Feature-level Fusion of Dual-band Infrared Images Based on Gradient Pyramid Decomposition

Qu, Xiujie; Zhang, Fu; Zhang, Ying

doi:10.2991/iccsee.2013.571

Cited by 6 publications

(8 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A gradient pyramid [21] for image I can be obtained by applying a gradient operator to each level of its Gaussian pyramid representation. The image can be represented by a set of four gradient pyramids one for each derivatives in horizontal, vertical and the two diagonal directions.…”

Section: Gradient Pyramidmentioning

confidence: 99%

Evaluation of Spatial and Transform Fusion methods for Medical Images using Normalized Non-Reference Quality Metrics

Barani¹,

Sumathi²

2016

IJCA

View full text Add to dashboard Cite

Medical image fusion is a method which enhances the image content by combining the images obtained using different imaging modalities like Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET) and Single Photon Emission Computed Tomography (SPECT). The main objective of medical image fusion is to extract and merge the useful information from multi-modality medical images thus highlighting the significant features for improved prediction of the scenario for treatment planning. In this paper, the different image fusion techniques in spatial and transform domain are implemented for MRI/CT and PET/CT images. The resultant fused images are analyzed with non-reference image quality metrics: Entropy (EN), Standard Deviation (SD), Peak Signal to Noise Ratio (PSNR), Spatial Frequency (SF), Average Gradient (AG), Edge Strength (ES), Fusion Factor (FF) and Fusion Symmetry (FS). It is found that the image fusion using Discrete Wavelet Transform (DWT) outperforms all the other spatial and pyramid based fusion methods.

show abstract

Section: Gradient Pyramidmentioning

confidence: 99%

Evaluation of Spatial and Transform Fusion methods for Medical Images using Normalized Non-Reference Quality Metrics

Barani¹,

Sumathi²

2016

IJCA

View full text Add to dashboard Cite

show abstract

“…and one of the most important measurement for Infrared images ,due to the difficulty of distinguishing objects from their background, local contrast important to identify objects and also in the trace. It can be calculated from this equation [10]: 9…”

Section: Local Contrastmentioning

confidence: 99%

“…Average gradient is a way to measure the resolution and contrast of the images, it refer to the clarity of details in the image. If the average gradient is high the resolution of the image will be higher also which mean that the image is enhanced further [10]. 10…”

Section: Average Gradientmentioning

confidence: 99%

See 2 more Smart Citations

Enhancement of IR Images using Homomorphic Filtering in Fast Discrete Curvelet Transform (FDCT)

Ein-shoka¹,

Kelash²,

Faragallah³

et al. 2014

IJCA

View full text Add to dashboard Cite

This paper presents an efficient model for enhancement of Infrared images. The proposed method is employing homomorphic filtering in the Fast Discrete Curvelet Transform (FDCT). It based on mixing the advantages of FDCT for representing curves and clarifying features on it with Homomorphic filtering which is an efficient method for enhancing the appearance of IR images. Also, we investigate the influence of FDCT coefficients on the Infrared images. The proposed method gives good results with respect to objective and subjective measurements when using only the first and last FDCT coefficients.

show abstract

Image Fusion of Infrared Weak-Small Target Based on Wavelet Transform and Feature Extraction

et al. 2020

View full text Add to dashboard Cite

The image details and contour information cannot be fully reflected for the current infrared single-band data. It is difficult for the weak-small target to resist background interference after imaging, so that the image produces a low ratio of signal-to-noise. Therefore, it is necessary to use the texture difference of different band data to improve the signal-to-noise ratio of the image by using the complementary fusion method. Based on the above-mentioned, a fusion method based on wavelet transform and feature extraction is proposed. Firstly, the source images are multi-scale and two-dimensionally decomposed to obtain low-frequency information and high-frequency information. And that, the high-frequency information adopt the method of maximizing the absolute value, the low-frequency information adopt the method of weighted averaging, and reconstruct the image. Then, the infrared feature extraction method is used to obtain the medium wave and long wave feature images. Finally, the reconstructed image is contrast-modulated and refused with the medium-long wave infrared feature image. The fusion results are compared with a variety of fusion algorithms. The experimental results show that the algorithm can enhance the gray scale of weak-small targets in the image, which can identify the target well and solve the problem of weak target against background interference in infrared images.

show abstract

Feature-level Fusion of Dual-band Infrared Images Based on Gradient Pyramid Decomposition

Cited by 6 publications

References 1 publication

Evaluation of Spatial and Transform Fusion methods for Medical Images using Normalized Non-Reference Quality Metrics

Evaluation of Spatial and Transform Fusion methods for Medical Images using Normalized Non-Reference Quality Metrics

Enhancement of IR Images using Homomorphic Filtering in Fast Discrete Curvelet Transform (FDCT)

Image Fusion of Infrared Weak-Small Target Based on Wavelet Transform and Feature Extraction

Contact Info

Product

Resources

About