...

src/main/java/kr/co/swh/lecture/opensource/ocr/ImageToText.java

@@ -21,10 +21,10 @@ public class ImageToText {
 
 	public static void main(String[] args) {
 		// TODO Auto-generated method stub
-		File image = new File("src/main/resources/ocr/sample.jpg");
+		File image = new File("C:\\Users\\tobby48\\git\\swh-opensource\\src\\main\\python\\kr\\co\\swh\\lecture\\opensource\\ocr_tts\\data\\test3.PNG");
 		Tesseract tesseract = new Tesseract();
-		tesseract.setDatapath("src/main/resources/ocr/result");
-		tesseract.setLanguage("ko");
+		tesseract.setDatapath("C:\\Program Files\\Tesseract-OCR\\tessdata");
+		tesseract.setLanguage("kor");
 		tesseract.setPageSegMode(1);
 		tesseract.setOcrEngineMode(1);
 		try {

src/main/python/kr/co/swh/lecture/opensource/ocr_tts/s1_image_to_text.py

@@ -1,3 +1,3 @@
 import pytesseract
 pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract'
-print(pytesseract.image_to_string('data\\test1.PNG',lang='kor'))
+print(pytesseract.image_to_string('data\\test4.PNG',lang='kor'))

src/main/python/kr/co/swh/lecture/opensource/ocr_tts/s4_image_to_text_to_voice.py

@@ -3,7 +3,7 @@ import pygame
 import pytesseract
 
 pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract'
-text = pytesseract.image_to_string('data\\test2.PNG',lang='kor')
+text = pytesseract.image_to_string('data\\test1.PNG',lang='kor')
 print(text)
 tts = gTTS(text=text, lang='ko')
 tts.save("data\\hello.mp3")

src/main/python/kr/co/swh/lecture/opensource/ocr_tts/sspecial_image_to_text.py

@@ -0,0 +1,17 @@
+import pytesseract
+
+
+import cv2
+
+originalImage = cv2.imread('data\\test3.PNG')
+grayImage = cv2.cvtColor(originalImage, cv2.COLOR_BGR2GRAY) 
+(thresh, blackAndWhiteImage) = cv2.threshold(grayImage, 127, 255, cv2.THRESH_BINARY)
+
+cv2.imshow('Black white image', blackAndWhiteImage)
+cv2.imshow('Original image',originalImage)
+cv2.imshow('Gray image', grayImage)
+# cv2.waitKey(0)
+
+
+pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract'
+print(pytesseract.image_to_string(blackAndWhiteImage,lang='kor'))

src/main/python/kr/co/swh/lecture/opensource/ocr_tts/sspecial_image_to_text2.py

@@ -0,0 +1,40 @@
+# import the necessary packages
+from PIL import Image
+import pytesseract
+import argparse
+import cv2
+import os
+# construct the argument parse and parse the arguments
+# ap = argparse.ArgumentParser()
+# ap.add_argument("-i", "--image", required=True,
+#     help="path to input image to be OCR'd")
+# ap.add_argument("-p", "--preprocess", type=str, default="thresh",
+#     help="type of preprocessing to be done")
+# args = vars(ap.parse_args())
+
+# load the example image and convert it to grayscale
+image = cv2.imread('data\\test5.PNG')
+gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+# check to see if we should apply thresholding to preprocess the
+# image
+# if args["preprocess"] == "thresh":
+gray = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
+# make a check to see if median blurring should be done to remove
+# noise
+# elif args["preprocess"] == "blur":
+#     gray = cv2.medianBlur(gray, 3)
+# write the grayscale image to disk as a temporary file so we can
+# apply OCR to it
+filename = "{}.png".format(os.getpid())
+cv2.imwrite(filename, gray)
+
+# load the image as a PIL/Pillow image, apply OCR, and then delete
+# the temporary file
+pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract'
+text = pytesseract.image_to_string(Image.open(filename))
+os.remove(filename)
+print(text)
+# show the output images
+cv2.imshow("Image", image)
+cv2.imshow("Output", gray)
+cv2.waitKey(0)