Final_open_idea

collect-data.py

@@ -0,0 +1,83 @@
+import cv2
+import os
+
+if not os.path.exists("data"):
+    os.makedirs("data")
+    os.makedirs("data/train")
+    os.makedirs("data/train/0")
+    os.makedirs("data/train/1")
+    os.makedirs("data/train/2")
+    os.makedirs("data/train/3")
+    os.makedirs("data/train/4")
+    os.makedirs("data/train/5")
+
+
+mode = 'train'
+directory = 'data/'+mode+'/'
+
+# url = '<YOUR IP ADDRESS>/video'
+# cap=cv2.VideoCapture(url)
+
+cap=cv2.VideoCapture(0)
+
+while True:
+    _, frame = cap.read()
+    frame = cv2.flip(frame, 1)
+
+    cv2.putText(frame, "subha-18", (int(0.35*frame.shape[1]),int(0.25*frame.shape[1]) ), cv2.FONT_HERSHEY_SIMPLEX, 1, (147,20,255), 3)
+
+    count = {'zero': len(os.listdir(directory+"/0")),
+             'one': len(os.listdir(directory+"/1")),
+             'two': len(os.listdir(directory+"/2")),
+             'three': len(os.listdir(directory+"/3")),
+             'four': len(os.listdir(directory+"/4")),
+             'five': len(os.listdir(directory+"/5"))}
+
+    cv2.putText(frame, "MODE : "+mode, (10, 50), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0,0,0), 1)
+    cv2.putText(frame, "IMAGE COUNT", (10, 100), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0,0,0), 1)
+    cv2.putText(frame, "ZERO : "+str(count['zero']), (10, 120), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (255,153,51), 1)
+    cv2.putText(frame, "ONE : "+str(count['one']), (10, 140), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (204,102,0), 1)
+    cv2.putText(frame, "TWO : "+str(count['two']), (10, 160), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (255,102,102), 1)
+    cv2.putText(frame, "THREE : "+str(count['three']), (10, 180), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (255,51,51), 1)
+    cv2.putText(frame, "FOUR : "+str(count['four']), (10, 200), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (204,0,0), 1)
+    cv2.putText(frame, "FIVE : "+str(count['five']), (10, 220), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (153,0,76), 1)
+
+
+    x1 = int(0.5*frame.shape[1])
+    y1 = 10
+    x2 = frame.shape[1]-10
+    y2 = int(0.5*frame.shape[1])
+    cv2.rectangle(frame, (x1-1, y1-1), (x2+1, y2+1), (255,0,0) ,3)
+    roi = frame[y1:y2, x1:x2]
+    roi = cv2.resize(roi, (300, 300)) 
+    cv2.putText(frame, "R.O.I", (int(0.75*frame.shape[1]),int(0.55*frame.shape[1])), cv2.FONT_HERSHEY_SIMPLEX, 1, (0,225,0), 3)
+    cv2.imshow("Frame", frame)
+
+
+
+
+    roi = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
+    roi = cv2.GaussianBlur(roi, (15, 15), 0)
+    _, roi = cv2.threshold(roi, 120, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU) 
+    cv2.imshow("ROI", roi)
+
+
+
+    interrupt = cv2.waitKey(10)
+    if interrupt & 0xFF == 27:
+        break
+    if interrupt & 0xFF == ord('0'):
+        cv2.imwrite(directory+'0/'+str(count['zero'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('1'):
+        cv2.imwrite(directory+'1/'+str(count['one'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('2'):
+        cv2.imwrite(directory+'2/'+str(count['two'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('3'):
+        cv2.imwrite(directory+'3/'+str(count['three'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('4'):
+        cv2.imwrite(directory+'4/'+str(count['four'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('5'):
+        cv2.imwrite(directory+'5/'+str(count['five'])+'.jpg', roi)
+
+cap.release()
+cv2.destroyAllWindows()

