major changes

FRAS/Attendance/Attendance.csv

@@ -0,0 +1,51 @@
+Id,Name,Date,Time
+1,Bhaskar,2024-07-11,13:04:18
+1,Bhaskar,2024-07-11,13:04:18
+1,Bhaskar,2024-07-11,13:04:18
+1,Bhaskar,2024-07-11,13:04:18
+1,Bhaskar,2024-07-11,13:04:18
+1,Bhaskar,2024-07-11,13:04:18
+1,Bhaskar,2024-07-11,13:04:19
+1,Bhaskar,2024-07-11,13:04:19
+1,Bhaskar,2024-07-11,13:04:19
+1,Bhaskar,2024-07-11,13:04:19
+1,Bhaskar,2024-07-11,13:04:19
+1,Bhaskar,2024-07-11,13:04:19
+1,Bhaskar,2024-07-11,13:04:19
+1,Bhaskar,2024-07-11,13:04:19
+1,Bhaskar,2024-07-11,13:04:19
+1,Bhaskar,2024-07-11,13:04:20
+1,Bhaskar,2024-07-11,13:04:20
+1,Bhaskar,2024-07-11,13:04:20
+1,Bhaskar,2024-07-11,13:04:20
+1,Bhaskar,2024-07-11,13:04:20
+1,Bhaskar,2024-07-11,13:04:20
+1,Bhaskar,2024-07-11,13:04:20
+1,Bhaskar,2024-07-11,13:04:20
+1,Bhaskar,2024-07-11,13:04:20
+1,Bhaskar,2024-07-11,13:04:20
+1,Bhaskar,2024-07-11,13:04:20
+1,Bhaskar,2024-07-11,13:04:21
+1,Bhaskar,2024-07-11,13:04:21
+1,Bhaskar,2024-07-11,13:04:21
+1,Bhaskar,2024-07-11,13:04:21
+1,Bhaskar,2024-07-11,13:04:21
+1,Bhaskar,2024-07-11,13:04:22
+1,Bhaskar,2024-07-11,13:04:22
+1,Bhaskar,2024-07-11,13:04:22
+1,Bhaskar,2024-07-11,13:04:22
+1,Bhaskar,2024-07-11,13:04:22
+1,Bhaskar,2024-07-11,13:04:23
+1,Bhaskar,2024-07-11,13:04:23
+1,Bhaskar,2024-07-11,13:04:23
+1,Bhaskar,2024-07-11,13:04:23
+1,Bhaskar,2024-07-11,13:04:24
+1,Bhaskar,2024-07-11,13:04:25
+1,Bhaskar,2024-07-11,13:04:27
+1,Bhaskar,2024-07-11,13:04:27
+1,Bhaskar,2024-07-11,13:04:27
+1,Bhaskar,2024-07-11,13:04:27
+1,Bhaskar,2024-07-11,13:04:27
+1,Bhaskar,2024-07-11,13:04:28
+1,Bhaskar,2024-07-11,13:04:28
+1,Bhaskar,2024-07-11,13:04:28

FRAS/Attendance/Attendance_2024-07-11_Thursday.csv

@@ -0,0 +1,4 @@
+Id,Name,Date,Time
+1,Bhaskar,2024-07-11,13:14:16
+1,Bhaskar,2024-07-11,13:16:00
+2,Bhaskar,2024-07-11,16:51:38

FRAS/Recognize.py

@@ -1,85 +1,120 @@
 import datetime
 import os
 import time
-
 import cv2
 import pandas as pd
 
-
-#-------------------------
-def recognize_attendence():
-    recognizer = cv2.face.LBPHFaceRecognizer_create()  # cv2.createLBPHFaceRecognizer()
-    recognizer.read("./TrainingImageLabel/Trainner.yml")
+def recognize_attendance():
+    recognizer = cv2.face.LBPHFaceRecognizer_create()
+    recognizer.read("TrainingImageLabel/Trainner.yml")
     harcascadePath = "haarcascade_frontalface_default.xml"
     faceCascade = cv2.CascadeClassifier(harcascadePath)
-    df = pd.read_csv("StudentDetails"+os.sep+"StudentDetails.csv")
+    df = pd.read_csv("StudentDetails/StudentDetails.csv")
     font = cv2.FONT_HERSHEY_SIMPLEX
+
+    # Ensure the Attendance directory exists
+    if not os.path.exists("Attendance"):
+        os.makedirs("Attendance")
+
+    # Get current date and day name
+    today = datetime.datetime.now()
+    date_str = today.strftime("%Y-%m-%d")
+    day_name = today.strftime("%A")
+    attendance_file = f"Attendance/Attendance_{date_str}_{day_name}.csv"
+
     col_names = ['Id', 'Name', 'Date', 'Time']
-    attendance = pd.DataFrame(columns=col_names)
+
+    # Create the attendance CSV file if it doesn't exist for the day
+    if not os.path.exists(attendance_file):
+        attendance = pd.DataFrame(columns=col_names)
+        attendance.to_csv(attendance_file, index=False)
 
