School of Microelectronics and Communications Engineering, Chongqing University, Chongqing 400044, China.
Sensors (Basel). 2022 May 11;22(10):3667. doi: 10.3390/s22103667.
Dealing with low-light images is a challenging problem in the image processing field. A mature low-light enhancement technology will not only be conductive to human visual perception but also lay a solid foundation for the subsequent high-level tasks, such as target detection and image classification. In order to balance the visual effect of the image and the contribution of the subsequent task, this paper proposes utilizing shallow Convolutional Neural Networks (CNNs) as the priori image processing to restore the necessary image feature information, which is followed by super-pixel image segmentation to obtain image regions with similar colors and brightness and, finally, the Attentive Neural Processes (ANPs) network to find its local enhancement function on each super-pixel to further restore features and details. Through extensive experiments on the synthesized low-light image and the real low-light image, the experimental results of our algorithm reach 23.402, 0.920, and 2.2490 for Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM), and Natural Image Quality Evaluator (NIQE), respectively. As demonstrated by the experiments on image Scale-Invariant Feature Transform (SIFT) feature detection and subsequent target detection, the results of our approach achieve excellent results in visual effect and image features.
处理低光照图像是图像处理领域的一个具有挑战性的问题。成熟的低光照增强技术不仅有助于人类视觉感知，而且为后续的高级任务（如目标检测和图像分类）奠定了坚实的基础。为了平衡图像的视觉效果和后续任务的贡献，本文提出利用浅层卷积神经网络（CNNs）作为先验图像处理来恢复必要的图像特征信息，然后进行超像素图像分割，以获得颜色和亮度相似的图像区域，最后使用注意力神经过程（ANPs）网络在每个超像素上找到其局部增强函数，以进一步恢复特征和细节。通过对合成低光照图像和真实低光照图像进行广泛的实验，我们算法的实验结果在峰值信噪比（PSNR）、结构相似性（SSIM）和自然图像质量评估器（NIQE）方面分别达到 23.402、0.920 和 2.2490。通过对图像尺度不变特征变换（SIFT）特征检测和随后的目标检测的实验表明，我们的方法在视觉效果和图像特征方面都取得了优异的结果。
