图像截取与文字识别

#图像截取与文字识别

# coding:utf8
import cv2
import numpy as np
import pytesseract


def match_img(image, Target, value):

    img_rgb = cv2.imread(image)
    img_gray = cv2.cvtColor(img_rgb, cv2.COLOR_BGR2GRAY)
    template = cv2.imread(Target,0)
    w, h = template.shape[::-1]
    res = cv2.matchTemplate(img_gray,template,cv2.TM_CCOEFF_NORMED)
    threshold = value
    loc = np.where( res >= threshold)
    for pt in zip(*loc[::-1]):
        print pt,(pt[0] + w, pt[1] + h)
        get_loc_img(img_gray, pt[1], h, pt[0], w)
        cv2.rectangle(img_rgb, pt, (pt[0] + w, pt[1] + h), (7,249,151), 2)
        cv2.imshow('Detected',img_rgb)
    cv2.waitKey(0)
    cv2.destroyAllWindows()


def get_loc_img(img_src, y, h, x, w):
    # img = cv2.imread("./data/cut/thor.jpg")

    print y, h, x, w
    cropped = img_src[y:y+h, x:x+w]  # 裁剪坐标为[y0:y1, x0:x1]
    cv2.imwrite("./images/new.jpg", cropped)
    roi = cv2.imread("./images/new.jpg")
    tessdata_dir_config = '-l eng --oem 1 --psm 7 --tessdata-dir "C:\\Program Files (x86)\\Tesseract-OCR\\tessdata"'
    text = pytesseract.image_to_string(roi, config=tessdata_dir_config)
    print text


image=("./images/1.png")
Target=('./images/2.png')
value=0.9
match_img(image,Target,value)