For digital media, the risk of piracy is aggravated by the ease to copy and distribute the content. Watermarking has become the technology of choice for discouraging people from creating illegal copies of digital content. Watermarking is the practice of imperceptibly altering the media content by embedding a message, which can be used to identify the owner of that content. A watermark message can also be a set of instructions for the display equipment, providing information about the content’s usage restrictions. Several applications are considered and three watermarking solutions are provided. First, applications such as owner identification, proof of ownership, and digital fingerprinting are considered and a fast content-dependent image watermarking method is proposed. The scheme offers a high degree of robustness against distortions, mainly additive noise, scaling, low-pass filtering, and lossy compression. This method also requires a small amount of computations. The method generates a set of evenly distributed codewords that are constructed via an iterative algorithm. Every message bit is represented by one of these codewords and is then embedded in one of the image’s 8 × 8 pixel blocks. The information in that particular block is used in the embedding so as to ensure robustness and image fidelity. Two watermarking schemes designed to prevent theatre camcorder piracy are also presented. In these methods, the video is watermarked so that its display is not permitted if a compliant video player detects the watermark. A watermark that is robust to geometric distortions (rotation, scaling, cropping) and lossy compression is required in order to block access to media content that has been recorded with a camera inside a movie theatre. The proposed algorithms take advantage of the properties of the dual-tree complex wavelet transform (DT CWT). This transform offers the advantages of both the regular and the complex wavelets (perfect reconstruction, approximate shift invariance and good directional selectivity). Our methods use these characteristics to create watermarks that are robust to geometric distortions and lossy compression. The proposed schemes are simple to implement and outperform comparable methods when tested against geometric distortions.

For digital media, the risk of piracy is aggravated by the ease to copy and distribute the content. Watermarking has become the technology of choice for discouraging people from creating illegal copies of digital content. Watermarking is the practice of imperceptibly altering the media content by embedding a message, which can be used to identify the owner of that content. A watermark message can also be a set of instructions for the display equipment, providing information about the content’s usage restrictions. Several applications are considered and three watermarking solutions are provided. First, applications such as owner identification, proof of ownership, and digital fingerprinting are considered and a fast content-dependent image watermarking method is proposed. The scheme offers a high degree of robustness against distortions, mainly additive noise, scaling, low-pass filtering, and lossy compression. This method also requires a small amount of computations. The method generates a set of evenly distributed codewords that are constructed via an iterative algorithm. Every message bit is represented by one of these codewords and is then embedded in one of the image’s 8 × 8 pixel blocks. The information in that particular block is used in the embedding so as to ensure robustness and image fidelity. Two watermarking schemes designed to prevent theatre camcorder piracy are also presented. In these methods, the video is watermarked so that its display is not permitted if a compliant video player detects the watermark. A watermark that is robust to geometric distortions (rotation, scaling, cropping) and lossy compression is required in order to block access to media content that has been recorded with a camera inside a movie theatre. The proposed algorithms take advantage of the properties of the dual-tree complex wavelet transform (DT CWT). This transform offers the advantages of both the regular and the complex wavelets (perfect reconstruction, approximate shift invariance and good directional selectivity). Our methods use these characteristics to create watermarks that are robust to geometric distortions and lossy compression. The proposed schemes are simple to implement and outperform comparable methods when tested against geometric distortions.

