A Feature Level Fusion in Similarity Matching to Content-Based Image Retrieval

Rahman, Md. Mahmudur; Desai, Bipin C.; Bhattacharya, Prabir

doi:10.1109/icif.2006.301664

Cited by 11 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The histograms of each six captured images from both the portrait and reference image are computed. The Chi-square and Bhattacharyya distance are used for measuring the difference of histograms [15] and [16], shown in Table 1. The small values in Table 1 reveal that the histograms are heavily correlated and indicate that the images have been captured in highly correlated light conditions as far as the intensity information of each two captured images of the portrait and reference image are almost remained the same.…”

Section: Measurement Resultsmentioning

confidence: 99%

Towards Measuring of Depth Perception from Monocular Shadow Technique with Application in a Classical Painting

Wei

Khatibi

2016

JCP

View full text Add to dashboard Cite

Depth perception is one of important abilities of the human visual system to perceive the three dimensional world. Shadow technique that offers different depth information from different viewing points, known as Da Vinci stereopsis, has been used in classical paintings. In this paper, we report a method towards measuring the relative depth information stimulated by Da Vinci stereopsis in a classical painting. We set up a positioning array of cameras for capturing images from the portrait using a high resolution camera, where the changes of shadow areas are measured by featuring the effects as point and line changes. The result shows that 3D effects of the classical painting are not only a perceptual phenomenon but they are also physically tangible and can be measured. We confirm validity of the method by its implementation even on a typical single image and comparison of results between the single image and the portrait.

show abstract

Section: Measurement Resultsmentioning

confidence: 99%

Towards Measuring of Depth Perception from Monocular Shadow Technique with Application in a Classical Painting

Wei

Khatibi

2016

JCP

View full text Add to dashboard Cite

show abstract

“…In this work the results cover only classifier fusion and rock images, not natural scenes. In [6], a content based image retrieval task is carried out with a fusion based weighted similarity matching function with experimentally selected weights. The highest weight is assigned to the similarity measure that appears to be the most accurate among the global, semi-global and local similarity measures.…”

Section: Introductionmentioning

confidence: 99%

Fusing image representations for classification using support vector machines

Demirkesen

Cherifi

2009

2009 24th International Conference Image and Vision Computing New Zealand

View full text Add to dashboard Cite

International audienceIn order to improve classification accuracy different image representations are usually combined. This can be done by using two different fusing schemes. In feature level fusion schemes, image representations are combined before the classification process. In classifier fusion, the decisions taken separately based on individual representations are fused to make a decision. In this paper the main methods derived for both strategies are evaluated. Our experimental results show that classifier fusion performs better. Specifically Bayes belief integration is the best performing strategy for image classification task

show abstract