collect-data_modified.py

@@ -0,0 +1,107 @@
+import cv2
+import os
+
+if not os.path.exists("data"):
+    os.makedirs("data")
+    os.makedirs("data/train")
+    os.makedirs("data/train/0")
+    os.makedirs("data/train/1")
+    os.makedirs("data/train/2")
+    os.makedirs("data/train/3")
+    os.makedirs("data/train/4")
+    os.makedirs("data/train/5")
+    os.makedirs("data/train/6")
+    os.makedirs("data/train/7")
+    os.makedirs("data/train/8")
+    os.makedirs("data/train/9")
+
+
+mode = 'train'
+directory = 'data/'+mode+'/'
+
+# url = '<YOUR IP ADDRESS>/video'
+# cap=cv2.VideoCapture(url)
+
+cap=cv2.VideoCapture(0)
+
+while True:
+    _, frame = cap.read()
+    frame = cv2.flip(frame, 1)
+
+    cv2.putText(frame, "subha-18", (int(0.35*frame.shape[1]),int(0.25*frame.shape[1]) ), cv2.FONT_HERSHEY_SIMPLEX, 1, (147,20,255), 3)
+
+    count = {'zero': len(os.listdir(directory+"/0")),
+             'one(index)': len(os.listdir(directory+"/1")),
+             'two': len(os.listdir(directory+"/2")),
+             'three': len(os.listdir(directory+"/3")),
+             'four': len(os.listdir(directory+"/4")),
+             'five': len(os.listdir(directory+"/5")),
+             'one_thumb': len(os.listdir(directory+"/6")),
+             'two_2nd_4th': len(os.listdir(directory+"/7")),
+             'three_3rd_4th_5th': len(os.listdir(directory+"/8")),
+             'blank': len(os.listdir(directory+"/9"))
+             }
+
+    cv2.putText(frame, "MODE : "+mode, (10, 50), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0,0,0), 1)
+    cv2.putText(frame, "IMAGE COUNT", (10, 100), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0,0,0), 1)
+    cv2.putText(frame, "ZERO : "+str(count['zero']), (10, 120), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (255,153,51), 1)
+    cv2.putText(frame, "ONE : "+str(count['one(index)']), (10, 140), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (204,102,0), 1)
+    cv2.putText(frame, "TWO : "+str(count['two']), (10, 160), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (255,102,102), 1)
+    cv2.putText(frame, "THREE : "+str(count['three']), (10, 180), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (255,51,51), 1)
+    cv2.putText(frame, "FOUR : "+str(count['four']), (10, 200), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (204,0,0), 1)
+    cv2.putText(frame, "FIVE : "+str(count['five']), (10, 220), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (153,0,76), 1)
+    cv2.putText(frame, "one_thumb(6) : "+str(count['one_thumb']), (10, 240), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (153,0,76), 1)
+    cv2.putText(frame, "two_2nd_4th(7) : "+str(count['two_2nd_4th']), (10, 260), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (153,0,76), 1)
+    cv2.putText(frame, "three_3rd_4th_5th(8) : "+str(count['three_3rd_4th_5th']), (10, 280), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (153,0,76), 1)
+    cv2.putText(frame, "blank(9): "+str(count['blank']), (10, 300), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (153,0,76), 1)
+
+
+
+    x1 = int(0.5*frame.shape[1])
+    y1 = 10
+    x2 = frame.shape[1]-10
+    y2 = int(0.5*frame.shape[1])
+    cv2.rectangle(frame, (x1-1, y1-1), (x2+1, y2+1), (255,0,0) ,3)
+    roi = frame[y1:y2, x1:x2]
+    roi = cv2.resize(roi, (300, 300)) 
+    cv2.putText(frame, "R.O.I", (int(0.75*frame.shape[1]),int(0.55*frame.shape[1])), cv2.FONT_HERSHEY_SIMPLEX, 1, (0,225,0), 3)
+    cv2.imshow("Frame", frame)
+
+
+
+
+    roi = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
+    roi = cv2.GaussianBlur(roi, (5, 5), 0)
+    _, roi = cv2.threshold(roi, 120, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU) 
+    cv2.imshow("ROI", roi)
+
+
+
+    interrupt = cv2.waitKey(10)
+    if interrupt & 0xFF == 27:
+        break
+    if interrupt & 0xFF == ord('0'):
+        cv2.imwrite(directory+'0/'+str(count['zero'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('1'):
+        cv2.imwrite(directory+'1/'+str(count['one(index)'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('2'):
+        cv2.imwrite(directory+'2/'+str(count['two'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('3'):
+        cv2.imwrite(directory+'3/'+str(count['three'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('4'):
+        cv2.imwrite(directory+'4/'+str(count['four'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('5'):
+        cv2.imwrite(directory+'5/'+str(count['five'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('6'):
+        cv2.imwrite(directory+'6/'+str(count['one_thumb'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('7'):
+        cv2.imwrite(directory+'7/'+str(count['two_2nd_4th'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('8'):
+        cv2.imwrite(directory+'8/'+str(count['three_3rd_4th_5th'])+'.jpg', roi)
+    if interrupt & 0xFF == ord('9'):
+        cv2.imwrite(directory+'9/'+str(count['blank'])+'.jpg', roi)
+
+
+
+cap.release()
+cv2.destroyAllWindows()

