data train and process but dont get the correct result,why?

import cv2
import numpy as np
from datetime import datetime
import os
from PIL import Image
import hashlib, os, math, time
import Image
#from PIL import Image
import ImageEnhance
from pytesser import *
from urllib import urlretrieve
import math
import random
import glob
iconset = ['0','0','0','3','3','3','3','3','3','3','3','5','5','5','5','7','7',
'7','7','7','7','7','7','7','4','4','4','4','4','4','4','4','2','2','2','2','2','2','2','2','2','2']
iconset = [0,1,20,5,6,7,8,10,11,15,17,2,12,21,22,3,4,
13,14,16,18,19,23,9,24,25,26,27,28,29,30,31,32,
33,34,35,36,37,38,39,40,41]
samples=np.empty((0,100))
responses =[]
for f in range(filen):
    img =Image.open('./iconset/'+str(f)+'.gif')
    img.convert('RGB').save ('img.jpg','JPEG')
    img= cv2.imread('img.jpg')
    im3= img.copy()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    ret,thresh = cv2.threshold(gray,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
    fg = cv2.erode(thresh,None,iterations = 2)
    bgt = cv2.dilate(thresh,None,iterations = 3)
    ret,bg = cv2.threshold(bgt,1,128,1)
    marker = cv2.add(fg,bg)
    marker32 = np.int32(marker)
    cv2.watershed(img,marker32)
    m = cv2.convertScaleAbs(marker32)
    ret,thresh = cv2.threshold(m,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
    roismall = cv2.resize(thresh,(10,10))
    sample = roismall.reshape((1,100))
    samples = np.append(samples,sample,0)
    responses.append(iconset[f])
responses = np.array(responses,np.float32)
responses = responses.reshape((responses.size,1))
print "training complete"
np.savetxt('general-samples.data',samples)
np.savetxt('general-responses.data',responses)
def train():
    samples = np.loadtxt('general-samples.data',np.float32)
    responses = np.loadtxt('general-responses.data',np.float32)
    responses = responses.reshape((1,responses.size))
    model = cv2.KNearest()
    model.train(samples,responses)
    return model

import cv2
import numpy as np
samples = np.loadtxt('general-samples.data', np.float32)
responses = np.loadtxt('general-responses.data', np.float32)
responses = responses.reshape((responses.size,1))
model = cv2.KNearest()
model.train(samples, responses)

image = cv2.imread('captcha1.png')
out = np.zeros(image.shape, np.uint8)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(gray,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
fg = cv2.erode(thresh,None,iterations = 2)
bgt = cv2.dilate(thresh,None,iterations = 3)
ret,bg = cv2.threshold(bgt,1,128,1)
marker = cv2.add(fg,bg)
marker32 = np.int32(marker)
cv2.watershed(image,marker32)
m = cv2.convertScaleAbs(marker32)
ret,thresh = cv2.threshold(m,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
res = cv2.bitwise_and(image,image,mask = thresh)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_LIST
        , cv2.CHAIN_APPROX_SIMPLE)
for contour in contours:
    if cv2.contourArea(contour) > 50:
        [x, y, w, h] = cv2.boundingRect(contour)
        if  h > 28:
            cv2.rectangle(image, (x, y), (x+w, y+h), (0, 255, 0), 2)
            roi = thresh[y:y+h, x:x+w]
            roi_small = cv2.resize(roi,(10,10))
            roi_small = roi_small.reshape((1,100))
            roi_small = np.float32(roi_small)
            retval, results, neigh_resp, dists = model.find_nearest(roi_small
                    , k = 1)
            string = str(int((results[0][0])))
            cv2.putText(out, string, (x, y+h), 0, 1, (0, 255, 0))
cv2.imshow('im',image)
cv2.imshow('out',out)
cv2.waitKey(0)