-    # Initialize and start realtime video capture
     cam = cv2.VideoCapture(0)
-    cam.set(3, 640)  # set video width
-    cam.set(4, 480)  # set video height
-    # Define min window size to be recognized as a face
+    cam.set(3, 640)
+    cam.set(4, 480)
     minW = 0.1 * cam.get(3)
     minH = 0.1 * cam.get(4)
 
+    recognized_faces = set()
+
     while True:
-        _,im = cam.read()
+        _, im = cam.read()
         gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
-        faces = faceCascade.detectMultiScale(gray, 1.2, 5,minSize = (int(minW), int(minH)),flags = cv2.CASCADE_SCALE_IMAGE)
-        for(x, y, w, h) in faces:
+        faces = faceCascade.detectMultiScale(gray, 1.2, 5, minSize=(int(minW), int(minH)), flags=cv2.CASCADE_SCALE_IMAGE)
+
+        for (x, y, w, h) in faces:
             cv2.rectangle(im, (x, y), (x+w, y+h), (10, 159, 255), 2)
             Id, conf = recognizer.predict(gray[y:y+h, x:x+w])
 
             if conf < 100:
-
-                aa = df.loc[df['Id'] == Id]['Name'].values
-                confstr = "  {0}%".format(round(100 - conf))
-                tt = str(Id)+"-"+aa
-
-
-            else:
-                Id = '  Unknown  '
-                tt = str(Id)
+                name = df.loc[df['Id'] == Id]['Name'].values[0] if not df[df['Id'] == Id].empty else 'Unknown'
                 confstr = "  {0}%".format(round(100 - conf))
+                tt = str(Id) + "-" + name
+
+                if (100 - conf) > 67 and Id not in recognized_faces:
+                    ts = time.time()
+                    date = datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d')
+                    timeStamp = datetime.datetime.fromtimestamp(ts).strftime('%H:%M:%S')
+
+                    # Append attendance data to the CSV file
+                    attendance_data = pd.DataFrame([[Id, name, date, timeStamp]], columns=col_names)
+                    attendance_data.to_csv(attendance_file, mode='a', header=False, index=False)
+                    print(f"Attendance logged: ID {Id}, Name {name}, Date {date}, Time {timeStamp}")
+                    recognized_faces.add(Id)
+
+                    # Exit the loop after recognizing the face
+                    cam.release()
+                    cv2.destroyAllWindows()
+                    return
+
+                tt = str(tt)[2:-2]
+                if (100 - conf) > 67:
+                    tt = tt + " [Pass]"
+                    cv2.putText(im, str(tt), (x+5, y-5), font, 1, (255, 255, 255), 2)
+                else:
+                    cv2.putText(im, str(tt), (x + 5, y - 5), font, 1, (255, 255, 255), 2)
+
+                if (100 - conf) > 67:
+                    cv2.putText(im, str(confstr), (x + 5, y + h - 5), font, 1, (0, 255, 0), 1)
+                elif (100 - conf) > 50:
+                    cv2.putText(im, str(confstr), (x + 5, y + h - 5), font, 1, (0, 255, 255), 1)
+                else:
+                    cv2.putText(im, str(confstr), (x + 5, y + h - 5), font, 1, (0, 0, 255), 1)
 
-            if (100-conf) > 67:
-                ts = time.time()
-                date = datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d')
-                timeStamp = datetime.datetime.fromtimestamp(ts).strftime('%H:%M:%S')
-                aa = str(aa)[2:-2]
-                attendance.loc[len(attendance)] = [Id, aa, date, timeStamp]
-
-            tt = str(tt)[2:-2]
-            if(100-conf) > 67:
-                tt = tt + " [Pass]"
-                cv2.putText(im, str(tt), (x+5,y-5), font, 1, (255, 255, 255), 2)
-            else:
-                cv2.putText(im, str(tt), (x + 5, y - 5), font, 1, (255, 255, 255), 2)
-
-            if (100-conf) > 67:
-                cv2.putText(im, str(confstr), (x + 5, y + h - 5), font,1, (0, 255, 0),1 )
-            elif (100-conf) > 50:
-                cv2.putText(im, str(confstr), (x + 5, y + h - 5), font, 1, (0, 255, 255), 1)
-            else:
-                cv2.putText(im, str(confstr), (x + 5, y + h - 5), font, 1, (0, 0, 255), 1)
-
-
-
-        attendance = attendance.drop_duplicates(subset=['Id'], keep='first')
         cv2.imshow('Attendance', im)
         if (cv2.waitKey(1) == ord('q')):
             break
-    ts = time.time()
-    date = datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d')
-    timeStamp = datetime.datetime.fromtimestamp(ts).strftime('%H:%M:%S')
-    Hour, Minute, Second = timeStamp.split(":")
-    fileName = "Attendance"+os.sep+"Attendance_"+date+"_"+Hour+"-"+Minute+"-"+Second+".csv"
-    attendance.to_csv(fileName, index=False)
-    print("Attendance Successful")
+
     cam.release()
     cv2.destroyAllWindows()
 
