Optimizing dual energy X-ray image enhancement using a novel hybrid fusion method

Area of Science:

• Image processing
• Signal processing
• Security technology

Background:

• Airport security relies heavily on Dual-Energy X-ray Imaging (DEXI) for detecting concealed items.
• Image noise in DEXI compromises the accuracy of object identification, posing a security risk.

Purpose of the Study:

• To develop and validate a robust denoising technique for DEXI images.
• To address noise interference and enhance object recognition in airport security screening.

Main Methods:

• Utilized Discrete Wavelet Transform (DWT) and Stationary Wavelet Transform (SWT) for image denoising.
• Applied thresholding techniques to subbands for noise reduction while preserving image details.
• Reconstructed images to achieve a clearer representation for analysis.

Main Results:

• The DWT and SWT-based denoising effectively suppressed noise in DEXI images.
• Achieved an average Peak Signal-to-Noise Ratio (PSNR) of 35.23 and Mean Squared Error (MSE) of 19.52 for 256x256 images.
• Attained an average PSNR of 36.01 and MSE of 16.29 for 512x512 images, demonstrating significant noise reduction.

Conclusions:

• The proposed denoising approach significantly enhances DEXI image quality.
• This technique shows strong potential for improving the effectiveness of airport security screening systems.