Journal of Frontiers of Computer Science and Technology ›› 2024, Vol. 18 ›› Issue (9): 2449-2465.DOI: 10.3778/j.issn.1673-9418.2308052

• Graphics·Image • Previous Articles     Next Articles

No-Reference Low-Light Image Enhancement with Enhanced Feature Map

YUAN Heng, WANG Xiaoxue, ZHANG Shengchong   

  1. 1. College of Software, Liaoning Technical University, Huludao, Liaoning 125105, China
    2. Key Laboratory of Optoelectronic Information Control and Security Technology, Tianjin 300308, China
  • Online:2024-09-01 Published:2024-09-01

强化特征图的无参考低光照图像增强

袁姮,王笑雪,张晟翀   

  1. 1. 辽宁工程技术大学 软件学院,辽宁 葫芦岛 125105
    2. 光电信息控制和安全技术重点实验室,天津 300308

Abstract: Since low-light images are of poor quality and carry noise, resulting in insufficient contrast and brightness, unclear details in the image, and the problem of high cost of obtaining paired low-light image datasets, a no-reference low-light image enhancement method for feature map enhancement is proposed under the influence of the Mach band effect of biological vision. Firstly, the model uses the enhanced filter block (EFB) to enhance the feature of images and feature maps, which can suppress noise and enhance the feature details to improve the ability of the network to learn features. Then, skip connection is combined with efficient spatial attention (ESA) module to extract global context information and local regional features by fusing enhanced shallow features and deep features, which effectively retains image color information, avoids detail loss, and improves the generalization ability of the network. Finally, the pixel estimation curve is used to adjust the dynamic range of the pixels in the low-light image and enhance the brightness of the low-light image. Experimental results show that the PSNR, SSIM, LPIPS and NIQE of the image processed by the algorithm reach 17.709 dB, 0.657, 0.239 and 3.486 respectively. Compared with the existing mainstream algorithms, it can better achieve the purpose of image enhancement, and effectively improves the image brightness and detail information, while maintaining the naturalness of the image.

Key words: image enhancement, biological vision mechanism, enhanced feature map, no-reference method, attention mechanism, image processing

摘要: 针对低光照图像质量不佳、夹杂噪声导致对比度和亮度不足、细节不清晰,且成对的低光照图像数据集获取成本过高的问题,在生物视觉马赫带效应的启发下,提出一种强化特征图的无参考低光照图像增强方法。使用强化滤波块(EFB)对图像和特征图进行特征强化,抑制噪声的同时强化特征细节,提高网络对特征的学习能力。将跳跃连接与空间注意力模块(ESA)结合,通过融合强化的浅层特征与深层特征来提取全局上下文信息和局部区域特征,有效保留了图像的色彩信息,避免细节丢失,提高网络的泛化能力。使用像素估计曲线调整低光照图像像素的动态范围,对其进行亮度增强。实验结果表明,经该算法处理后的图像在PSNR、SSIM、LPIPS和NIQE等指标上分别达到了17.709 dB、0.657、0.239和3.486,该方法相较于现有的主流算法能够更好地达到图像增强目的,有效地提升图像亮度和细节信息,同时保持图像的自然属性。

关键词: 图像增强, 生物视觉机制, 强化特征图, 无参考方法, 注意力机制, 图像处理