[Project Addition]: Ethnicity Classification of Asian People

[abhisheks008]

Deep Learning Simplified Repository (Proposing new issue)

:red_circle: Project Title : Asian People - Liveness Detection :red_circle: Aim : The aim is to apply deep learning methods to find out the asian faces from the dataset. :red_circle: Dataset : https://www.kaggle.com/datasets/trainingdatapro/asian-people-liveness-detection-video-dataset :red_circle: Approach : Try to use 3-4 algorithms to implement the models and compare all the algorithms to find out the best fitted algorithm for the model by checking the accuracy scores. Also do not forget to do a exploratory data analysis before creating any model.

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

:red_circle::yellow_circle: Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

:white_check_mark: To be Mentioned while taking the issue :

• Full name :
• GitHub Profile Link :
• Email ID :
• Participant ID (if applicable):
• Approach for this Project :
• What is your participant role? (Mention the Open Source program)

---

Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[tushtithakur]

Hi , I'm excited to contribute to this project. Could you please assign me? Looking forward to getting started! @abhisheks008

Full name : Tushti Thakur GitHub Profile Link : https://github.com/tushtithakur Email ID : [email protected] Approach for this Project : Implement different deep learning algorithms using the dataset, evaluate it and compare performance. What is your participant role? GSSoC 2024

[abhisheks008]

Hi @tushtithakur wait for the induction session to complete by today evening, after that issues will be assigned to the contributors.

[tushtithakur]

@abhisheks008 Sure sir, I'll wait for the induction session to be completed. Thank you for the update!

[Subhranil2004]

Hi @abhisheks008 , I am willing to contribute to this issue! Please assign me to it.

• Full name : Subhranil Nandy
• GitHub Profile Link : https://github.com/Subhranil2004
• Email ID : [email protected]
• Approach for this Project : I would like to do EDA, some image preprocessing and apply different DL(CNN) techniques for model creation and evaluation.
• What is your participant role? GSSoC 2024 Contributor

[abhisheks008]

Hi @Subhranil2004 can you elaborate your approach? What are the deep learning models you are planning to use?

[gtanish2003]

I'm excited to contribute to this project as it aligns perfectly with my expertise in machine learning and deep learning. I have experience with implementing and comparing algorithms, as well as conducting exploratory data analysis. I would be thrilled to take on this issue and work towards finding the best-fitted algorithm for the model.

[abhisheks008]

Hi @gtanish2003 nice to have you here. Can you please follow the issue template and comment with your approach for solving this issue?

[gtanish2003]

Definitely sir , Full name : Tanish Gupta GitHub Profile Link : https://github.com/gtanish2003 Email ID : [email protected]

Approach for this Project :

Data Collection and Preparation:

Download the dataset from Kaggle and explore its contents. Preprocess the data, ensuring it is suitable for training the models. This might include resizing images, normalizing pixel values, and organizing the dataset into appropriate directories.

Exploratory Data Analysis (EDA):

Conduct EDA to understand the distribution of data, the characteristics of images, and any potential challenges in the dataset. Visualize the data to gain insights into the features that distinguish live and spoof faces.

Model Selection and Implementation:

Choose 3-4 algorithms suitable for image classification tasks, such as Convolutional Neural Networks (CNNs).

Model Training and Evaluation:

Train each model on the dataset and evaluate their performance using metrics like accuracy, precision, recall, and F1-score. Use techniques like cross-validation to ensure the models generalize well.

Model Comparison and Selection:

Compare the performance of the different models to determine the best-fitted algorithm for the liveness detection task. Consider factors like accuracy, computational efficiency, and ease of implementation.

Documentation and Reporting:

Create a README.md file inside the Model folder, documenting the steps followed, the rationale behind model selection, and the results obtained.

What is your participant role? (Mention the Open Source program) Girlscript sumer of code

[Subhranil2004]

Hi @Subhranil2004 can you elaborate your approach? What are the deep learning models you are planning to use?

Sure sir,

• Dataset creation : I observed the dataset. It contains 10 folders containing (1 image and 1 video) each of a particular Asian person. I am planning to extract frames from the videos to expand and create the dataset. Then segregate it into train, validation and test sets.

• Model Training : As I observed, the images were divided into 3 classes of ethnicity : South Asia, East Asia and Middle East. So I will be creating a model for classifying the images into those 3 categories. I will test with different SOTA pretrained models/ frameworks like Deepface, VGG-Face, ResNet etc. or with manually created CNNs and compare the results to find the best fitting model.

• Results : I will compare the evaluation metrics like accuracy, precision, recall, F1-score, etc. and present my findings in a well documented ipynb file. I will also create a README.md file

Please assign me this issue, so I can start working on it.

[abhisheks008]

Both of you guys are proposing really solid approach, but I'll go with @Subhranil2004. Issue assigned to you.

@gtanish2003 you can check out other open issues present here in this repo.

[Subhranil2004]

@abhisheks008, I have done the ethnicity classification task, as I said in my approach before. Also it's mentioned in the Aim of this issue. Should I change the title of my Project Folder a little : From Asian People - Liveness Detection to Asian People - Ethnicity Classification ? It will be more straightforward to understand.

[abhisheks008]

@abhisheks008, I have done the ethnicity classification task, as I said in my approach before. Also it's mentioned in the Aim of this issue. Should I change the title of my Project Folder a little : From Asian People - Liveness Detection to Asian People - Ethnicity Classification ? It will be more straightforward to understand.

Yeah no issues. Let me update the issue name for the same.

[abhisheks008]

@abhisheks008, I have done the ethnicity classification task, as I said in my approach before. Also it's mentioned in the Aim of this issue. Should I change the title of my Project Folder a little : From Asian People - Liveness Detection to Asian People - Ethnicity Classification ? It will be more straightforward to understand.

Yeah no issues. Let me update the issue name for the same.

Updated! Follow the issue name Ethnicity Classification of Asian People as your project folder name. @Subhranil2004