A gradient-based hybrid image fusion scheme using object extraction

Ghantous, Milad; Ghosh, S.; Bayoumi, Magdy

doi:10.1109/icip.2008.4712001

Cited by 16 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…By successively filtering and down sampling process, the image is fused. Then, the image pyramid has the original image as the pyramid base with successive levels that are low-pass filtered and down sampled view of the level below is generated (Ghantous et al, 2008).…”

Section: Development and Evaluation Of Image Fusion Techniquesmentioning

confidence: 99%

Survey and analysis of various image fusion techniques for clinical CT and MRI images

Tamilselvan

Murugesan

2014

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The research and development of biomedical imaging techniques requires more number of image data from medical image acquisition devices, like computed tomography (CT), magnetic resonance imaging (MRI), positron emission technology, and single photon emission computed tomography. Multimodal image fusion is the process of combining information from various images to get the maximum amount of content captured by a single image acquisition device at different angles and different times or stages. This article analyses and compares the performance of different existing image fusion techniques for the clinical images in the medical field. The fusion techniques compared are simple or pixel-based fusion, pyramid-based fusion, and transform-based fusion techniques. Four set of CT and MRI images are used for the above fusion techniques. The performance of the fused results is measured with seven parameters. The experimental results show that out of seven parameters the values of four parameters, such as average difference, mean difference, root mean square error, and standard deviation are minimum and the values of remaining three parameters, such as peak signal to noise ratio, entropy, and mutual information are maximum. From the experimental results, it is clear that out of 14 fusion techniques taken for survey, image fusion using dual tree complex wavelet transform gives better fusion result for the clinical CT and MRI images. Advantages and limitations of all the techniques are discussed with their experimental results and their relevance.

show abstract

Section: Development and Evaluation Of Image Fusion Techniquesmentioning

confidence: 99%

Survey and analysis of various image fusion techniques for clinical CT and MRI images

Tamilselvan

Murugesan

2014

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…Cada nível contém uma versão da imagem original filtrada por um filtro passa-baixas, denominada imagem de aproximação, e três imagens filtradas por filtros passa-altas (detalhes verticais, horizontais e diagonais) da imagem original, denominadas sub-imagens (imagens de detalhes) [6,7]. Os métodos de multi-resolução, em particular os que usam a transformada wavelet são os que produzem os melhores resultados no processo de fusão de imagens [8].…”

Section: Técnicas De Fusão De Imagensunclassified

Análise Comparativa de Métodos de Fusão de Imagens

Silva¹,

Pagliari²,

Silva³

et al. 2011

Anais De XXIX Simpósio Brasileiro De Telecomunicações

View full text Add to dashboard Cite

Resumo-Em geral, dados oriundos de regiões espectrais diferentes aumentam a qualidade da informação para o observador. Este artigo aborda a fusão de imagens oriundas da região da luz visível e da região do infra-vermelho. Um ponto crítico da fusão é a seleção dos pontos 'relevantes', em cada uma das imagens, a serem combinados. Diversas técnicas de fusão são aplicadas às imagens fonte, onde são avaliados os efeitos causados pelas diferentes combinações de medidas de informação 'relevante' e outros parâmetros, incluindo métodos de decisão na imagem combinada. Os resultados são comparados, objetivamente e perceptualmente, a fim de se estipular combinações ótimas de parâmetros de fusão entre imagens de diferentes faixas de frequência. Uma nova combinação de regras de fusão, que produz ótimos resultados, é uma outra contribuição deste artigo. Palavras-Chave-fusão de imagens, região do infravermelho, análise objetiva, análise subjetiva Abstract-In general, data from different spectral regions convey additional quality information to the observer. This article studies fusion of infrared and visible light images. A key point to any fusion scheme lies in the selection of 'relevant'(feature) points, on each image, to be fused. Several fusion techniques are applied to the original images, in order to evaluate the effects inflicted by the combination of 'relevant' information measures, and other parameters, such as fusion decision methods to the fused image. The results are, objectively and subjectively, compared in order to find optimal parameter combinations for fusion of infrared and visible imagery. A new combination of fusion rules, that produces very good results, is another contribution of this work.

show abstract

“…The fusion rule is applied in this case over the homogenous classes, allowing a better optimization of the fusion algorithm parameters. The obtained results are therefore more accurate, which implies that the coupling techniques can improve the global performances (Ghantous, Ghosh, and Bayoumi 2008;Yang and Blum 2006). Among the fast and accurate classification methods, we can cite the International Journal of Remote Sensing 7071…”

Section: Introductionmentioning

confidence: 97%

“…Moreover, for better results, fusion approaches are sometimes coupled with classification algorithms (Ghantous, Ghosh, and Bayoumi 2008;Yang and Blum 2006). The classification allows the decomposition of the image into homogeneous classes (Delleji, Zribi, and Hamida 2007).…”

Section: Introductionmentioning

confidence: 99%

Multispectral image adaptive pansharpening based on wavelet transformation and NMDB approaches

Delleji

Kallel

Hamida

2014

International Journal of Remote Sensing

View full text Add to dashboard Cite

In remote sensing, satellite images acquired from sensors provide either high spectral or high spatial resolution. The pansharpening framework is applied to remote-sensing systems to enhance the spatial quality of coarse-resolution multispectral (MS) images using information from panchromatic imagery. A multidecomposition pansharpening approach combining MS and panchromatic (PAN) images is proposed in this paper in order to bring the resolution of the low-resolution MS imagery up to that of the panchromatic images. In particular, multilevel wavelet decomposition is applied to the luminance-chrominance (YUV) space transformation (taking into account the red green and blue (RGB) bands) or extended-YUV transformation (taking into account the near infrared (NIR) band in addition to RGB) of the original MS channels, where geometrical details from the panchromatic image are introduced into the MS ones. Our approach contains a preprocessing step that consists of homogenizing the luminance, Y, and the panchromatic image reflectance, which are, respectively, a value integrated over a wavelength spectrum and simply a linear combination of some values in the same spectrum. Hence, as the panchromatic image reflectance and luminance reflectance correspond to different measurements, they do not correspond to the same physical information, which results in a difference between their histograms. Therefore, simple histogram matching is traditionally applied to panchromatic data to fit it to the luminance to avoid colour distortion after fusion. However, as the transformation concerns just the details of the panchromatic and MS images, a new scheme for matching the images which ignores the divergence between their approximations and maximizes the resemblance between their details is proposed in this work. After that, the fusion approach is applied, and in contrast to the original approach where the details of the fused MS luminance are set equal to the PAN luminance, we propose an adaptive approach in which just a part of the PAN details proportional to the similarity between the luminance and lowered PAN image is taken. Indeed, high-resolution geometrical details cannot be similar if the low-resolution details are not in good agreement. Besides, as the agreement between PAN and MS images depends on the occupation class, we have created a segmentation map and then computed separately the correlation in each region. Finally, the evaluation is done based on QuickBird and Pleiades-1A data sets showing rural and suburban areas. When compared to recent methods, our approach provides better results.

show abstract

A gradient-based hybrid image fusion scheme using object extraction

Cited by 16 publications

References 15 publications

Survey and analysis of various image fusion techniques for clinical CT and MRI images

Survey and analysis of various image fusion techniques for clinical CT and MRI images

Análise Comparativa de Métodos de Fusão de Imagens

Multispectral image adaptive pansharpening based on wavelet transformation and NMDB approaches

Contact Info

Product

Resources

About