Actived Edge Strength for Image Quality Assessment

These years has witnessed the success of deep learning methods in computer vision. The approximation capabilities of neural networks is partly responsible for these success, and active function is crucial for the approximation capability. Motivated by the success of deep learning, this paper presents an Actived Edge Strength Similarity (AESSIM) based image quality assessment algorithm. Numerical experiments on the public datasets indicates that AESSIM is quite competitive in assessing performance.