基于独立分量分析的红外热波无损检测图像增强

摘要

A method of image enhancing based on Independent Component Analysis（ICA） is presented for infrared（IR） thermal images that acquired by an IR camera in the test system and always have the problem of low- contrast and high-noise, which can effectively eliminate the noise interference of the images and enhance defect contrast. The fundamental theory of ICA and Fast ICA algorithm based on negative entropy criterion is introduced. The detailed processes of the method and results are given. The results of the experiments show that the method has higher peak signal to noise ratio（PSNR） and can improve image quality, which establishes basis for future research of image segmentation.%在红外热波无损检测过程中，热像图存在低对比度、高噪声的问题。提出一种基于独立分量分析的图像增强方法，该方法能够有效地去除热像图中噪声的干扰，提高缺陷的对比度。阐述了ICA的基本原理，介绍了基于负熵判据的FastICA算法，给出了该方法在热像图增强处理中的具体实现步骤及相应的试验处理结果。结果表明，该方法具有较大的峰值信噪比，可提高图像质量，改善图像的可视性，为后续的图像分割等研究奠定基础。