How to detect objects in real time by using Jupyter Notebook and Neural Networks , by using Yolo3

Overview

Real Time Object Recognition From your Screen Desktop .

In this post, I will explain how to build a simply program to detect objects from you desktop computer.

We will see how using OpenCV and Python, we can detect objects by applying the most popular YOLO(You Look Only Once) algorithm.

OpenCV is the computer vision library/ framework that we we will be using to support our YOLOv3 algorithm

Darknet Architecture is pre-trained model for classifying 80 different classes. Our goal now is that we will use Darknet(YOLOv3) in OpenCV to classify objects using Python language.

For this project we will consider an standard resolution 1920 x 1080 , in windows 10 in Display Setting , select the resolution 1920 x 1080

Then you need to install Anaconda at this link

img

After you install it , check that your terminal , recognize conda

C:\conda --version
conda 4.10.3

The environments supported that I will consider is Python 3.7, Keras 2.4.3 and TensorFlow 2.4.0, let us create the environment, go to you command promt terminal and type the following:

conda create -n detector python==3.7.10
conda activate detector

then in your terminal type the following commands:

conda install ipykernel
Proceed ([y]/n)? y
python -m ipykernel install --user --name detector --display-name "Python (Object Detector)"

Then we install the correct versions of the the Tensorflow, and Numpy and Keras

we create a file called requirements.txt

if your are in Windows

notepad requirements.txt

or Linux

nano  requirements.txt

and you paste the following lines

Keras==2.4.3
keras-resnet==0.2.0
numpy==1.19.3
opencv-python==3.4.2.17
tensorflow==2.4.0
tensorflow-estimator==2.4.0
tensorflow-gpu==2.4.0
Pillow==9.0.0

and then we return back to the terminal and install them

pip install -r requirements.txt

then open the Jupyter notebook with the command

jupyter notebook&

then you click create new notebook Python (Object Detector) and then you can test if you can import the the following libraries

import numpy as np
from PIL import ImageGrab
import cv2
import time
import win32gui, win32ui, win32con, win32api

The next step is is define a function that enable record you screen

def grab_screen(region=None):
    hwin = win32gui.GetDesktopWindow()
    if region:
            left,top,x2,y2 = region
            width = x2 - left + 1
            height = y2 - top + 1
    else:
        width = win32api.GetSystemMetrics(win32con.SM_CXVIRTUALSCREEN)
        height = win32api.GetSystemMetrics(win32con.SM_CYVIRTUALSCREEN)
        left = win32api.GetSystemMetrics(win32con.SM_XVIRTUALSCREEN)
        top = win32api.GetSystemMetrics(win32con.SM_YVIRTUALSCREEN)
    hwindc = win32gui.GetWindowDC(hwin)
    srcdc = win32ui.CreateDCFromHandle(hwindc)
    memdc = srcdc.CreateCompatibleDC()
    bmp = win32ui.CreateBitmap()
    bmp.CreateCompatibleBitmap(srcdc, width, height)
    memdc.SelectObject(bmp)
    memdc.BitBlt((0, 0), (width, height), srcdc, (left, top), win32con.SRCCOPY)
    signedIntsArray = bmp.GetBitmapBits(True)
    img = np.fromstring(signedIntsArray, dtype='uint8')
    img.shape = (height,width,4)
    srcdc.DeleteDC()
    memdc.DeleteDC()
    win32gui.ReleaseDC(hwin, hwindc)
    win32gui.DeleteObject(bmp.GetHandle())
    return cv2.cvtColor(img, cv2.COLOR_BGRA2RGB)

then you define a new function called main() which will record your screen

def main():
    last_time = time.time()
    while True:
        # 1920 windowed mode
        screen = grab_screen(region=(0,40,1920,1120))
        img = cv2.resize(screen,None,fx=0.4,fy=0.3)
        height,width,channels = img.shape
        #detecting objects
        blob = cv2.dnn.blobFromImage(img,0.00392,(416,416),(0,0,0),True,crop=False)
        net.setInput(blob)
        outs = net.forward(outputlayers)
        #Showing info on screen/ get confidence score of algorithm in detecting an object in blob
        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:
                    #onject detected
                    center_x= int(detection[0]*width)
                    center_y= int(detection[1]*height)
                    w = int(detection[2]*width)
                    h = int(detection[3]*height)
                    #rectangle co-ordinaters
                    x=int(center_x - w/2)
                    y=int(center_y - h/2)
                    boxes.append([x,y,w,h]) #put all rectangle areas
                    confidences.append(float(confidence)) #how confidence was that object detected and show that percentage
                    class_ids.append(class_id) #name of the object tha was detected
        indexes = cv2.dnn.NMSBoxes(boxes,confidences,0.4,0.6)
        font = cv2.FONT_HERSHEY_PLAIN
        for i in range(len(boxes)):
            if i in indexes:
                x,y,w,h = boxes[i]
                label = str(classes[class_ids[i]])
                color = colors[i]
                cv2.rectangle(img,(x,y),(x+w,y+h),color,2)
                cv2.putText(img,label,(x,y+30),font,1,(255,255,255),2)
        #print('Frame took {} seconds'.format(time.time()-last_time))
        last_time = time.time()
        cv2.imshow('window', img)
        if cv2.waitKey(25) & 0xFF == ord('q'):
            cv2.destroyAllWindows()
            break

