Python tesseract 的准确性

Question

我有运行 tesseract ocr 将图像文件转换为字符串。

现在我有输出了

如何比较原始PNG文件和输出文本文件的准确性是否正确

basewidth = 2700
img = Image.open('D:OCR\page1.png')
wpercent = (basewidth/float(img.size[0]))
hsize = int((float(img.size[1])*float(wpercent)))
img = img.resize((basewidth,hsize), PIL.Image.ANTIALIAS)
img.save('page1_zoom.png') 
print(image_to_string(Image.open('D:\page1_zoom.png')))

Answer 1

如何检查内容是否准确？

您肯定需要一些 手动基线/黄金数据 来比较结果。您将需要您的测试数据或至少要验证的参数。

Test cases could be something like: 
 1. Whole textual data 
 2. No of lines 
 3. No of Paragraphs 
 4. Position of text

Tesseract 与 Google ocr:

If you want to test tesseract accuracy with other OCR then you can try google OCR that gives better results than tesseract (although it is based on it)

Tesseract 训练：

Tesseract does provide feature of training to improve the accuracy of results.

Python tesseract 的准确性

Python accuracy for tesseract

python

ocr

tesseract

floating-accuracy