Abstract
The detection of poor quality images for reasons such as focus, lighting, compression, and encoding is of great importance in the field of computer vision. The ability to quickly and automatically classify an image as poor quality creates opportunities for a multitude of applications such as digital cameras, phones, self-driving cars, and web search technologies. In this paper an end-to-end approach using Convolutional Neural Networks (CNN) is presented to classify images into six categories of bad lighting, Gaussian blur, motion blur, JPEG 2000, white-noise, and high quality reference images. A new dataset of images was produced and used to train and validate the model. Finally, the application of the developed model was evaluated using images from the German Traffic Sign Recognition Benchmark. The results show that the trained CNN can detect and correctly classify images into the aforementioned categories with high accuracy and the model can be easily re-calibrated for other applications with only a small sample of training images.
Similar content being viewed by others
References
Aghdam HH, Heravi EJ (2017) Guide to convolutional neural networks. New York, NY: Springer. doi 10:225–226
Ahmed WS et al (2020) The impact of filter size and number of filters on classification accuracy in cnn. In: 2020 International conference on computer science and software engineering (CSASE), pp 88–93. IEEE
Bianco S, Celona L, Napoletano P, Schettini R (2018) On the use of deep learning for blind image quality assessment. SIViP 12(2):355–362
Brinded M (2011) Computer vision methods for detection of blurry photographs. Ph.D. Thesis, University of Leeds, School of Computing Studies
Chung Y-C, Wang J-M, Bailey RR, Chen S-W, Chang S-L (2004) A non-parametric blur measure based on edge analysis for image processing applications. In: Cybernetics and intelligent systems, 2004 IEEE conference on, vol 1, pp 356–360. IEEE
Da Rugna J, Konik H (2003) Automatic blur detection for meta-data extraction in content-based retrieval context. In: Internet imaging V, vol 5304, pp 285–295. International society for optics and photonics
Golchubian A, Marquez O, Nojoumian M (2020) Photo quality classification using deep learning - dataset and programming. https://github.com/agolchub/Photo_Quality_Classification
Golestaneh SA, Karam LJ (2017) Spatially-varying blur detection based on multiscale fused and sorted transform coefficients of gradient magnitudes. In: CVPR, pp 596–605
Gu K, Zhai G, Lin W, Yang X, Zhang W (2015) No-reference image sharpness assessment in autoregressive parameter space. IEEE Trans Image Process 24(10):3218–3231
Hsu P, Chen B-Y (2008) Blurred image detection and classification. In: International conference on multimedia modeling, pp 277–286. Springer
Liu R, Li Z, Jia J (2008) Image partial blur detection and classification. In: Computer vision and pattern recognition, 2008. CVPR 2008. IEEE Conference on, pp 1–8. IEEE
Liu W, Lin W (2013) Additive white gaussian noise level estimation in svd domain for images. IEEE Transactions on Image processing 22(3):872–883
Marziliano P, Dufaux F, Winkler S, Ebrahimi T (2002) A no-reference perceptual blur metric. In: Image processing. 2002. Proceedings. 2002 international conference on, vol 3, pp III–III. IEEE
Sheikh HR, Wang Z, Cormack L, Bovik AC (2005) Live image quality assessment database release 2 (2005)
Stallkamp J, Schlipsing M, Salmen J, Igel C (2012) Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition. Neural networks 32:323–332
Su B, Lu S, Tan CL (2011) Blurred image region detection and classification. In: Proceedings of the 19th ACM international conference on multimedia, pp 1397–1400. ACM
Tang X, Luo W, Wang X (2013) Content-based photo quality assessment. IEEE Transactions on Multimedia 15(8):1930–1943
Tong H, Li M, Zhang H, Zhang C (2004) Blur detection for digital images using wavelet transform. In: Multimedia and Expo, 2004. ICME’04. 2004 IEEE International Conference on, vol 1, pp 17–20. IEEE
Tsomko E, Kim H J, Paik J, Yeo I-K (2008) Efficient method of detecting blurry images. Journal of Ubiquitous Convergence Technology 2(1):pp–27
Yang SJ, Berndl M, Ando DM, Barch M, Narayanaswamy A, Christiansen E, Hoyer S, Roat C, Hung J, Rueden CT et al (2018) Assessing microscope image focus quality with deep learning. BMC bioinformatics 19(1):77
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Golchubian, A., Marques, O. & Nojoumian, M. Photo quality classification using deep learning. Multimed Tools Appl 80, 22193–22208 (2021). https://doi.org/10.1007/s11042-021-10766-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-10766-7