How to Cite
Abstract
Avaliação da qualidade da imagem é a medição de um atributo (propriedades ou características) de uma determinada imagem. Esta é utilizada em diversas aplicações na área de processamento de imagens. A qualidade da imagem pode ser avaliada por duas metodologias distintas, forma subjetiva ou objetiva. O método objetivo quantifica a qualidade da imagem de forma automática, havendo ou não a imagem ideal de referência. O método subjetivo faz uso da opinião de um observador, sendo este um método mais caro. Este artigo apresenta uma revisão de métodos objetivos sem referência da avaliação da qualidade de imagem. Foram abordadas as principais características dos algoritmos de evolução, neural e de Ruídos e Borramento, todos sem a utilização de uma imagem como referência. Baseando-se nos resultados satisfatórios apresentados, o estudo e comparação destas métricas podem ser aprofundados de forma prática em futuros trabalhos.
Palavras-chave: Avaliação da Qualidade de Imagem (AQI). Método objetivo. Método sem referência. Algoritmo evolutivo. Algoritmo neural. Borramento e ruído.
Studies of methods for blind image quality assessment
Abstract
Image Quality Evaluation is the measurement of an attribute (properties or characteristics) of a given image. It is used in several applications in the field of image processing. The quality of the image can be evaluated in two different methods: subjective and objective. The objective method quantifies the image quality automatically, with or without the ideal image reference. The subjective method uses the opinion of an observer; however, it is more expensive. This paper presents a review of the objective method with no reference of the image quality evaluation. The survey covered the main features of evolutionary, neural and Noise and Blurring algorithms. All of them had no use of an image as reference. Based on the satisfactory results presented, the study and the comparison of these metrics may undergo a more practical approach in future works.
Keywords: Image Quality Evaluation (IQA). Objective method. No reference method. Evolutionary algorithm. Neural algorithm. Blur and noise.
References
CARDON, A.; MULLER, D. N. Introdução às redes neurais artificiais. 1994. Dissertação (Curso de Pós Graduação e Ciência da Computação) Instituto de Informática, Universidade Federal do Rio Grande do Sul: Porto Alegre, 994.
CHOI, M. G.; JUNG, J. H.; JEON, J. W. No-Reference image quality assessment using Blur and Noise. World Academy of Science, Engineering and Technology, n. 12, v. 28. p 163-167, jan. 2009.
DIMAURO,G. A new image quality metric based on human visual system. In: IEEE INTERNATIONAL CONFERENCE ON VIRTUAL ENVIRONMENTS HUMAN-COMPUTER INTERFACES AND MEASUREMENT SYSTEMS (VECIMS), 2012, Tianjin. Proceedings... Disponível em: <http://ieeexplore.ieee.org/xpl/articleDetails.jsp?
arnumber=6273216>. Acesso em: 16 jun. 2013.
DOSSELMANN, R.; YANG, X. D. No-Reference image quality assessment using Level-of-Detail, 2011. Department of Computer Science, University of Regina, Regina, Canadá, maio 2011.
GEORGE, A. G.; PRABATHY, A. K. A Survey On different approaches used in image quality assessment. International Journal of Emerging Technology and Advanced Engineering, Coimbatore, India, n. 2, v. 3, fev. 2013.
GONZALEZ, R. C.; WOODS, R. Processamento de imagens digitais. 1. ed. São Paulo: Edgard Blucher, 2000.
SURESH, S. No-reference image quality assessment using modified extreme learning machine classifier. Applied Soft Computing, Seoul, n. 2, v. 9. p. 541-552, mar. 2009.
THUNG, K. H.; RAVEENDRAN, P. A survey of image quality measures. In: INTERNATIONAL CONFERENCE FOR TECHNICAL POSTGRADUATES (TECHPOS), 2009, Kuala Lumpur. Proceedings... Disponível em:
articleDetails.jsp?arnumber=5412098>. Acesso em: 21 mar. 2013.
VENKATESH BABU, R. No-reference JPEG-image quality assessment using GAP-RBF. Signal Processing, Singapura, p. 1493-1503, jun. 2007.
Authors who post on ForScience agree to the following terms:
- The said work is of own authorship and has never been published or sent to another magazine, this magazine having the right of exclusivity on the edition and publication, under the license Creative Commons Attribution License 3.0 (CC-BY-NC) which allows anyone to share to adapt the work according to the following terms:
Atribuição — You must give the appropriate credit, provide a link to the license and indicate if the changes have been made. You must do so in any reasonable circumstance, but in no way do you suggest to the licensor to support you or your use.
Non-Commercial — You may not use the material for commercial purposes.
- If plagiarism has been proven in any published work, this Journal is free of any responsibility, and its author (s) shall bear the penalties provided by law.
- Authors are authorized to take additional contracts separately, for non-exclusive distribution of the version of the work published in this journal (eg, publish in institutional repository or as a book chapter), with acknowledgment of authorship and initial publication in this journal.
- Authors are allowed and encouraged to publish and distribute their work online (eg in institutional repositories or on their personal page), as this can generate productive changes, as well as increase the impact and citation of the published work. However, it should be noted that once approved by the evaluators, the manuscript can not be changed. If the author wishes to do so, he should restart the submission process.