0% found this document useful (0 votes)
31 views4 pages

Lab 10 - Digital Image Processing Practice

dddddddddddddddddddddddddd

Uploaded by

52200188
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
31 views4 pages

Lab 10 - Digital Image Processing Practice

dddddddddddddddddddddddddd

Uploaded by

52200188
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

DIGITAL IMAGE PROCESSING COURSE - 505060

PRACTICE LABS

LAB 10. Face Detection with OpenCV and Deep learning

Requirements
(1) Follow the instructions with the help from your instructor.
(2) Finish all the exercises in class and do the homework at home. You can update your solutions
after class and re-submit all your work together with the homework.
(3) Grading
Total score = 50% * Attendance + 50% * Exercises
Rules:
- If the number of finished exercises is less than 80% total number of excercises, you will
get zero for the lab.
- Name a source file as “src_XX.py” where XX is the exercise number, for ex., “src_03.py” is
the source code for the Exercise 3.
- Add the text of your Student ID to each of the output image.
- Name an output image as “image_XX_YY.png” where XX is the exercise number and YY
is the order of output images in the exercise, for ex., “image_03_02.png” is the second
output image in the Exercise 3.
- Submit the source code and output image files directly to Google classroom assignment,
donot compress the files.
If you submit the exercises with wrong rules, you will get zero for the lab or the corresponding
exercises.

(4) Plagiarism check


If any 2 of the students have the same output images, then all will get zero for the
corresponding exercises.

INTRODUCTION
In this Lab, you will apply some image processing and deep learning techniques to build an
application for detecting faces in images, such as:
● Cascade Classifier
● Multi-task Cascade Convolutional Neural Network

INSTRUCTIONS

Look at articles in the reference links below to learn more about the steps to detect faces using
OpenCV and deep learning.

1. OpenCV
https://www.geeksforgeeks.org/opencv-python-program-face-detection/?ref=lbp
2. Deep learning
https://machinelearningmastery.com/how-to-perform-face-detection-with-classical-and-deep-learning-
methods-in-python-with-keras/

3. Setup guide:

- python -m pip install tensorflow==2.0


- python -m pip install mtcnn

If there exists DLL file errors, install Microsoft Visual C++ 2015 Redistributable Update
3 from https://www.microsoft.com/en-us/download/details.aspx?id=53840

If you cannot install those above packages, you can use Google Colab:
Insert the following codes into your Colab file:

!pip install mtcnn

!wget 'https://machinelearningmastery.com/wp-content/uploads/2019/03/test1.jpg'
!wget 'https://machinelearningmastery.com/wp-content/uploads/2019/03/test2.jpg'
and then change a little the method of loading image:

# load image from file


pixels = pyplot.imread("test1.jpg")

EXERCISES

Ex10.1. Build the applications to detect faces as in the two above articles in the
INSTRUCTIONS section.

Ex10.2. Extract all information of bar codes in the following image (position and thickness of
each line in a bar code):
Submit your code in practice class.

REFERENCES
1. https://docs.opencv.org/3.4/db/d28/tutorial_cascade_classifier.html
2. https://www.geeksforgeeks.org/face-detection-using-cascade-classifier-using-opencv-python/

You might also like