Merge branch 'IT19170480' into 'master'

It19170480

See merge request !8

activity3.py

+import cv2
+import numpy as np
+from keras.models import load_model
+from PyQt5.QtCore import *
+from PyQt5.QtGui import *
+from PyQt5.QtWidgets import *
+import numpy as np
+import matplotlib.pyplot as plt
+
+
+# model = load_model('model_handDrawnrnSinhalaLettersRecognition-24-05-22.h5')
+model = load_model('model_handDrawnrnShapeRecognition-25-05-22.h5')
+
+# image_path
+img_path = "activity3.png"
+
+# read image
+img_raw = cv2.imread(img_path)
+
+# select ROI function
+roi = cv2.selectROI(img_raw)
+
+# print rectangle points of selected roi
+print(roi)
+
+# Crop selected roi from raw image
+roi_cropped = img_raw[int(roi[1]):int(roi[1]+roi[3]),
+                      int(roi[0]):int(roi[0]+roi[2])]
+
+# #show cropped image
+# cv2.imshow("ROI", roi_cropped)
+
+cv2.imwrite("crop.jpeg", roi_cropped)
+
+# #hold window
+# cv2.waitKey(0)
+
+
+img = cv2.imread('crop.jpeg')
+
+# cv2.imread() -> takes an image as an input
+h, w, channels = img.shape
+
+half = w//2
+
+
+# this will be the first column
+left_part = img[:, :half]
+
+# [:,:half] means all the rows and
+# all the columns upto index half
+
+# this will be the second column
+right_part = img[:, half:]
+
+# [:,half:] means al the rows and all
+# the columns from index half to the end
+# cv2.imshow is used for displaying the image
+# cv2.imshow('Left part', left_part)
+# cv2.imshow('Right part', right_part)
+
+# this is horizontal division
+half2 = h//2
+
+top = img[:half2, :]
+bottom = img[half2:, :]
+
+# cv2.imshow('Top', top)
+# cv2.imshow('Bottom', bottom)
+
+# saving all the images
+# cv2.imwrite() function will save the image
+# into your pc
+# cv2.imwrite('top.jpg', top)
+# cv2.imwrite('bottom.jpg', bottom)
+cv2.imwrite('right.jpg', right_part)
+cv2.imwrite('left.jpg', left_part)
+
+  
+def predict_digit():
+    imgArray = ["right.jpg", "left.jpg"]
+    for image in imgArray:
+        img = cv2.imread(image)
+        img_copy = img.copy()
+
+        img = cv2.resize(img, (400, 440))
+
+        img_copy = cv2.GaussianBlur(img, (7, 7), 0)
+        _, img_thresh = cv2.threshold(img, 100, 255, cv2.THRESH_BINARY_INV)
+        img_final = cv2.resize(img_thresh, (28, 28))
+        plt.imshow(img_final, cmap='gray')
+        # plt.show()
+        img_final = np.reshape(img_final, (-1, 28, 28, 1))
+
+        img = img/255.0
+        word_dict = {0: 'circle', 1: 'square', 2: 'star', 3: 'triangle'}
+        img_pred = word_dict[np.argmax(model.predict(img_final))]
+
+        print(img_pred)
+        # return img_pred
+
+
+predict_digit()
+cv2.waitKey(0)

data_augmentation.py

+from os import listdir
+from PIL import Image as PImage
+import cv2
+import numpy as np
+from keras.preprocessing.image import ImageDataGenerator
+from keras.preprocessing.image import img_to_array
+from keras.preprocessing.image import load_img
+import numpy as np
+import argparse
+import glob
+import skimage.io
+import matplotlib.pyplot as plt
+import skimage.filters
+import random
+from skimage.util import random_noise
+imageList = []
+
+ap = argparse.ArgumentParser()
+#ap.add_argument("-i", "--imageFolder", required=True,help="path to the input image")
+ap.add_argument("-o", "--output", required=True,
+                help="path to output directory to store augmentation examples")
+ap.add_argument("-p", "--prefix", type=str, default="image",
+                help="output filename prefix")
+args = vars(ap.parse_args())
+# /home/cyrrup/Desktop/outnew/*.jpg
+print("[INFO] loading example image...")
+
+
+def add_noise(img):
+    '''Add random noise to an image'''
+    # VARIABILITY = 10
+    # deviation = VARIABILITY*random.random()
+    # noise = np.random.normal(0, deviation, img.shape)
+    # img += noise
+    # np.clip(img, 0., 255.)
+    sigma = 2.5
+    blurred = skimage.filters.gaussian(
+        img, sigma=(sigma, sigma), truncate=2.5, multichannel=True)
+    # img = blurred
+    return blurred
+
+# for filename in glob.glob('E:/data separated/y/*.png'):
+for filename in glob.glob('G:/data augmengt/Data-aumentation-of-images-folder-using-keras-and-PIL-master/h/*.jpg'):
+    #print (filename)
+    #print("[INFO] loading example image...")
+    image = load_img(filename)
+    image = img_to_array(image)
+    image = np.expand_dims(image, axis=0)
+
+    # construct the image generator for data augmentation then
+    # initialize the total number of images generated thus far
+    # aug = ImageDataGenerator(rotation_range=30, width_shift_range=0.1,
+    #                          height_shift_range=0.1, shear_range=0.2, zoom_range=0.2,
+    #                          horizontal_flip=True, fill_mode="nearest")
+
+    # aug = ImageDataGenerator(rotation_range=30,  fill_mode='nearest')
+    aug = ImageDataGenerator(preprocessing_function=add_noise)
+    total = 0
+
+    # construct the actual Python generator
+    print("[INFO] generating images...")
+    imageGen = aug.flow(image, batch_size=1, save_to_dir=args["output"],
+                        save_prefix=args["prefix"], save_format="jpg")
+
+    # loop over examples from our image data augmentation generator
+    for image in imageGen:
+        # increment our counter
+        total += 1
+
+        # if we have reached 10 examples, break from the loop
+        if total == 5:
+            break