prediction.py

@@ -0,0 +1,61 @@
+from keras.models import model_from_json
+import operator
+import cv2
+import numpy as np
+import math
+
+json_file = open("model-bw.json", "r")
+model_json = json_file.read()
+json_file.close()
+loaded_model = model_from_json(model_json)
+loaded_model.load_weights("model-bw.h5")
+print("Loaded model from disk")
+
+cap = cv2.VideoCapture(0) 
+
+categories = {0: 'ZERO', 1: 'ONE', 2: 'TWO', 3: 'THREE', 4: 'FOUR', 5: 'FIVE', 6:'One', 7:'Two', 8:'Three', 9:'Blank'}
+
+while True:
+    _, frame = cap.read()
+    frame = cv2.flip(frame, 1)
+
+    x1 = int(0.5*frame.shape[1])
+    y1 = 10
+    x2 = frame.shape[1]-10
+    y2 = int(0.5*frame.shape[1])
+
+    cv2.putText(frame, "Expressando - TDOC 2021", (175, 450), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (225,255,0), 3)
+    cv2.rectangle(frame, (x1-1, y1-1), (x2+1, y2+1), (255,255,255) ,3)
+    roi = frame[y1:y2, x1:x2]
+
+
+
+    roi = cv2.resize(roi, (64, 64)) 
+    roi = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
+    cv2.putText(frame, "R.O.I", (440, 350), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0,225,0), 3)
+
+    _, test_image = cv2.threshold(roi, 120, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+    cv2.imshow("ROI", test_image)
+
+    result = loaded_model.predict(test_image.reshape(1, 64, 64, 1))
+    prediction = {'ZERO': result[0][0], 
+                  'ONE': result[0][1], 
+                  'TWO': result[0][2],
+                  'THREE': result[0][3],
+                  'FOUR': result[0][4],
+                  'FIVE': result[0][5],
+                  'One': result[0][6],
+                  'Two': result[0][7],
+                  'Three': result[0][8],
+                  'Blank': result[0][9]}
+    prediction = sorted(prediction.items(), key=operator.itemgetter(1), reverse=True) #(0.9 = FIVE, 0.7, 0.6, 0.5, 0.4)
+    cv2.putText(frame, "PREDICTION:", (30, 90), cv2.FONT_HERSHEY_SIMPLEX, 1, (255,255,255), 2)
+    cv2.putText(frame, prediction[0][0], (180, 130), cv2.FONT_HERSHEY_SIMPLEX, 1, (0,0,255), 2)
+    cv2.imshow("Frame",frame)
+    interrupt = cv2.waitKey(10)
+    if interrupt & 0xFF == 27:
+        break
+
+
+cap.release()
+cv2.destroyAllWindows()

