TheAthleticCoder / Deep-Image-Tasks

In this repository we perform various image processing and downstream tasks using various algorithms and approaches.

Deep Image Tasks

In this repository we apply algorithms such as:

1. Apply K-Means Clustering on images.
2. Apply Image Compression using PCA.
3. Implementing Gaussian Mixture Models.
4. Using PCA for reconstructing faces.
5. Implementing Hard and Soft Margin SVMs.
6. Implementing MLPs and their variations and performing a detailed analysis.
7. Implemented AutoEncoders of three types:
   1. MLP-Only Model
   2. CNN-Only Model
   3. MLP+CNN Model
8. Experimenting with different parametric variations of the autoencoders.

---

File Structure

1. clustering compression which does K-Means Clustering on images and applies Image Compression using PCA.
2. GMMs which implements Gaussian Mixture Models.
3. reconstructed_faces which implements PCA for facial reconstruction and recognition.
4. Knowing_MLPs.ipynb which implementsg MLPs and their variations and performing a detailed analysis.
5. SVM.ipynb which impements Hard and Soft Margin SVMs.
6. Let's_Dive_into_CNNs.ipynb which implements AutoEncoders of the three mentioned types and we perform a deatiled analysis of the same.

---