "opencv_fallback"
+    if not east_used and len(boxes) == 1:
+        try:
+            if tuple([int(v) for v in boxes[0]]) == (0, 0, w, h):
+                text_locator = "full_image"
+        except Exception:
+            pass
 
     prep_options = {
         "upscale": OCR_UPSCALE,
@@ -389,6 +397,7 @@ def image2text():
             "latency_ms": latency_ms,
             "coral_used": coral_used,
             "east_used": east_used,
+            "text_locator": text_locator,
             "ocr_lang": ocr_lang_selected,
             "ocr_lang_requested": OCR_LANG,
             "ocr_lang_strategy": ocr_lang_strategy,

core/text_detect.py

@@ -24,7 +24,7 @@ class TextDetector(object):
             print('[WARN] OpenCV not installed; EAST disabled', file=sys.stderr)
             return
         if not os.path.exists(self.east_model_path):
-            print('[INFO] EAST model not found; will use whole-image fallback', file=sys.stderr)
+            print('[INFO] EAST model not found; using OpenCV contour fallback', file=sys.stderr)
             return
         try:
             self.net = cv2.dnn.readNet(self.east_model_path)
@@ -42,10 +42,19 @@ class TextDetector(object):
             self.east_available = False
 
     def detect(self, img_rgb):
-        if not self.east_available:
+        h, w = img_rgb.shape[:2]
-            h, w = img_rgb.shape[:2]
+        if self.east_available:
-            return [(_int0(0), _int0(0), _int0(w), _int0(h))], False
+            boxes = self._detect_with_east(img_rgb)
+            if boxes:
+                return boxes, True
 
+        boxes = self._detect_with_cv_fallback(img_rgb)
+        if boxes:
+            return boxes, False
+
+        return [(_int0(0), _int0(0), _int0(w), _int0(h))], False
+
+    def _detect_with_east(self, img_rgb):
         h, w = img_rgb.shape[:2]
         # EAST expects width/height divisible by 32
         new_w = 320
@@ -71,9 +80,7 @@ class TextDetector(object):
                 x2 = int((x + bw) * rW)
                 y2 = int((y + bh) * rH)
                 boxes.append((_int0(x1), _int0(y1), _int0(x2), _int0(y2)))
-        if not boxes:
+        return self._normalize_boxes(boxes, w, h, max_boxes=16)
-            boxes.append((_int0(0), _int0(0), _int0(w), _int0(h)))
-        return boxes, True
 
     def _decode(self, scores, geometry, score_thresh):
         num_rows, num_cols = scores.shape[2:4]
@@ -105,9 +112,145 @@ class TextDetector(object):
                 confidences.append(float(score))
         return rectangles, confidences
 
