Convolutional Neural Network for Blur Images Detection as an Alternative for Laplacian Method
This addresses the need for non-manual image quality assessment in digital photography, but it is incremental as it applies an existing deep learning approach to a known task.
The paper tackled the problem of automated blur detection in digital images by proposing a convolutional neural network (CNN) method, which was evaluated and shown to be effective compared to deterministic methods using a confusion matrix.
With the prevalence of digital cameras, the number of digital images increases quickly, which raises the demand for non-manual image quality assessment. While there are many methods considered useful for detecting blurriness, in this paper we propose and evaluate a new method that uses a deep convolutional neural network, which can determine whether an image is blurry or not. Experimental results demonstrate the effectiveness of the proposed scheme and are compared to deterministic methods using the confusion matrix.