IEEE Trans Image Process. 2019 May;28(5):2107-2115. doi: 10.1109/TIP.2018.2881830. Epub 2018 Nov 16.
Defocus blur detection is an important and challenging task in computer vision and digital imaging fields. Previous work on defocus blur detection has put a lot of effort into designing local sharpness metric maps. This paper presents a simple yet effective method to automatically obtain the local metric map for defocus blur detection, which based on the feature learning of multiple convolutional neural networks (ConvNets). The ConvNets automatically learn the most locally relevant features at the super-pixel level of the image in a supervised manner. By extracting convolution kernels from the trained neural network structures and processing it with principal component analysis, we can automatically obtain the local sharpness metric by reshaping the principal component vector. Meanwhile, an effective iterative updating mechanism is proposed to refine the defocus blur detection result from coarse to fine by exploiting the intrinsic peculiarity of the hyperbolic tangent function. The experimental results demonstrate that our proposed method consistently performed better than the previous state-of-the-art methods.
散焦模糊检测是计算机视觉和数字成像领域中的一项重要且具有挑战性的任务。先前在散焦模糊检测方面的工作主要集中在设计局部锐度度量图上。本文提出了一种简单而有效的方法，通过多个卷积神经网络（ConvNets）的特征学习，自动获取用于散焦模糊检测的局部度量图。ConvNets 以监督的方式自动学习图像的超像素级别的最局部相关特征。通过从训练好的神经网络结构中提取卷积核，并对其进行主成分分析处理，我们可以通过重塑主成分向量自动获得局部锐度度量。同时，我们还提出了一种有效的迭代更新机制，通过利用双曲正切函数的内在特性，从粗到精地细化散焦模糊检测结果。实验结果表明，我们提出的方法始终优于先前的最先进方法。
