Recently, the learning based methods have been well exploited to hallucinate grayscale face images. When facing color images, however, the previous approaches either suffering from the non-flexibility for arbitrary pa...
详细信息
Recently, the learning based methods have been well exploited to hallucinate grayscale face images. When facing color images, however, the previous approaches either suffering from the non-flexibility for arbitrary pattern shapes or ignoring the inherent color informa-tion. To address these concerns, in this paper we propose a new learning model named as Superpixel-guided locality Quaternion Representation (SLQR) for color face hallucination. Rather than handling squared patches with fixed size, the proposed method handles super -pixels with adaptive shapes segmented from face images according to semantic contents, which can well preserve the face spatial features. Moreover, the superpixels are mapped into quaternion space to exploit the inherent spectral information for color image recon-struction. In addition, considering that images are inevitably corrupted by noise in practice, we extend the SLQR to the robust version (W-SLQR) by introducing a proper reweighting strategy into the objective function to suppress noise. Compared to some state-of-the-art methods, various experiments have been conducted to verify the superiority of our pro-posed methods in hallucinating clean and noisy face images.(c) 2022 Elsevier Inc. All rights reserved.
In the past few years, neighbor-embedding (NE) based methods have been widely exploited for face hallucination. However, the existing NE based methods in spatial domain just employ single type of features for data rep...
详细信息
In the past few years, neighbor-embedding (NE) based methods have been widely exploited for face hallucination. However, the existing NE based methods in spatial domain just employ single type of features for data representation, ignoring the compensatory information among multiple image features, resulting in bias in high resolution (HR) face image reconstruction. To tackle such problem, this paper presents a novel Multiple feature Learning model with Hierarchical Structure (MLHS) for face hallucination. Compared with conventional NE based methods, the proposed MLHS makes full use of multi-level information of face images, which can effectively remedy the flaw caused by just using single type of spatial pixel features, and adopts hierarchical structure to better maintain the manifold consistency hypothesis between the HR and low resolution (LR) patch spaces. The multiple learning strategy and hierarchical structure admit the proposed MLHS to well reconstruct the face details such as eyes, nostrils and mouth. The validity of the proposed MLHS method is confirmed by the comparison experiments in some public face databases. (C) 2019 Published by Elsevier Inc.
Most of the action recognition researchers are undergoing intense study on sparse representation, due to its discriminative nature. The basis of the sparse representation is sparse coding, which give way for creating ...
详细信息
ISBN:
(纸本)9781538611418
Most of the action recognition researchers are undergoing intense study on sparse representation, due to its discriminative nature. The basis of the sparse representation is sparse coding, which give way for creating sparse dictionaries. The aim of this paper is to show the details about action recognition in video;the basics of sparse representation and its usage in action recognition;advancements in sparse representation;practical issues of recent sparse representation methods and future possibilities to solve such issues. This paper also provides various models and techniques used for the sparse representation based action recognition.
暂无评论