DrCyZ: Techniques for analyzing and extracting useful information from CyZ.

Samples from NASA Perseverance and set of GAN generated synthetic images from Neural Mars.

Repository: https://github.com/decurtoidiaz/drcyz

Subset of samples from (includes tools to visualize and analyse the dataset):

CyZ: MARS Space Exploration Dataset. [https://doi.org/10.5281/zenodo.5655473]

Images from NASA missions of the celestial body.

Repository: https://github.com/decurtoidiaz/cyz

Authors:

J. de Curtò c@decurto.be

I. de Zarzà z@dezarza.be

File Information from DrCyZ-1.1

• Subset of samples from Perseverance (drcyz/c).
  ∙ png (drcyz/c/png).
    PNG files (5025) selected from NASA Perseverance (CyZ-1.1) after t-SNE and K-means Clustering. 
  ∙ csv (drcyz/c/csv).
    CSV file.


• Resized samples from Perseverance (drcyz/c+).
  ∙ png 64x64; 128x128; 256x256; 512x512; 1024x1024 (drcyz/c+/drcyz_64-1024).
    PNG files resized at the corresponding size. 
  ∙ TFRecords 64x64; 128x128; 256x256; 512x512; 1024x1024 (drcyz/c+/tfr_drcyz_64-1024).
    TFRecord resized at the corresponding size to import on Tensorflow.


• Synthetic images from Neural Mars generated using Stylegan2-ada (drcyz/drcyz+).
  ∙ png 100; 1000; 10000 (drcyz/drcyz+/drcyz_256_100-10000)
    PNG files subset of 100, 1000 and 10000 at size 256x256.


• Network Checkpoint from Stylegan2-ada trained at size 256x256 (drcyz/model_drcyz).
  ∙ network-snapshot-000798-drcyz.pkl


• Notebooks in python to analyse the original dataset and reproduce the experiments; K-means Clustering, t-SNE, PCA, synthetic generation using Stylegan2-ada and instance segmentation using Deeplab (https://github.com/decurtoidiaz/drcyz/tree/main/dr_cyz+).
  ∙ clustering_curiosity_de_curto_and_de_zarza.ipynb
    K-means Clustering and PCA(2) with images from Curiosity.
  ∙ clustering_perseverance_de_curto_and_de_zarza.ipynb
    K-means Clustering and PCA(2) with images from Perseverance.
  ∙ tsne_curiosity_de_curto_and_de_zarza.ipynb
    t-SNE and PCA (components selected to explain 99% of variance) with images from Curiosity.
  ∙ tsne_perseverance_de_curto_and_de_zarza.ipynb
    t-SNE and PCA (components selected to explain 99% of variance) with images from Perseverance.
  ∙ Stylegan2-ada_de_curto_and_de_zarza.ipynb
    Stylegan2-ada trained on a subset of images from NASA Perseverance (DrCyZ).
  ∙ statistics_perseverance_de_curto_and_de_zarza.ipynb
    Compute statistics from synthetic samples generated by Stylegan2-ada (DrCyZ) and images from NASA Perseverance (CyZ).
  ∙ DeepLab_TFLite_ADE20k_de_curto_and_de_zarza.ipynb
    Example of instance segmentation using Deeplab with a sample from NASA Perseverance (DrCyZ).

Cropped Yale Face Dataset (Grayscale Images)

The Cropped Yale Face Dataset is a widely used benchmark in computer vision and machine learning for face recognition tasks. It consists of grayscale images of human faces captured under varying lighting conditions and expressions. The dataset is well-suited for research in facial recognition, image preprocessing, and machine learning model evaluation.

Dataset Overview

Example of Dataset Structure

CroppedYale/
├── yaleB01/
│  ├── yaleB01_P00A+000E+00.pgm
│  ├── yaleB01_P00A+000E+05.pgm
│  └── ...
├── yaleB02/
│  └── ...
└── ...

• Each folder corresponds to a single subject.
• File naming convention: yaleB<subject_id>_P<pose>A<ambient>E<expression>.pgm.

Example Use Cases

1. Face Recognition

The dataset is perfect for evaluating facial recognition algorithms under controlled lighting and expression variations.

from sklearn.decomposition import PCA
from sklearn.svm import SVC
import numpy as np

# Load images and flatten
X = images.reshape(len(images), -1)
y = labels

# Reduce dimensions using PCA
pca = PCA(n_components=100)
X_pca = pca.fit_transform(X)

# Train classifier
clf = SVC(kernel='linear')
clf.fit(X_pca, y)

2. Dimensionality Reduction

Due to its moderate image size, the dataset is ideal for testing dimensionality reduction methods like PCA, LDA, or t-SNE.

from sklearn.manifold import TSNE
import matplotlib.pyplot as plt

X_embedded = TSNE(n_components=2).fit_transform(X_pca)
plt.scatter(X_embedded[:,0], X_embedded[:,1], c=y)
plt.show()

3. Lighting & Expression Robustness

Researchers can use this dataset to study the effect of lighting conditions and facial expressions on recognition accuracy.

• yaleB01_P00A+000E+00.pgm → Normal expression
• yaleB01_P00A+000E+05.pgm → Smiling expression
• yaleB01_P00A+010E+00.pgm → Slightly rotated face

Key Advantages

• Controlled environment: Minimal background noise, making it easier to focus on the face features.
• Diverse lighting conditions: Excellent for testing illumination-invariant algorithms.
• Compact size: Easy to load and experiment with on most machines without high computational cost.
• Grayscale: Simplifies preprocessing while still retaining critical facial features.