283375/arcaea-offline-ocr
1
0
Fork 0
mirror of https://github.com/283375/arcaea-offline-ocr.git synced 2025-04-18 13:00:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor!: hog computing

Browse Source
This commit is contained in:
283375 2023-10-12 01:37:59 +08:00
parent 02599780e3
commit 2895eb7233
Signed by: 283375
SSH Key Fingerprint: SHA256:UcX0qg6ZOSDOeieKPGokA5h7soykG61nz2uxuQgVLSk
1 changed files with 3 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
src/arcaea_offline_ocr/ocr.py
View File

@ -3,7 +3,6 @@ from typing import Optional, Sequence, Tuple
import cv2 import cv2
import numpy as np import numpy as np
from numpy.linalg import norm
from .crop import crop_xywh from .crop import crop_xywh
from .types import Mat, cv2_ml_KNearest from .types import Mat, cv2_ml_KNearest
@ -142,28 +141,11 @@ def resize_fill_square(img: Mat, target: int = 20):
def preprocess_hog(digit_rois): def preprocess_hog(digit_rois):
# https://github.com/opencv/opencv/blob/f834736307c8328340aea48908484052170c9224/samples/python/digits.py # https://learnopencv.com/handwritten-digits-classification-an-opencv-c-python-tutorial/
samples = [] samples = []
for digit in digit_rois: for digit in digit_rois:
gx = cv2.Sobel(digit, cv2.CV_32F, 1, 0) hog = cv2.HOGDescriptor((20, 20), (10, 10), (5, 5), (10, 10), 9)
gy = cv2.Sobel(digit, cv2.CV_32F, 0, 1) hist = hog.compute(digit)
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) samples.append(hist)
return np.float32(samples) return np.float32(samples)