Locally Linear Image Structural Embedding for Image Structure Manifold Learning
This work addresses image quality assessment for applications like image processing, but it is incremental as it adapts an existing manifold learning method.
The paper tackled the problem of image quality assessment by introducing the image structure manifold concept and proposing Locally Linear Image Structural Embedding (LLISE), which uses SSIM instead of MSE, resulting in a method that captures image structure features and discriminates distortions.
Most of existing manifold learning methods rely on Mean Squared Error (MSE) or $\ell_2$ norm. However, for the problem of image quality assessment, these are not promising measure. In this paper, we introduce the concept of an image structure manifold which captures image structure features and discriminates image distortions. We propose a new manifold learning method, Locally Linear Image Structural Embedding (LLISE), and kernel LLISE for learning this manifold. The LLISE is inspired by Locally Linear Embedding (LLE) but uses SSIM rather than MSE. This paper builds a bridge between manifold learning and image fidelity assessment and it can open a new area for future investigations.