+    def _detect_with_cv_fallback(self, img_rgb):
+        if cv2 is None:
+            return []
+        try:
+            gray = cv2.cvtColor(img_rgb, cv2.COLOR_RGB2GRAY)
+        except Exception:
+            return []
+
+        h, w = gray.shape[:2]
+        img_area = float(max(1, h * w))
+        min_area = max(160.0, img_area * 0.00035)
+
+        boxes = []
+
+        # Pass #1: gradient + morphology for horizontal text lines.
+        try:
+            grad_x = cv2.Sobel(gray, ddepth=cv2.CV_32F, dx=1, dy=0, ksize=3)
+            grad_x = cv2.convertScaleAbs(grad_x)
+            grad_x = cv2.GaussianBlur(grad_x, (3, 3), 0)
+            _, bin1 = cv2.threshold(grad_x, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+            k_close = cv2.getStructuringElement(cv2.MORPH_RECT, (25, 5))
+            k_dilate = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 3))
+            bin1 = cv2.morphologyEx(bin1, cv2.MORPH_CLOSE, k_close, iterations=1)
+            bin1 = cv2.dilate(bin1, k_dilate, iterations=1)
+            boxes.extend(self._boxes_from_mask(bin1, w, h, min_area=min_area))
+        except Exception:
+            pass
+
+        # Pass #2: adaptive threshold for low-contrast / noisy scenes.
+        try:
+            bin2 = cv2.adaptiveThreshold(
+                gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 31, 15
+            )
+            k_close = cv2.getStructuringElement(cv2.MORPH_RECT, (15, 3))
+            k_dilate = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
+            bin2 = cv2.morphologyEx(bin2, cv2.MORPH_CLOSE, k_close, iterations=1)
+            bin2 = cv2.dilate(bin2, k_dilate, iterations=1)
+            boxes.extend(self._boxes_from_mask(bin2, w, h, min_area=min_area))
+        except Exception:
+            pass
+
+        return self._normalize_boxes(boxes, w, h, max_boxes=18)
+
+    def _boxes_from_mask(self, mask, image_w, image_h, min_area):
+        out = []
+        contours_result = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+        contours = contours_result[0] if len(contours_result) == 2 else contours_result[1]
+        min_h = max(10, int(image_h * 0.015))
+        min_w = max(16, int(image_w * 0.02))
+        for cnt in contours:
+            x, y, bw, bh = cv2.boundingRect(cnt)
+            area = float(bw * bh)
+            if area < min_area:
+                continue
+            if bw < min_w or bh < min_h:
+                continue
+            aspect = float(bw) / float(max(1, bh))
+            if aspect < 0.7 or aspect > 45.0:
+                continue
+            contour_area = float(cv2.contourArea(cnt))
+            fill_ratio = contour_area / float(max(1, bw * bh))
+            if fill_ratio < 0.03:
+                continue
+            pad_x = max(2, int(bw * 0.08))
+            pad_y = max(2, int(bh * 0.30))
+            x1 = max(0, x - pad_x)
+            y1 = max(0, y - pad_y)
+            x2 = min(image_w, x + bw + pad_x)
+            y2 = min(image_h, y + bh + pad_y)
+            out.append((_int0(x1), _int0(y1), _int0(x2), _int0(y2)))
+        return out
+
+    def _normalize_boxes(self, boxes, image_w, image_h, max_boxes=16):
+        norm = []
+        for box in boxes or []:
+            x1, y1, x2, y2 = _clip_box(box, image_w, image_h)
+            if x2 <= x1 or y2 <= y1:
+                continue
+            norm.append((x1, y1, x2, y2))
+        if not norm:
+            return []
+        kept = _nms_by_iou(norm, iou_thresh=0.45)
+        kept = sorted(kept, key=lambda b: ((b[3] - b[1]) * (b[2] - b[0])), reverse=True)
+        if max_boxes and len(kept) > max_boxes:
+            kept = kept[:max_boxes]
+        kept = sorted(kept, key=lambda b: (b[1], b[0]))
+        return kept
+
 
 def _int0(val):
     try:
         return int(val)
     except Exception:
         return 0
+
+
+def _clip_box(box, image_w, image_h):
+    x1, y1, x2, y2 = box
+    x1 = max(0, min(_int0(x1), _int0(image_w)))
+    y1 = max(0, min(_int0(y1), _int0(image_h)))
+    x2 = max(0, min(_int0(x2), _int0(image_w)))
+    y2 = max(0, min(_int0(y2), _int0(image_h)))
+    return x1, y1, x2, y2
+
+
+def _nms_by_iou(boxes, iou_thresh=0.45):
+    if not boxes:
+        return []
+    ranked = sorted(boxes, key=_box_area, reverse=True)
+    keep = []
+    for candidate in ranked:
+        should_keep = True
+        for chosen in keep:
+            if _iou(candidate, chosen) >= iou_thresh:
+                should_keep = False
+                break
+        if should_keep:
+            keep.append(candidate)
+    return keep
+
+
+def _box_area(box):
+    x1, y1, x2, y2 = box
+    return max(0, x2 - x1) * max(0, y2 - y1)
+
+
+def _iou(a, b):
+    ax1, ay1, ax2, ay2 = a
+    bx1, by1, bx2, by2 = b
+    xx1 = max(ax1, bx1)
+    yy1 = max(ay1, by1)
+    xx2 = min(ax2, bx2)
+    yy2 = min(ay2, by2)
+    iw = max(0, xx2 - xx1)
+    ih = max(0, yy2 - yy1)
+    inter = iw * ih
+    if inter <= 0:
+        return 0.0
+    union = float(_box_area(a) + _box_area(b) - inter)
+    if union <= 0:
+        return 0.0
+    return inter / union

run_service.sh

@@ -9,6 +9,7 @@ export MODEL_EDGETPU_PATH=${MODEL_EDGETPU_PATH:-./models/ssd_mobilenet_v2_coco_q
 export MODEL_LABELS_PATH=${MODEL_LABELS_PATH:-./models/coco_labels.txt}
 export MODEL_EAST_PATH=${MODEL_EAST_PATH:-./models/frozen_east_text_detection.pb}
 export OCR_LANG=${OCR_LANG:-eng+rus}
+export OCR_AUTO_LANG=${OCR_AUTO_LANG:-true}
 export OCR_CONFIG=${OCR_CONFIG:---oem 1 --psm 6}
 # Point to tessdata_best if installed
 export TESSDATA_PREFIX=${TESSDATA_PREFIX:-}