Last active
December 10, 2015 13:48
-
-
Save josephcc/4443212 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from nltk.corpus import wordnet as wn | |
import tesseract | |
import string | |
api = tesseract.TessBaseAPI() | |
api.Init(".","eng",tesseract.OEM_DEFAULT) | |
api.SetVariable("tessedit_char_whitelist", string.ascii_uppercase) | |
mBuffer = open('source.jpg','rb').read() | |
result = tesseract.ProcessPagesBuffer(mBuffer,len(mBuffer),api) | |
print result | |
def iter_result(_min, _max, result): | |
for length in range(_min, _max+1): | |
for y in range(len(result)): | |
for x in range(len(result[0])): | |
h = result[y][x:x+length] | |
if len(h) == length: | |
yield ((y,x),(y,x+length),''.join(h)) | |
v = [row[x] for row in result[y:y+length]] | |
if len(v) == length: | |
yield ((y,x),(y+length,x),''.join(v)) | |
d = [row[x:x+length] for row in result[y:y+length]] | |
if len(d) != length or len(d[-1]) != length: | |
continue | |
d = [d[i][i] for i in range(length)] | |
yield ((y,x),(y+length,x+length),''.join(d)) | |
result = [x.split() for x in result.strip().splitlines()] | |
for s,e,w in iter_result(3, 17, result): | |
lemmas = wn.lemmas(w.lower()) | |
if len(lemmas) != 0 and sum([x.count() for x in lemmas]) >= 1: | |
print w, s, e |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment