python.py

import cv2
import numpy as np
from scipy.spatial import distance as dist
import dlib

# Initialize text-to-speech engine

# Load the pre-trained face detection and landmark models
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")

# Function to detect eyes and calculate eye aspect ratio (EAR)
def eye_aspect_ratio(eye):
    A = dist.euclidean(eye[1], eye[5])
    B = dist.euclidean(eye[2], eye[4])
    C = dist.euclidean(eye[0], eye[3])
    ear = (A + B) / (2.0 * C)
    return ear

# Function to calibrate eye movements
def calibrate_eye():
    # Capture and process frames for calibration (simplified for illustration)
    # Implement a proper calibration routine for accurate results
    # You can collect eye positions for different screen points here
    # This example assumes you store these positions for later use
    eye_positions = {"top_left": [], "top_right": [], "bottom_left": [], "bottom_right": []}
    # Capture eye positions here...
    return eye_positions

# Function to detect gaze location
def detect_gaze(eye_positions):
    # Capture frame from webcam
    ret, frame = cap.read()
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    rects = detector(gray, 0)

    for rect in rects:
        shape = predictor(gray, rect)
        shape = face_utils.shape_to_np(shape)
        leftEye = shape[face_utils.FACIAL_LANDMARKS_IDXS["left_eye"][0]:face_utils.FACIAL_LANDMARKS_IDXS["left_eye"][1]]
        rightEye = shape[face_utils.FACIAL_LANDMARKS_IDXS["right_eye"][0]:face_utils.FACIAL_LANDMARKS_IDXS["right_eye"][1]]
        
        leftEAR = eye_aspect_ratio(leftEye)
        rightEAR = eye_aspect_ratio(rightEye)
        
        # Implement gaze detection logic using calibrated positions
        # Determine gaze location based on eye aspect ratio or other features
        # This is a simplified placeholder example
        if leftEAR < 0.3 and rightEAR < 0.3:
            gaze_location = "center"
        else:
            gaze_location = "unknown"

        return gaze_location

# Function to convert text to speech
def text_to_speech(text):
    engine.say(text)
    engine.runAndWait()

# Initialize webcam
cap = cv2.VideoCapture(0)

# Calibrate eye movements
eye_positions = calibrate_eye()

# Display eye-tracking keyboard (simplified for illustration)
print("Eye-tracking keyboard activated. Look at a letter to type:")
print("[A] [B] [C]")

# Main loop for gaze detection and typing
while True:
    gaze_location = detect_gaze(eye_positions)

    # Implement typing logic based on gaze location
    # This is a simplified placeholder example
    if gaze_location == "center":
        text = "A"
        print("Typed:", text)
        text_to_speech(text)

    # Exit condition for the loop
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# Release resources
cap.release()
cv2.destroyAllWindows()