GuideAppForBlindPeople

import cv2
import pyttsx3
import numpy as np


cap = cv2.VideoCapture(0)

engine = pyttsx3.init()

net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")


with open("coco.names", "r") as f:
    classes = f.read().strip().split("\n")

while True:
  
    ret, frame = cap.read()

    blob = cv2.dnn.blobFromImage(frame, 1 / 255.0, (416, 416), swapRB=True, crop=False)
    net.setInput(blob)

    layer_names = net.getUnconnectedOutLayersNames()
    outs = net.forward(layer_names)

    class_ids = []
    confidences = []
    boxes = []


    for out in outs:
        for detection in out:
            scores = detection[5:]
            class_id = np.argmax(scores)
            confidence = scores[class_id]

            if confidence > 0.5:
               
                center_x = int(detection[0] * frame.shape[1])
                center_y = int(detection[1] * frame.shape[0])
                width = int(detection[2] * frame.shape[1])
                height = int(detection[3] * frame.shape[0])

             
                x = int(center_x - width / 2)
                y = int(center_y - height / 2)

                class_ids.append(class_id)
                confidences.append(float(confidence))
                boxes.append([x, y, width, height])

    indices = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)

    for i in indices:
        i = i[0]
        label = str(classes[class_ids[i]])
        confidence = confidences[i]


        x, y, w, h = boxes[i]
        cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)

     
        object_label = f"I see a {label} with {int(confidence * 100)}% confidence"
        engine.say(object_label)
        engine.runAndWait()

    cv2.imshow('Object Detection', frame)

    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()