python-tesseract https://code.google.com/p/python-tesseract/を使用できます。イメージで動作します。必要なことは、結果の文字列を分割することです。https://www. dropbox.com/sh/kcybs1i04w3ao97/u33YGH_Kv6#f:euro9.jpgでテスト。ソースコードは以下。アップデート
# -*- coding: utf-8 -*-
from PIL import Image
from PIL import ImageEnhance
import tesseract
im = Image.open('test.jpg')
enhancer = ImageEnhance.Contrast(im)
im = enhancer.enhance(4)
im = im.convert('1')
w, h = im.size
im = im.resize((w * (416 / h), 416))
pix = im.load()
LINE_CR = 0.01
WHITE_HEIGHT_CR = int(h * (20 / 416.0))
status = 0
white_line = []
for i in xrange(h):
line = []
for j in xrange(w):
line.append(pix[(j, i)])
p = line.count(0) / float(w)
if not p > LINE_CR:
white_line.append(i)
wp = None
for i in range(10, len(white_line) - WHITE_HEIGHT_CR):
k = white_line[i]
if white_line[i + WHITE_HEIGHT_CR] == k + WHITE_HEIGHT_CR:
wp = k
break
result = []
flag = 0
while 1:
if wp < 0:
result.append(wp)
break
line = []
for i in xrange(w):
line.append(pix[(i, wp)])
p = line.count(0) / float(w)
if flag == 0 and p > LINE_CR:
l = []
for xx in xrange(20):
l.append(pix[(xx, wp)])
if l.count(0) > 5:
break
l = []
for xx in xrange(416-1, 416-100-1, -1):
l.append(pix[(xx, wp)])
if l.count(0) > 17:
break
result.append(wp)
wp -= 1
flag = 1
continue
if flag == 1 and p < LINE_CR:
result.append(wp)
wp -= 1
flag = 0
continue
wp -= 1
result.reverse()
for i in range(1, len(result)):
if result[i] - result[i - 1] < 15:
result[i - 1] = -1
result = filter(lambda x: x >= 0, result)
im = im.crop((0, result[0], w, result[-1]))
im.save('test_converted.jpg')
api = tesseract.TessBaseAPI()
api.Init(".","eng",tesseract.OEM_DEFAULT)
api.SetVariable("tessedit_char_whitelist", "0123456789abcdefghijklmnopqrstuvwxyz")
api.SetPageSegMode(tesseract.PSM_AUTO)
mImgFile = "test_converted.jpg"
mBuffer=open(mImgFile,"rb").read()
result = tesseract.ProcessPagesBuffer(mBuffer,len(mBuffer),api)
print "result(ProcessPagesBuffer)=",result
python 2.7 python-tesseract-win32 python-opencv numpy PIL に依存し、必ず python-tesseract の忘れないようにしてください。