and finally we download the following files

  1. yolo.cfg (Download from here) — Configuration file
  2. yolo.weights (Download from here) — pre-trained weights
  3. coco.names (Download from here)- 80 classes names

then you add the following code

net = cv2.dnn.readNetFromDarknet('yolov3.cfg', 'yolov3.weights')
classes = []
with open("coco.names","r") as f:
    classes = [line.strip() for line in f.readlines()]
    
layer_names = net.getLayerNames()
outputlayers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
colors= np.random.uniform(0,255,size=(len(classes),3))

and finally you just run it with the simple code

main()

you can stop with simple press q

for example you want to identiy a Youtube video, of one beautiful girl

or this video https://youtu.be/QW-qWS3StZg?t=170

or the classic traffic recognition https://youtu.be/7HaJArMDKgI

Owner
Ruslan Magana Vsevolodovna
I am Data Scientist and Data Engineer. I have a Ph.D. in Physics and I am AWS certified in Machine Learning and Data Analytics
Ruslan Magana Vsevolodovna
A collection of resources (including the papers and datasets) of OCR (Optical Character Recognition).

OCR Resources This repository contains a collection of resources (including the papers and datasets) of OCR (Optical Character Recognition). Contents

Zuming Huang 363 Jan 03, 2023
Awesome anomaly detection in medical images

A curated list of awesome anomaly detection works in medical imaging, inspired by the other awesome-* initiatives.

Kang Zhou 57 Dec 19, 2022
Comparison-of-OCR (KerasOCR, PyTesseract,EasyOCR)

Optical Character Recognition OCR (Optical Character Recognition) is a technology that enables the conversion of document types such as scanned paper

21 Dec 25, 2022
A Python script to capture images from multiple webcams at once and save them into your local machine

Capturing multiple images at once from Webcam Using OpenCV Capture multiple image by accessing the webcam of your system and save it to your machine.

Fazal ur Rehman 2 Apr 16, 2022
Super Mario Game With Python

Super_Mario Hello all this is a simple python program which tries to use our body as a controller for the super mario game Here I have used media pipe

Adarsh Badagala 219 Nov 25, 2022
An application of high resolution GANs to dewarp images of perturbed documents

Docuwarp This project is focused on dewarping document images through the usage of pix2pixHD, a GAN that is useful for general image to image translat

Thomas Huang 97 Dec 25, 2022
Automatically remove the mosaics in images and videos, or add mosaics to them.

Automatically remove the mosaics in images and videos, or add mosaics to them.

Hypo 1.4k Dec 30, 2022
Assignment work with webcam

work with webcam : Press key 1 to use emojy on your face Press key 2 to use lip and eye on your face Press key 3 to checkered your face Press key 4 to

Hanane Kheirandish 2 May 31, 2022
Camera Intrinsic Calibration and Hand-Eye Calibration in Pybullet

This repository is mainly for camera intrinsic calibration and hand-eye calibration. Synthetic experiments are conducted in PyBullet simulator. 1. Tes

CAI Junhao 7 Oct 03, 2022
Shape Detection - It's a shape detection project with OpenCV and Python.

Shape Detection It's a shape detection project with OpenCV and Python. Setup pip install opencv-python for doing AI things. pip install simpleaudio fo

1 Nov 26, 2022
Scan the MRZ code of a passport and extract the firstname, lastname, passport number, nationality, date of birth, expiration date and personal numer.

PassportScanner Works with 2 and 3 line identity documents. What is this With PassportScanner you can use your camera to scan the MRZ code of a passpo

Edwin Vermeer 441 Dec 24, 2022
Corner-based Region Proposal Network

Corner-based Region Proposal Network CRPN is a two-stage detection framework for multi-oriented scene text. It employs corners to estimate the possibl

xhzdeng 140 Nov 04, 2022
Repository relating to the CVPR21 paper TimeLens: Event-based Video Frame Interpolation

TimeLens: Event-based Video Frame Interpolation This repository is about the High Speed Event and RGB (HS-ERGB) dataset, used in the 2021 CVPR paper T

Robotics and Perception Group 544 Dec 19, 2022
2 telegram-bots: for image recognition and for text generation

💻 📱 Telegram_Bots 🔎 & 📖 2 telegram-bots: for image recognition and for text generation. About Image recognition bot: User sends a photo and bot de

Marina Polukoshko 1 Jan 27, 2022
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

English | 简体中文 Introduction PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools that help users train better models and a

27.5k Jan 08, 2023
Detect textlines in document images

Textline Detection Detect textlines in document images Introduction This tool performs border, region and textline detection from document image data

QURATOR-SPK 70 Jun 30, 2022
Detect the mathematical formula from the given picture and the same formula is extracted and converted into the latex code

Mathematical formulae extractor The goal of this project is to create a learning based system that takes an image of a math formula and returns corres

6 May 22, 2022
Erosion and dialation using structure element in OpenCV python

Erosion and dialation using structure element in OpenCV python

Tamzid hasan 2 Nov 11, 2021
An unofficial package help developers to implement ZATCA (Fatoora) QR code easily which required for e-invoicing

ZATCA (Fatoora) QR-Code Implementation An unofficial package help developers to implement ZATCA (Fatoora) QR code easily which required for e-invoicin

TheAwiteb 28 Nov 03, 2022
Links to awesome OCR projects

Awesome OCR This list contains links to great software tools and libraries and literature related to Optical Character Recognition (OCR). Contribution

Konstantin Baierer 2.2k Jan 02, 2023