| In the first chapter, a new image decomposition scheme, called the adaptive directional total variation (ADTV) model, is proposed to achieve effective segmentation and enhancement for latent fingerprint images in this work. The proposed model is inspired by the classical total variation models, but it differentiates itself by integrating two unique features of fingerprints; namely, scale and orientation. The proposed ADTV model decomposes a latent fingerprint image into two layers: cartoon and texture. The cartoon layer contains unwanted components (e.g. structured noise) while the texture layer mainly consists of the latent fingerprint. This cartoon-texture decomposition facilitates the process of segmentation, as the region of interest can be easily detected from the texture layer using traditional segmentation methods. The effectiveness of the proposed scheme is validated through experimental results on the entire NIST SD27 latent fingerprint database. The proposed scheme achieves accurate segmentation and enhancement results, leading to improved feature detection and latent matching performance.;In the second chapter, we present a compressed-domain video retargeting solution that operates without compromising the resizing quality. Existing video retargeting methods operate in the spatial (or pixel) domain. Such a solution is not practical if it is implemented in mobile devices due to its large memory requirement. In the proposed solution, each component of the retargeting system is designed to exploit the low-level compressed domain features extracted from the coded bit stream. For example, motion information is obtained directly from motion vectors. An efficient column shape mesh deformation is employed to solve the difficulty of sophisticated quad-shape mesh deformation in the compressed domain. The proposed solution achieves comparable (or slightly better) visual quality performance as compared with several state-of-the-art pixel-domain retargeting methods at lower computational and memory costs, making content-aware video resizing both scalable and practical in real-world applications.;In chapter three, we proposed a novel objective quality of experience (QoE) index, called the GLS index, to evaluate image retargeting results. We first identified three key factors related to human perception on the quality of retargeted images. They are global structural distortion, local region distortion and loss of salient information. Using this knowledge as guidance, we found effective features that capture these distortion types and utilized a machine learning mechanism to fuse all features into one single quality score. One major advantage of applying the machine learning tool is that the feature weights can be determined automatically. It was shown by experimental results that the proposed GLS index outperforms four other existing objective indices by a significant margin in all four performance metrics of consideration. |