-
+def clear_attendance():
+    attendance_dir = "Attendance"
+    for file in os.listdir(attendance_dir):
+        file_path = os.path.join(attendance_dir, file)
+        if os.path.isfile(file_path):
+            os.remove(file_path)
+    print("All attendance logs cleared.")
+
+def clear_attendance_by_date(date_str):
+    attendance_dir = "Attendance"
+    for file in os.listdir(attendance_dir):
+        if date_str in file:
+            file_path = os.path.join(attendance_dir, file)
+            if os.path.isfile(file_path):
+                os.remove(file_path)
+                print(f"Attendance log for {date_str} cleared.")
+    print(f"No attendance log found for {date_str}.")
+
+if __name__ == "__main__":
+    while True:
+        choice = input("Enter 'r' to recognize attendance, 'c' to clear all attendance logs, or 'd' to clear attendance logs by date: ").lower()
+        if choice == 'r':
+            recognize_attendance()
+        elif choice == 'c':
+            clear_attendance()
+        elif choice == 'd':
+            date_str = input("Enter the date (YYYY-MM-DD) for which to clear attendance logs: ")
+            clear_attendance_by_date(date_str)
+        else:
+            print("Invalid choice. Please enter 'r', 'c', or 'd'.")

FRAS/StudentDetails/StudentDetails.csv

@@ -1,3 +1,3 @@
 Id,Name
-1,s
-2,sh
+1,Bhaskar
+2,Bhaskar

FRAS/Train_Image.py

@@ -5,51 +5,53 @@
 from PIL import Image
 from threading import Thread
 
+# Ensure the directory exists
+def create_directory(path):
+    if not os.path.exists(path):
+        os.makedirs(path)
 
-
-# -------------- image labesl ------------------------
-
+# -------------- image labels ------------------------
 def getImagesAndLabels(path):
-    # get the path of all the files in the folder
-    imagePaths = [os.path.join(path, f) for f in os.listdir(path)]
-    # print(imagePaths)
+    # Ensure the directory exists
+    create_directory(path)
+
+    # Debugging line to check if the directory exists
+    print(f"Directory checked/created: {path}")
 
-    # create empth face list
+    # get the path of all the files in the folder
+    try:
+        imagePaths = [os.path.join(path, f) for f in os.listdir(path)]
+    except FileNotFoundError as e:
+        print(f"Error: {e}")
+        return [], []
+
+    # Debugging line to check the image paths
+    print(f"Image paths: {imagePaths}")
+
     faces = []
-    # create empty ID list
     Ids = []
-    # now looping through all the image paths and loading the Ids and the images
     for imagePath in imagePaths:
-        # loading the image and converting it to gray scale
         pilImage = Image.open(imagePath).convert('L')
-        # Now we are converting the PIL image into numpy array
         imageNp = np.array(pilImage, 'uint8')
-        # getting the Id from the image
         Id = int(os.path.split(imagePath)[-1].split(".")[1])
-        # extract the face from the training image sample
         faces.append(imageNp)
         Ids.append(Id)
     return faces, Ids
 
-
-# ----------- train images function ---------------
+# -------------- training the images ---------------------
 def TrainImages():
-    recognizer = cv2.face_LBPHFaceRecognizer.create()
-    harcascadePath = "haarcascade_frontalface_default.xml"
-    detector = cv2.CascadeClassifier(harcascadePath)
+    recognizer = cv2.face.LBPHFaceRecognizer_create()
     faces, Id = getImagesAndLabels("TrainingImage")
-    Thread(target = recognizer.train(faces, np.array(Id))).start()
-    # Below line is optional for a visual counter effect
-    Thread(target = counter_img("TrainingImage")).start()
-    recognizer.save("TrainingImageLabel"+os.sep+"Trainner.yml")
-    print("All Images")
-
-# Optional, adds a counter for images trained (You can remove it)
-def counter_img(path):
-    imgcounter = 1
-    imagePaths = [os.path.join(path, f) for f in os.listdir(path)]
-    for imagePath in imagePaths:
-        print(str(imgcounter) + " Images Trained", end="\r")
-        time.sleep(0.008)
-        imgcounter += 1
-
+
+    # Debugging line to check the number of faces and Ids
+    print(f"Number of faces: {len(faces)}, Number of Ids: {len(Id)}")
+
+    try:
+        recognizer.train(faces, np.array(Id))
+        recognizer.save("TrainingImageLabel/Trainner.yml")
+        print("Images trained successfully.")
+    except cv2.error as e:
+        print(f"Error in training: {e}")
+
+    # Make the program sleep for 3 seconds
+    time.sleep(3)