由于“警告:分辨率无效”错误,Tesseract OCR 图像识别失败
Tesseract OCR image recognition failed because of `Warning: Invalid resolution` error
我试图从图像中检测文本,在图像中我在 select 个字符周围绘制边界框并将它们拼接在一起形成另一个图像,如下所示:
我使用 cv2 使用以下代码在字符周围绘制边界框:
cnts = cv2.findContours(inverted, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
(cnts, bounding_boxes) = sort_contours(cnts)
ROI_number = 0
for c in cnts:
x, y, w, h = cv2.boundingRect(c)
ROI = inverted[y:y + h, x:x + w]
# ROI = cv2.erode(ROI, kernel, iterations=1)
ROI = cv2.filter2D(ROI, -1, sharpen_kernel)
# ROI = cv2.GaussianBlur(ROI, (5, 5), 0)
# ROI = cv2.filter2D(ROI, -100, sharpen_kernel)
ROI = cv2.bitwise_not(ROI)
ht, wd = ROI.shape
ww = 26
hh = 30
result = np.full((hh, ww), 255, dtype=np.uint8)
xx = (ww - wd) // 2
yy = (hh - ht) // 2
result[yy:yy + ht, xx:xx + wd] = ROI
cv2.imwrite('ROI_{}.jpeg'.format(ROI_number), result)
cv2.rectangle(inverted, (x, y), (x + w, y + h), (36, 255, 12), 0)
ROI_number += 1
我使用了 numpy 中的 hstack,使用以下代码将图像拼接在一起:
def stitch_images(input_path):
imagePaths = []
for image_path in glob.glob(os.path.join(input_path, '*.jpeg')):
imagePaths.append(image_path)
sorted_paths = sorted(imagePaths)
list_im = [sorted_paths[0], sorted_paths[1], sorted_paths[2], sorted_paths[3], sorted_paths[4], sorted_paths[5]]
imgs = [Image.open(i) for i in list_im]
min_shape = sorted([(np.sum(i.size), i.size) for i in imgs])[0][1]
imgs_comb = np.hstack((np.asarray(i.resize(min_shape)) for i in imgs))
imgs_comb = Image.fromarray(imgs_comb)
imgs_comb.save('stitched.jpeg')
但是无法使用 tesseract 读取拼接图像并出现以下错误:
Tesseract Open Source OCR Engine v4.1.1-rc2-21-gf4ef with Leptonica
Warning: Invalid resolution 0 dpi. Using 70 instead.
Estimating resolution as 334
Empty page!!
Estimating resolution as 334
Empty page!
加载图像、转换为灰度并使用 image_to_string
对我来说很有效。来自 pytesseract 的结果:
418081
代码
import cv2
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# Perfrom OCR with Pytesseract
data = pytesseract.image_to_string(gray, lang='eng', config='--psm 6')
print(data)
------------------
System information
------------------
Python: 3.7.4
NumPy: 1.14.5
OpenCV: 4.1.0
------------------
我试图从图像中检测文本,在图像中我在 select 个字符周围绘制边界框并将它们拼接在一起形成另一个图像,如下所示:
我使用 cv2 使用以下代码在字符周围绘制边界框:
cnts = cv2.findContours(inverted, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
(cnts, bounding_boxes) = sort_contours(cnts)
ROI_number = 0
for c in cnts:
x, y, w, h = cv2.boundingRect(c)
ROI = inverted[y:y + h, x:x + w]
# ROI = cv2.erode(ROI, kernel, iterations=1)
ROI = cv2.filter2D(ROI, -1, sharpen_kernel)
# ROI = cv2.GaussianBlur(ROI, (5, 5), 0)
# ROI = cv2.filter2D(ROI, -100, sharpen_kernel)
ROI = cv2.bitwise_not(ROI)
ht, wd = ROI.shape
ww = 26
hh = 30
result = np.full((hh, ww), 255, dtype=np.uint8)
xx = (ww - wd) // 2
yy = (hh - ht) // 2
result[yy:yy + ht, xx:xx + wd] = ROI
cv2.imwrite('ROI_{}.jpeg'.format(ROI_number), result)
cv2.rectangle(inverted, (x, y), (x + w, y + h), (36, 255, 12), 0)
ROI_number += 1
我使用了 numpy 中的 hstack,使用以下代码将图像拼接在一起:
def stitch_images(input_path):
imagePaths = []
for image_path in glob.glob(os.path.join(input_path, '*.jpeg')):
imagePaths.append(image_path)
sorted_paths = sorted(imagePaths)
list_im = [sorted_paths[0], sorted_paths[1], sorted_paths[2], sorted_paths[3], sorted_paths[4], sorted_paths[5]]
imgs = [Image.open(i) for i in list_im]
min_shape = sorted([(np.sum(i.size), i.size) for i in imgs])[0][1]
imgs_comb = np.hstack((np.asarray(i.resize(min_shape)) for i in imgs))
imgs_comb = Image.fromarray(imgs_comb)
imgs_comb.save('stitched.jpeg')
但是无法使用 tesseract 读取拼接图像并出现以下错误:
Tesseract Open Source OCR Engine v4.1.1-rc2-21-gf4ef with Leptonica
Warning: Invalid resolution 0 dpi. Using 70 instead.
Estimating resolution as 334
Empty page!!
Estimating resolution as 334
Empty page!
加载图像、转换为灰度并使用 image_to_string
对我来说很有效。来自 pytesseract 的结果:
418081
代码
import cv2
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# Perfrom OCR with Pytesseract
data = pytesseract.image_to_string(gray, lang='eng', config='--psm 6')
print(data)
------------------
System information
------------------
Python: 3.7.4
NumPy: 1.14.5
OpenCV: 4.1.0
------------------