An algorithm which is able to consistently identify features in an image is a basic building block of many object recognition systems. Attaining sufficient consistency is challenging, because factors such as pose and lighting can dramatically change a feature’s appearance. Effective feature identification therefore requires both a reliable and accurate keypoint detector and a discriminative categoriser (or quantiser). The Dual Tree Complex Wavelet Transform (DTCWT) decomposes an image into oriented subbands at a range of scales. The resulting domain is arguably well suited for further image analysis tasks such as feature identification. This thesis develops feature identification in the complex wavelet domain, building on previous keypoint detection work and exploring the use of random forests for descriptor quantisation. Firstly, we extended earlier work on keypoint detection energy functions. Existing complex wavelet based detectors were observed to suffer from two defects: a tendency to produce keypoints on straight edges at particular orientations and sensitivity to small translations of the image. We introduced a new corner energy function based on the Same Level Product (SLP) transform. This function performed well compared to previous ones, combining competitive edge rejection and positional stability properties. Secondly, we investigated the effect of changing the resolution at which the energy function is sampled. We used the undecimated DTCWT to calculate energy maps at the same resolution as the original images. This revealed the presence of fine details which could not be accurately interpolated from an energy map at the standard resolution. As a result, doubling the resolution of the map along each axis significantly improved both the reliability and posi-tional accuracy of detections. However, calculating the map using interpolated coefficients resulted in artefacts introduced by inaccuracies in the interpolation. We therefore proposed a modification to the standard DTCWT structure which doubles its output resolution for a modest computational cost. Thirdly, we developed a random forest based quantiser which operates on complex wavelet polar matching descriptors, with optional rotational invariance. Trees were evaluated on the basis of how consistently they quantised features into the same bins, and several examples of each feature were obtained by means of tracking. We found that the trees produced the most consistent quantisations when they were trained with a second set of tracked keypoints. Detecting keypoints using the the higher resolution energy maps also resulted in more consistent quantiser outputs, indicating the importance of the choice of detector on quantiser performance. Finally, we introduced a fast implementation of the DTCWT, keypoint detection and descriptor extraction algorithms for OpenCL-capable GPUs. Several aspects were optimised to enable it to run more efficiently on modern hardware, allowing it to process HD footage in faster than real time. This particularly aided the development of the detector algorithms by permitting interactive exploration of their failure modes using a live camera feed.

For digital media, the risk of piracy is aggravated by the ease to copy and distribute the content. Watermarking has become the technology of choice for discouraging people from creating illegal copies of digital content. Watermarking is the practice of imperceptibly altering the media content by embedding a message, which can be used to identify the owner of that content. A watermark message can also be a set of instructions for the display equipment, providing information about the content’s usage restrictions. Several applications are considered and three watermarking solutions are provided. First, applications such as owner identification, proof of ownership, and digital fingerprinting are considered and a fast content-dependent image watermarking method is proposed. The scheme offers a high degree of robustness against distortions, mainly additive noise, scaling, low-pass filtering, and lossy compression. This method also requires a small amount of computations. The method generates a set of evenly distributed codewords that are constructed via an iterative algorithm. Every message bit is represented by one of these codewords and is then embedded in one of the image’s 8 × 8 pixel blocks. The information in that particular block is used in the embedding so as to ensure robustness and image fidelity. Two watermarking schemes designed to prevent theatre camcorder piracy are also presented. In these methods, the video is watermarked so that its display is not permitted if a compliant video player detects the watermark. A watermark that is robust to geometric distortions (rotation, scaling, cropping) and lossy compression is required in order to block access to media content that has been recorded with a camera inside a movie theatre. The proposed algorithms take advantage of the properties of the dual-tree complex wavelet transform (DT CWT). This transform offers the advantages of both the regular and the complex wavelets (perfect reconstruction, approximate shift invariance and good directional selectivity). Our methods use these characteristics to create watermarks that are robust to geometric distortions and lossy compression. The proposed schemes are simple to implement and outperform comparable methods when tested against geometric distortions. / Applied Science, Faculty of / Electrical and Computer Engineering, Department of / Graduate