task1.py

@@ -0,0 +1,55 @@
+import cv2
+
+#(width, height) = (130, 100)
+
+# url = '<YOUR IP ADDRESS>/video'
+# cap=cv2.VideoCapture(url)
+
+
+cap=cv2.VideoCapture(0)
+
+while (cap.isOpened()):
+    ret, img = cap.read()
+    img=cv2.flip(img, 1)
+    cv2.rectangle(img, (20, 20), (250, 250), (255,0,0), 4, cv2.LINE_AA)
+    cv2.imshow("RGB Output", img)
+    img1 = img[20:250,20:250]       
+    imCopy = img1.copy()
+    gray = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
+    blur = cv2.GaussianBlur(gray, (35, 35), 0)
+
+    cv2.imshow("Grayscale",gray)
+    cv2.imshow('Blur', blur)
+
+    ret, thresh1 = cv2.threshold(blur, 10, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+    #hand_resize = cv2.resize(thresh1, (width, height))
+    cv2.imshow("Thresh binary ", thresh1)
+
+    ret, thresh2 = cv2.threshold(blur, 10, 255, cv2.THRESH_TOZERO + cv2.THRESH_OTSU)
+    cv2.imshow("Tozero ", thresh2)
+
+    ret, thresh3 = cv2.threshold(blur, 10, 255, cv2.THRESH_TRUNC + cv2.THRESH_OTSU)
+    cv2.imshow("Trunc ", thresh3)
+
+    contours, hierarchy = cv2.findContours(thresh1, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
+    cv2.drawContours(imCopy, contours, -1, (0, 255, 0))
+    cv2.imshow('Contours_tree', imCopy)
+
+    imCopy3 = img1.copy()
+    contours, hierarchy = cv2.findContours(thresh1, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
+    cv2.drawContours(imCopy3, contours, -1, (0, 255, 0))
+    cv2.imshow('Contours_list', imCopy3)
+
+    imCopy2 = img1.copy()
+    contours, hierarchy = cv2.findContours(thresh1, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
+    cv2.drawContours(imCopy2, contours, -1, (0, 255, 0))
+    cv2.imshow('Contours_external', imCopy2)
+
+
+
+    k = 0xFF & cv2.waitKey(10)
+    if k == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()

train_model.py

@@ -0,0 +1,52 @@
+from keras.models import Sequential
+from keras.layers import Convolution2D, MaxPooling2D, Flatten, Dense
+
+classifier = Sequential()
+
+classifier.add(Convolution2D(32, (3, 3), input_shape=(64, 64, 1), activation='relu'))
+classifier.add(MaxPooling2D(pool_size=(2, 2)))
+
+classifier.add(Convolution2D(32, (3, 3), activation='relu'))
+classifier.add(MaxPooling2D(pool_size=(2, 2)))
+
+classifier.add(Flatten())
+
+classifier.add(Dense(units=128, activation='relu'))
+classifier.add(Dense(units=10, activation='softmax'))
+
+classifier.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
+
+
+from keras.preprocessing.image import ImageDataGenerator
+
+train_datagen = ImageDataGenerator(
+        rescale=1./255,
+        shear_range=0.2,
+        zoom_range=0.2,
+        horizontal_flip=True)
+
+test_datagen = ImageDataGenerator(rescale=1./255) #epoch
+
+training_set = train_datagen.flow_from_directory('data/train',
+                                                 target_size=(64, 64),
+                                                 batch_size=10,
+                                                 color_mode='grayscale',
+                                                 class_mode='categorical')
+
+test_set = test_datagen.flow_from_directory('data/test',
+                                            target_size=(64, 64),
+                                            batch_size=10,
+                                            color_mode='grayscale',
+                                            class_mode='categorical') 
+
+classifier.fit_generator(
+        training_set,
+        epochs=10,
+        validation_data=test_set)
+
+#Saving
+model_json = classifier.to_json()
+with open("model-bw.json", "w") as json_file:
+    json_file.write(model_json)
+classifier.save_weights('model-bw.h5')
+