With the increasing pervasiveness of digital cameras, the Internet, and social networking, there is a growing need to catalog and analyze large collections of photos and videos. In this dissertation, we explore unconstrained still-image and video-based face recognition in real-world scenarios, e.g. social photo sharing and movie trailers, where people of interest are recognized and all others are ignored. In such a scenario, we must obtain high precision in recognizing the known identities, while accurately rejecting those of no interest. Recent advancements in face recognition research has seen Sparse Representation-based Classification (SRC) advance to the forefront of competing methods. However, its drawbacks, slow speed and sensitivity to variations in pose, illumination, and occlusion, have hindered its wide-spread applicability. The contributions of this dissertation are three-fold: 1. For still-image data, we propose a novel Linearly Approximated Sparse Representation-based Classification (LASRC) algorithm that uses linear regression to perform sample selection for l1-minimization, thus harnessing the speed of least-squares and the robustness of SRC. On our large dataset collected from Facebook, LASRC performs equally to standard SRC with a speedup of 100-250x. 2. For video, applying the popular l1-minimization for face recognition on a frame-by-frame basis is prohibitively expensive computationally, so we propose a new algorithm Mean Sequence SRC (MSSRC) that performs video face recognition using a joint optimization leveraging all of the available video data and employing the knowledge that the face track frames belong to the same individual. Employing MSSRC results in a speedup of 5x on average over SRC on a frame-by-frame basis. 3. Finally, we make the observation that MSSRC sometimes assigns inconsistent identities to the same individual in a scene that could be corrected based on their visual similarity. Therefore, we construct a probabilistic affinity graph combining appearance and co-occurrence similarities to model the relationship between face tracks in a video. Using this relationship graph, we employ random walk analysis to propagate strong class predictions among similar face tracks, while dampening weak predictions. Our method results in a performance gain of 15.8% in average precision over using MSSRC alone.

This thesis deals with copyright protection and content authentication for still images. New blind transform domain block based algorithms using one-level and two-level Discrete Wavelet Transform (DWT) were developed for copyright protection. The mobile number with international code is used as the watermarking data. The robust algorithms used the Low-Low frequency coefficients of the DWT to embed the watermarking information. The watermarking information is embedded in the green channel of the RGB colour image and Y channel of the YCbCr images. The watermarking information is scrambled by using a secret key to increase the security of the algorithms. Due to the small size of the watermarking information comparing to the host image size, the embedding process is repeated several times which resulted in increasing the robustness of the algorithms. Shuffling process is implemented during the multi embedding process in order to avoid spatial correlation between the host image and the watermarking information. The effects of using one-level and two-level of DWT on the robustness and image quality have been studied. The Peak Signal to Noise Ratio (PSNR), the Structural Similarity Index Measure (SSIM) and Normalized Correlation Coefficient (NCC) are used to evaluate the fidelity of the images. Several grey and still colour images are used to test the new robust algorithms. The new algorithms offered better results in the robustness against different attacks such as JPEG compression, scaling, salt and pepper noise, Gaussian noise, filters and other image processing compared to DCT based algorithms. The authenticity of the images were assessed by using a fragile watermarking algorithm by using hash function (MD5) as watermarking information embedded in the spatial domain. The new algorithm showed high sensitivity against any tampering on the watermarked images. The combined fragile and robust watermarking caused minimal distortion to the images. The combined scheme achieved both the copyright protection and content authentication.

This thesis deals with copyright protection and content authentication for still images. New blind transform domain block based algorithms using one-level and two-level Discrete Wavelet Transform (DWT) were developed for copyright protection. The mobile number with international code is used as the watermarking data. The robust algorithms used the Low-Low frequency coefficients of the DWT to embed the watermarking information. The watermarking information is embedded in the green channel of the RGB colour image and Y channel of the YCbCr images. The watermarking information is scrambled by using a secret key to increase the security of the algorithms. Due to the small size of the watermarking information comparing to the host image size, the embedding process is repeated several times which resulted in increasing the robustness of the algorithms. Shuffling process is implemented during the multi embedding process in order to avoid spatial correlation between the host image and the watermarking information. The effects of using one-level and two-level of DWT on the robustness and image quality have been studied. The Peak Signal to Noise Ratio (PSNR), the Structural Similarity Index Measure (SSIM) and Normalized Correlation Coefficient (NCC) are used to evaluate the fidelity of the images. Several grey and still colour images are used to test the new robust algorithms. The new algorithms offered better results in the robustness against different attacks such as JPEG compression, scaling, salt and pepper noise, Gaussian noise, filters and other image processing compared to DCT based algorithms. The authenticity of the images were assessed by using a fragile watermarking algorithm by using hash function (MD5) as watermarking information embedded in the spatial domain. The new algorithm showed high sensitivity against any tampering on the watermarked images. The combined fragile and robust watermarking caused minimal distortion to the images. The combined scheme achieved both the copyright protection and content authentication.

This thesis concerns the background reconstruction from several photographs (so called depopulation scene efect). There are presented methods for obtaining the background from video and discussion of their use for photographs. The greatest emphasis is placed on the Gaussian mixture model and effort to improve this algorithm due to static image. The photographs should be taken with a tripod.