Computational visual quality of digitally printed images

The problem of understanding how humans perceive the quality of a reproduced image is of interest to researchers of many fields related to vision science and engineering: optics and material physics, image processing (compression and transfer), printing and media technology, and psychology. A measure for visual quality cannot be defined without ambiguity because it is ultimately the subjective opinion of an “end-user” observing the product. The purpose of this thesis is to devise computational methods to estimate the overall visual quality of prints, i.e. a numerical value that combines all the relevant attributes of the perceived image quality. The problem is limited to consider the perceived quality of printed photographs from the viewpoint of a consumer, and moreover, the study focuses only on digital printing methods, such as inkjet and electrophotography. The main contributions of this thesis are two novel methods to estimate the overall visual quality of prints. In the first method, the quality is computed as a visible difference between the reproduced image and the original digital (reference) image, which is assumed to have an ideal quality. The second method utilises instrumental print quality measures, such as colour densities, measured from printed technical test fields, and connects the instrumental measures to the overall quality via subjective attributes, i.e. attributes that directly contribute to the perceived quality, using a Bayesian network. Both approaches were evaluated and verified with real data, and shown to predict well the subjective evaluation results.

Comparison of Local Feature Detectors and Descriptors for Visual Object Categorization

Local features are used in many computer vision tasks including visual object categorization, content-based image retrieval and object recognition to mention a few. Local features are points, blobs or regions in images that are extracted using a local feature detector. To make use of extracted local features the localized interest points are described using a local feature descriptor. A descriptor histogram vector is a compact representation of an image and can be used for searching and matching images in databases. In this thesis the performance of local feature detectors and descriptors is evaluated for object class detection task. Features are extracted from image samples belonging to several object classes. Matching features are then searched using random image pairs of a same class. The goal of this thesis is to find out what are the best detector and descriptor methods for such task in terms of detector repeatability and descriptor matching rate.

Faster for the master! : exploring issues of religious expression and alternative Christian identity within the Finnish Christian metal music scene

Populärkulturen har i dagens läge kommit att utgöra en allt mer viktig och central inspirationskälla för allt fler människors konstruktion av den egna religiösa identiteten även inom traditionella och institutionella kristna sammanhang. Denna avhandling belyser denna utveckling i ljuset av den finländska kristna metallmusik-kulturen - en sällsynt stark sammanblanding av protestantisk kristendom och en utpräglad och kontroversiell populärmusikform och dess kultur. Fokus riktas framför allt på hur den kristna metallmusik-kulturen blir meningsfull för sina medlemmar genom de sätt på vilka den konstrueras diskursivt, dvs. genom de sätt på vilka den representeras och talas om bland sina egna anhängare. Den diskursiva konstruktionen av den kristna metallmusik-kulturen utforskas på ett såväl bredare transnationellt som ett finländskt nationellt plan. Studien redogör även för den kristna metalmusikens och -kulturens huvudsakliga verbala, visuella och estetiska kännetecken. Uppbyggnaden och spridningen av dagens transnationella kristna metallmusik-kultur undersöks även i ljuset av det teoretiska konceptet scene. Avhandlingens centrala argument är att den kristna metallmusikscenen erbjuder sina medlemmar en mängd resurser för skapandet av ett alternativt och komplementärt religiöst uttrycksätt, religiös praxis och en alternativ kristen identitet.

Bag-of-Features Approach to Unsupervised Visual Object Categorisation

The large and growing number of digital images is making manual image search laborious. Only a fraction of the images contain metadata that can be used to search for a particular type of image. Thus, the main research question of this thesis is whether it is possible to learn visual object categories directly from images. Computers process images as long lists of pixels that do not have a clear connection to high-level semantics which could be used in the image search. There are various methods introduced in the literature to extract low-level image features and also approaches to connect these low-level features with high-level semantics. One of these approaches is called Bag-of-Features which is studied in the thesis. In the Bag-of-Features approach, the images are described using a visual codebook. The codebook is built from the descriptions of the image patches using clustering. The images are described by matching descriptions of image patches with the visual codebook and computing the number of matches for each code. In this thesis, unsupervised visual object categorisation using the Bag-of-Features approach is studied. The goal is to find groups of similar images, e.g., images that contain an object from the same category. The standard Bag-of-Features approach is improved by using spatial information and visual saliency. It was found that the performance of the visual object categorisation can be improved by using spatial information of local features to verify the matches. However, this process is computationally heavy, and thus, the number of images must be limited in the spatial matching, for example, by using the Bag-of-Features method as in this study. Different approaches for saliency detection are studied and a new method based on the Hessian-Affine local feature detector is proposed. The new method achieves comparable results with current state-of-the-art. The visual object categorisation performance was improved by using foreground segmentation based on saliency information, especially when the background could be considered as clutter.

Music digitalization and its effects on the Finnish music industry stakeholders

For the past two decades the music digitalization has been considered the most significant phenomenon in the music industry as the physical sales have been decreasing rapidly. The advancement of the digital technology and the internet have facilitated the digitalization in the music industry and affected all stages of the music value chain, namely music creation, distribution and consumption. The newly created consumer culture has led to the establishment of novel business models such as music subscriptions and à-la-carte downloads websites and live streaming. The dynamic digital environment has presented the music industry stakeholders with the challenge to adapt to the requirements of the constantly changing modern consumers’ needs and demands. The purpose of this study was to identify how music digitalization can influence change in the Finnish music industry value chain; i.e. how digitalization affects the music industry stakeholders, their functions and inter-relatedness and how the stakeholders are able to react to the changes in the industry. The study was conducted as a qualitative research based entirely on primary data in the form of semi-structured interviews with experts from different units of the Finnish music industry value chain. Since the study offers assessment of diverse viewpoints on the value chain, it further provides an integrated picture of the Finnish music industry current situation and its competitive environment. The results suggest that the music industry is currently in a turbulent stage of experimentation with new business models and digital innovations. However, at this point it is impossible to determine which business model will be approved by the consumers in the longer run. Nevertheless, the study confirmed the claim that consumption of music in its digital form is to become dominant over the traditional physical copies sales in the nearest future. As a result the music industry is becoming more user-oriented; that is the focus is shifting from music production towards artist branding and management and visibility to the audience. Furthermore, the music industry is undergoing the process of integration with other industries such as media, social networks, internet services providers and mobile phone manufacturers in order to better fulfill the consumers’ needs. The previously underrated live music and merchandising are also increasing their significance for the revenues in the stagnant music markets. Therefore, the music industry is developing at present towards becoming an integrated entertainment industry deeply penetrating every point of modern people’s leisure activities.

Le jazz : jazz and music criticism in France

Kirjallisuusarvostelu