L'analyse des images numériques, bien que largement étudiée, reste encore aujourd'hui un réel défi. Avec pour objectifs la description pertinente et la reconnaissance sémantique du contenu de celles-ci, de nombreuses applications requièrent une attention particulière quant à cette analyse. Pour répondre à ces besoins, l'analyse du contenu des images est réalisée de façon automatique grâce à des méthodes informatiques se rapprochant par exemple des mathématiques, des statistiques, de la physique. Une façon pertinente et reconnue de représenter les objets observés dans les images réside dans leur segmentation. Couplée à la classification, la segmentation permet une ségrégation sémantique de ces objets. Cependant, les méthodes existantes ne peuvent être considérées comme génériques, et bien que motivées par de nombreux domaines (militaire, médical, satellite, etc.), celles-ci sont continuellement réévaluées, adaptées et améliorées. Par exemple, les images satellites se démarquent dans le milieu de l'image de par leur spécificité d'acquisition, de par leur support ou de par le sujet d'observation (la Terre dans notre cas).Cette thèse à pour but d'explorer les méthodes de caractérisation et de segmentation supervisées exploitant la notion de texture. Les sols observés depuis l'espace, à des échelles et des résolutions différentes, peuvent être perçus comme texturés. Les cartes d'occupation des sols peuvent être obtenues par la segmentation d'images satellites, notamment en utilisant l'information texturale. Nous proposons le développement d'algorithmes de segmentation compétitifs caractérisant la texture par l'utilisation de représentations multi-échelles des images obtenues par décomposition en ondelettes et de classificateurs supervisés tels que les Support Vector Machines. Dans cette optique, cette thèse est principalement articulée autour de plusieurs projets de recherche nécessitant une étude des images à des échelles et des résolutions différentes, ces images étant elles-mêmes de nature variée (e.g. multi-spectrales, optiques, LiDAR). Nous dériverons, pour ces différents cas d'étude, certains aspects de la méthodologie développée. / The analysis of digital images, albeit widely researched, continues to present a real challenge today. In the case of several applications which aim to produce an appropriate description and semantic recognition of image content, particular attention is required to be given to image analysis. In response to such requirements, image content analysis is carried out automatically with the help of computational methods that tend towards the domains of mathematics, statistics and physics. The use of image segmentation methods is a relevant and recognized way to represent objects observed in images. Coupled with classification, segmentation allows a semantic segregation of these objects. However, existing methods cannot be considered to be generic, and despite having been inspired by various domains (military, medical, satellite etc), they are continuously subject to reevaluation, adaptation or improvement. For example satellite images stand out in the image domain in terms of the specificity of their mode of acquisition, their format, or the object of observation (the Earth, in this case).The aim of the present thesis is to explore, by exploiting the notion of texture, methods of digital image characterization and supervised segmentation. Land, observed from space at different scales and resolutions, could be perceived as being textured. Land-use maps could be obtained through the segmentation of satellite images, in particular through the use of textural information. We propose to develop competitive algorithms of segmentation to characterize texture, using multi-scale representations of images obtained by wavelet decomposition and supervised classifiers such as Support Vector Machines.Given this context, the present thesis is principally articulated around various research projects which require the study of images at different scales and resolutions, and which are varying in nature (eg. multi-spectral, optic, LiDAR). Certain aspects of the methodology developed are applied to the different case studies undertaken.

In this work, a new method is proposed that can be used for area tracking. This method is based on the Complex Discrete Wavelet Transform (CDWT) developed by Magarey and Kingsbury. The CDWT has its advantages over the traditional Discrete Wavelet Transform such as approximate shift invariance, improved directional selectivity, and robustness to noise and illumination changes. The proposed method is a generalization of the CDWT based motion estimation method developed by Magarey and Kingsbury. The Complex Wavelet Tracker extends the original method to estimate the true motion of regions according to a parametric motion model. In this way, rotation, scaling, and shear type of motions can be handled in addition to pure translation. Simulations have been performed on the proposed method including both quantitative and qualitative tests. Quantitative tests are performed on synthetically created test sequences and results have been compared to true data. The performance is compared with intensity-based methods. Qualitative tests are performed on real sequences and evaluations are presented empirically. The results are compared with intensity-based methods. It is observed that the proposed method is very accurate in handling affine deformations for long term sequences and is robust to different target signatures and illumination changes. The accuracy of the proposed method is compatible with intensity-based methods. In addition to this, it can handle a wider range of cases and is robust to illuminaton changes compared to intensity-based methods. The method can be implemented in real-time and could be a powerful replacement of current area trackers.