Identificação e Classificação de Imagens Publicitárias Quanto à Qualidade Utilizando Aprendizado de Máquina

  • Evandro Oliveira UFP
  • Ana Carolina Costa UFC
  • Cícero Moura PUC Minas

Resumo


Este trabalho sugere um método para a predição da qualidade estética de imagens com o objetivo de filtrar imagens que seriam classificadas como ruins conforme a opinião do anotador. Para tal, são utilizadas técnicas de aprendizagem profunda em um conjunto de dados com imagens sintéticas de caráter publicitário. A abordagem sugerida é comparada com outros métodos já existentes para inferir a qualidade da imagem considerando o Coeficiente Pearson e Acurácia em conjuntos de imagens avaliadas numa escala de boa a ruim. Os resultados dos experimentos mostram que a ResNet50 se mostra mais eficiente do que os modelos NIMA e Koncept512, chegando em 33% de melhora em relação às correlações e melhora de 11% em relação ao MicroF1.

Referências

Esfandarani, H. T. and Milanfar, P. (2017). NIMA: neural image assessment. CoRR, abs/1709.05424.

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778.

Hosu, V., Lin, H., Szirányi, T., and Saupe, D. (2019). Koniq-10k: An ecologically valid database for deep learning of blind image quality assessment. CoRR, abs/1910.06180.

Isola, P., Zhu, J.-Y., Zhou, T., and Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1125–1134.

Li, Y., Po, L., Feng, L., and Yuan, F. (2016). No-reference image quality assessment with deep convolutional neural networks. pages 685–689.

Liu, S. and Forss, T. (2015). New classification models for detecting hate and violence web content. In 2015 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K), volume 01, pages 487–495.

Mohey El-Din, D. (2016). A survey on sentiment analysis challenges. Journal of King Saud University - Engineering Sciences, pages –.

Murray, N., Marchesotti, L., and Perronnin, F. (2012). Ava: A large-scale database for aesthetic visual analysis. In 2012 IEEE Conference on Computer Vision and Pattern Recognition, pages 2408–2415.

Ortis, A., Farinella, G., and Battiato, S. (2019). An overview on image sentiment analysis: Methods, datasets and current challenges. pages 290–300.

Papagiannopoulou, E. and Tsoumakas, G. (2020). A review of keyphrase extraction. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(2):e1339.

Pelle, R., Alcântara, C., and Moreira, V. (2018). A classifier ensemble for offensive text detection. pages 237–243.

Pitsilis, G. K., Ramampiaro, H., and Langseth, H. (2018). Detecting offensive language in tweets using deep learning. CoRR, abs/1801.04433.

Schmidt, A. and Wiegand, M. (2017). A survey on hate speech detection using natural language processing. In Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media, pages 1–10, Valencia, Spain. Association for Computational Linguistics.

Shahid, M., Rossholm, A., Lovstrom, B., and Zepernick, H.-J. (2014). No-reference image and video quality assessment: a classification and review of recent approaches. EURASIP Journal on Image and Video Processing, 2014.

Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2818–2826.

Wang, B., Chen, B., Ma, L., and Zhou, G. (2019). User-personalized review rating prediction method based on review text content and user-item rating matrix. Information, 10(1).

Xu, G., Yu, Z., Yao, H., Li, F., Meng, Y., and Wu, X. (2019). Chinese text sentiment analysis based on extended sentiment dictionary. IEEE Access, 7:43749–43762.

Zhai, G. and Min, X. (2020). Perceptual image quality assessment: a survey. Science China Information Sciences, 63:1–52.

Zhang, R., Isola, P., Efros, A. A., Shechtman, E., and Wang, O. (2018). The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 586–595.

Zhu, J.-Y., Park, T., Isola, P., and Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223–2232.
Publicado
25/10/2022
OLIVEIRA, Evandro; COSTA, Ana Carolina; MOURA, Cícero. Identificação e Classificação de Imagens Publicitárias Quanto à Qualidade Utilizando Aprendizado de Máquina. In: ESCOLA REGIONAL DE INFORMÁTICA DE GOIÁS (ERI-GO), 10. , 2022, Goiás. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 72-81. DOI: https://doi.org/10.5753/erigo.2022.227717.