wip: Chieri V4 B30 ocr

src/arcaea_offline_ocr/ocr.py

@@ -5,6 +5,7 @@ import cv2
 import numpy as np
 from imutils import grab_contours
 from imutils import resize as imutils_resize
+from numpy.linalg import norm
 from pytesseract import image_to_string
 
 from .template import (
@@ -122,6 +123,32 @@ def filter_digit_results(
     return final_result
 
 
+def preprocess_hog(digits):
+    samples = []
+    for img in digits:
+        gx = cv2.Sobel(img, cv2.CV_32F, 1, 0)
+        gy = cv2.Sobel(img, cv2.CV_32F, 0, 1)
+        mag, ang = cv2.cartToPolar(gx, gy)
+        bin_n = 16
+        bin = np.int32(bin_n * ang / (2 * np.pi))
+        bin_cells = bin[:10, :10], bin[10:, :10], bin[:10, 10:], bin[10:, 10:]
+        mag_cells = mag[:10, :10], mag[10:, :10], mag[:10, 10:], mag[10:, 10:]
+        hists = [
+            np.bincount(b.ravel(), m.ravel(), bin_n)
+            for b, m in zip(bin_cells, mag_cells)
+        ]
+        hist = np.hstack(hists)
+
+        # transform to Hellinger kernel
+        eps = 1e-7
+        hist /= hist.sum() + eps
+        hist = np.sqrt(hist)
+        hist /= norm(hist) + eps
+
+        samples.append(hist)
+    return np.float32(samples)
+
+
 def ocr_digits(
     img: Mat,
     templates: TemplateItem,