Quality and Randomness Assessment of Images Generated by a Convolutional Autoencoder

Rafael Castaneda-Diaz; Daniela López-Betancur; Carlos  Guerrero-Méndez; Efrén González-Ramírez; Salvador Gómez-Jiménez; Flossi Puma-Ttito

doi:10.61467/2007.1558.2026.v17i2.952

Authors

Rafael Castaneda-Diaz Instituto Politécnico Nacional https://orcid.org/0009-0008-2867-1734
Daniela López-Betancur Unidad Académica de Ciencia y Tecnología de la Luz y la Materia, Universidad Autónoma de Zacatecas https://orcid.org/0000-0003-0710-6062
Carlos Guerrero-Méndez Unidad Académica de Ciencia y Tecnología de la Luz y la Materia, Universidad Autónoma de Zacatecas https://orcid.org/0000-0003-0721-8515
Efrén González-Ramírez Universidad Autónoma de Zacatecas https://orcid.org/0000-0002-8060-6170
Salvador Gómez-Jiménez Universidad Autónoma de Zacatecas https://orcid.org/0000-0001-6654-3313
Flossi Puma-Ttito Unidad Académica de Ciencia y Tecnología de la Luz y la Materia, Universidad Autónoma de Zacatecas https://orcid.org/0000-0001-6692-0991

DOI:

https://doi.org/10.61467/2007.1558.2026.v17i2.952

Keywords:

Autoencoder, Artificial Neural Networks, Similarity Structural Index Measure, Pearson Correlation Coefficient, Peak Signal-to-Noise Ratio, Shannon Metric

Abstract

This paper presents an analysis of the quality and randomness of information in images generated with a convolutional autoencoder (CAE). The CAE convolved altered color images from CIFAR-10 dataset. The CIFAR-10 images were altered by randomly setting 30%, 60%, and 90% of pixel values to [0, 0, 0] or [255, 255, 255], respectively. In the validation stage, Mean Square Error (MSE) loss function reached 0.0115 and the accuracy metric 0.7461. Similarity Structural Index Measure (SSIM), Pearson Correlation Coefficient (PCC) and Peak Signal-to-Noise Ratio (PSNR) metrics, assessed quality of generated images. The assessment results ranged as follows: SSIM [0.3251, 0.6830], PCC [0.5034, 0.9358], and PSNR [18.63 dB, 26.04 dB]. The Shannon metric assessed randomness both locally and globally for each image, ranging from 1.25 to 2.49 bits, and from 6.61 to 9.71 bits, respectively. CAE implementations highlight their potential for applications in technological innovation.

Smart citations: https://scite.ai/reports/10.61467/2007.1558.2026.v17i2.952
Dimensions.
Open Alex.

References

Старовойтов, В. В. (2019). Индекс SSIM не является метрикой и плохо оценивает сходство изображений. Системный анализ и прикладная информатика, 2, 12–17. https://doi.org/10.21122/2309-4923-2019-2-12-17

Fan, L., Zhang, F., Fan, H., & Zhang, C. (2019). Brief review of image denoising techniques. Visual Computing for Industry, Biomedicine, and Art, 2(1), 7. https://doi.org/10.1186/s42492-019-0016-7

Ghojogh, B., et al. (2019). Feature selection and feature extraction in pattern analysis: A literature review. arXiv. https://doi.org/10.48550/arXiv.1905.02845

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.

Ilesanmi, A. E., & Ilesanmi, T. O. (2021). Methods for image denoising using convolutional neural network: A review. Complex & Intelligent Systems, 7(5), 2179–2198. https://doi.org/10.1007/s40747-021-00428-4

Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv. https://doi.org/10.48550/arXiv.1412.6980

Krizhevsky, A. (2009). Learning multiple layers of features from tiny images (CIFAR-10 and CIFAR-100 datasets). https://www.cs.toronto.edu/~kriz/cifar.html

López-Betancur, D., Bosco Durán, R., Guerrero-Méndez, C., Zambrano Rodríguez, R., & Saucedo Anaya, T. (2021). Comparación de arquitecturas… Computación y Sistemas, 25(3), 601–615. https://doi.org/10.13053/cys-25-3-3453

López-Betancur, D., González-Ramírez, E., Guerrero-Méndez, C., Saucedo-Anaya, T., Rivera, M. M., Olmos-Trujillo, E., & Gómez-Jiménez, S. (2024). Evaluation of optimization algorithms for measurement of suspended solids. Water, 16(13), Article 1761. https://doi.org/10.3390/w16131761

Navarro-Solís, D., Guerrero-Méndez, C., Saucedo-Anaya, T., López-Betancur, D., Silva, L., Robles-Guerrero, A., & Gómez-Jiménez, S. (2024). Analysis of convolutional neural network models for classifying the quality of dried chili peppers (Capsicum annuum L.). En H. Calvo et al. (Eds.), Advances in Computational Intelligence: MICAI 2023 International Workshops (pp. 116–131). Springer. https://doi.org/10.1007/978-3-031-51940-6_10

Nilsson, J., & Akenine-Möller, T. (2020). Understanding SSIM. arXiv. http://arxiv.org/abs/2006.13846

Pappas, T. N., Safranek, R. J., & Chen, J. (2000). Perceptual criteria for image quality evaluation. In Handbook of image and video processing.

Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533–536. https://doi.org/10.1038/323533a0

Sparavigna, A. C. (2019). Entropy in image analysis. Entropy, 21(5), 502. https://doi.org/10.3390/e21050502

Venkataraman, P. (2022). Image denoising using convolutional autoencoder. arXiv. https://doi.org/10.48550/arXiv.2207.11771

Vincent, P., Larochelle, H., Bengio, Y., & Manzagol, P.-A. (2008). Extracting and composing robust features with denoising autoencoders. En Proceedings of the 25th International Conference on Machine Learning (ICML) (pp. 1096–1103). https://doi.org/10.1145/1390156.1390294

Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 600–612. https://doi.org/10.1109/TIP.2003.819861

Zhang, Y. (2018). A better autoencoder for image: Convolutional autoencoder [Manuscrito no publicado]. http://users.cecs.anu.edu.au/Tom.Gedeon/conf/ABCs2018/paper/ABCs2018_paper_58.pdf

Quality and Randomness Assessment of Images Generated by a Convolutional Autoencoder

Authors

DOI:

Keywords:

Abstract

References

Downloads

Published

How to Cite

Issue

Section

License

Most read articles by the same author(s)

Information

Current Issue