Pressforming of a tray from a pulp sheet

The aim of this thesis work was to verify the possibility to produce tray packages directly from pulp sheets using press forming techniques. The different existing raw materials of pulp, various sources of molded pulp and different methods of production of molded pulp were studied. Nine different raw materials which were used for experimental work were provided by Stora Enso mills, and Stora Enso Research Centre, Imatra, Finland. The laboratory tests were carried out using LUT Adjustable packaging line at Lappeenranta University of Technology. The results prove that long virgin fibres of pine pulp seems to have better formability with high moisture content compared to others. No significant improvements were noticed with conditioned samples, never the less far studies has to be done to find optimal conditions for production. The results indicated the possibility for making pressformed tray from two different pulp qualities (Sunila pulp and Enopine). The method could prove to be beneficiary as the production line could be shortened and investment in board machines could be avoided if the trays were pressed directly from pulp sheets. Also the labour costs would be reduced. However, there is much work to be done before the quality of a tray produced out of a pulp sheet is comparable to a tray produced out of tray board.

Natural and synthetic fibres improving tensile strength and elongation of paper products

The theory part of the Master’s thesis introduces fibres with high tensile strength and elongation used in the production of paper or board. Strong speciality papers are made of bleached softwood long fibre pulp. The aim of the thesis is to find new fibres suitable for paper making to increase either tensile strength, elongation or both properties. The study introduces how fibres bond and what kind of fibres give the strongest bonds into fibre matrix. The fibres that are used the in manufacturing of non-wovens are long and elastic. They are longer than softwood cellulose fibres. The end applications of non-wovens and speciality papers are often the same, for instance, wet napkins or filter media. The study finds out which fibres are used in non-wovens and whether the same fibres could be added to cellulose pulp as armature fibres, what it would require for these fibres to be blended in cellulose, how they would bind with cellulose and whether some binding agents or thermal bonding, such as hot calendaring would be necessary. The following fibres are presented: viscose, polyester, nylon, polyethylene, polypropylene and bicomponent fibres. In the empiric part of the study the most suitable new fibres are selected for making hand sheets in laboratory. Test fibres are blended with long fibre cellulose. The test fibres are viscose (Tencel), polypropylene and polyethylene. Based on the technical values measured in the sheets, the study proposes how to continue trials on paper machine with viscose, polyester, bicomponent and polypropylene fibres.

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.