Fashion Sense Detector

[Vaibhav-kesarwani]

Deep Learning Simplified Repository (Proposing new issue)

🔴 Project Title : Fashion Sense Detector

🔴 Aim : The of this project to develop a model which is capable enough to detect the cloths and try to find the best match using some algorithums

🔴 Dataset : A collection of 60,000 training images

🔴 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.

---

🔴🟡 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.

---

✅ To be Mentioned while taking the issue :

• Full name : Vaibhav Kesarwani
• GitHub Profile Link : https://github.com/Vaibhav-kesarwani
• Email ID : [email protected]
• Participant ID (if applicable):
• Approach for this Project : Libraries Used: TensorFlow, ImageIO, Matplotlib, Numpy, PIL, TensorFlow-Docs.
• What is your participant role? (Mention the Open Source program) Contributor in GSSOC24.

---

Happy Contributing 🚀

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

[github-actions]

Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊

[Vaibhav-kesarwani]

@abhisheks008 please assign this to me

[abhisheks008]

Hi @Vaibhav-kesarwani can you elaborate the problem statement and the approach you are planning for this problem statement?

[5rujana]

@abhisheks008

Proposed Approaches
Convolutional Neural Networks (CNN) CNNs are particularly suited for image classification tasks, making them ideal for detecting and matching clothing. They excel at learning spatial hierarchies of features through their architecture, enabling the identification of patterns such as textures, shapes, and colors. I will experiment with established architectures like VGGNet or ResNet to create a robust baseline for the Fashion Sense Detector.

Transfer Learning with Pre-trained Models By leveraging powerful pre-trained models such as ResNet, InceptionV3, or MobileNet, I can enhance the model's performance while minimizing training time. These models, trained on large datasets like ImageNet, have already learned rich visual representations. Fine-tuning the final layers for the specific clothing dataset will yield superior accuracy, making this approach both efficient and effective.

Support Vector Machine (SVM) with HOG Features To complement deep learning approaches, I propose using Support Vector Machine (SVM) combined with Histogram of Oriented Gradients (HOG) features. This traditional machine learning model is particularly effective for smaller datasets and can classify clothing images based on their shapes and edges. The interpretability of SVM will also provide valuable insights into the decision boundaries for clothing categories.

Next Steps
I plan to conduct exploratory data analysis (EDA) before model implementation to understand the dataset better and identify key features. The models will be compared based on their accuracy scores to determine the best fit for the Fashion Sense Detector.

[abhisheks008]

Hi @5rujana thanks for sharing your approach. Can you please confirm the dataset which will be used here?

[ypsmalik]

can someone confirm the source of the dataset used here?