The Archivio Storico Ricordi holds the historical records of one of the most important music publisher of all times. For almost two hundred years, beyond their main business as music publishers, the Ricordis were also impresarios, agents, and cultural organisers, and played a central and unique mediating role within Italian musical life. This role is very well documented by some 30,000 autograph letters addressed to Casa Ricordi by composers, writers, librettists, singers, and conductors, and an impressive and neatly ordered collection of around 600,000 sent letters. The whole collection will be published online bit by bit. The goal of the project is to connect the letters not only with the relevant records of the Ricordi archive (ledgers, contracts, stage designs, scores, pictures...), but also with other music archives over the web. / Das Archivio Storico Ricordi sammelt historische Materialien eines der bedeutendsten Musikverlagshäuser aller Zeiten. Über fast 200 Jahre prägten die Ricordis nicht nur durch ihre Verlagstätigkeit, sondern ebenso als Impresarios, Agenten, Kulturförderer und -manager das italienische Musikleben. Rund 30 000 an die Ricordis gerichtete autografe Schreiben von Komponisten, Schriftstellern, Librettisten, Sängern und Dirigenten sowie 600 000 von den Ricordis verfasste Briefe dokumentieren die herausragende Rolle der Verlegerfamilie. Die gesamte Sammlung wird nach und nach online zur Verfügung gestellt. Dabei werden die Schriftstücke nicht nur mit anderen Objekten des Ricordi-Archivs wie Verlagsbüchern, Verträgen, Bühnenentwürfen, Noten, Bildern, sondern ebenso mit Materialien anderer Musikerarchive im Web verlinkt.

Anställda på företag gör ibland utlägg på köp åt företaget som de behöver dokumentera manuellt. För att underlätta dokumentation av utlägg hos anställda på företaget Consid AB har detta arbete haft i syfte att utveckla en tjänst som från en bild på ett kvitto kan extrahera relevant data såsom pris, datum, företagsnamn samt kategorisera kvittot. Resultatet som arbetet har medfört är en tjänst som kan extrahera text från kvitton med en säkerhet på i snitt 73 % på att texten är rätt. Efter tester kan det även fastställas att tjänsten kan hitta pris, datum och företagsnamn från ca. 64 % av testade kvitton med olika kvalité och innehåll. Tjänsten som byggdes har även implementerat två olika kategoriseringsmetoder där hälften av de testade kvittona kan kategoriseras av de båda metoderna. Efter analyser av metoder och resultat har slutsatser kunnat dragits i att tjänsten innehåller ett flertal brister samt att mer tid bör läggas för att optimera och testa tjänsten ytterligare. / Employees at companies sometimes make purchases on behalf of the company which they manually need to document. To ease the documentation of purchases made by employees at Consid AB, this study has had the goal to develop a service that from an image of a receipt can extract relevant data such as price, date, company name along with a category of the purchase. The resulting service can extract text from receipts with a confidence of 73 % in that the text is correct. Tests of the service shows that it can find price, date and company name on around 64 % of test receipts with different quality and contents. The resulting service has also implemented two different methods for categorisation where half of the test receipts could be categorised by both methods. After analysing methods and results, conclusions have been made in that the service contains of numerous flaws and that more time needs to be put in to optimise and test the service.

The current state of the art optical character recognition (OCR) algorithms are capable of extracting text from images in predefined conditions. OCR is extremely reliable for interpreting machine-written text with minimal distortions, but images taken in a natural scene are still challenging. In recent years the topic of improving recognition rates in natural images has gained interest because more powerful handheld devices are used. The main problem faced dealing with recognition in natural images are distortions like illuminations, font textures, and complex backgrounds. Different preprocessing approaches to separate text from its background have been researched lately. In our study, we assess the improvement reached by two of these preprocessing methods called k-means and Otsu by comparing their results from an OCR algorithm. The study showed that the preprocessing made some improvement on special occasions, but overall gained worse accuracy compared to the unaltered images. / Dagens optisk teckeninläsnings (OCR) algoritmer är kapabla av att extrahera text från bilder inom fördefinierade förhållanden. De moderna metoderna har uppnått en hög träffsäkerhet för maskinskriven text med minimala förvrängningar, men bilder tagna i en naturlig scen är fortfarande svåra att hantera. De senaste åren har ett stort intresse för att förbättra tecken igenkännings algoritmerna uppstått, eftersom fler kraftfulla och handhållna enheter används. Det huvudsakliga problemet när det kommer till igenkänning i naturliga bilder är olika förvrängningar som infallande ljus, textens textur och komplicerade bakgrunder. Olika metoder för förbehandling och därmed separation av texten och dess bakgrund har studerats under den senaste tiden. I våran studie bedömer vi förbättringen som uppnås vid förbehandlingen med två metoder som kallas för k-means och Otsu genom att jämföra svaren från en OCR algoritm. Studien visar att Otsu och k-means kan förbättra träffsäkerheten i vissa förhållanden men generellt sett ger det ett sämre resultat än de oförändrade bilderna.

Denna rapport redogör för skapandet av ett API som kan extrahera information från bilder på kvitton. Informationen som APIet skulle kunna ta fram var organisationsnummer, datum, tid, summa och moms. Här ingår även en fördjupning om tekniken OCR (optical character recognition) som omvandlar bilder och dokument till text. Examensarbetet utfördes åt Flex Applications AB. Examensarbetet utfördes åt Flex Applications AB. / This report describes the creation of an API that can extract information from pictures of receipts. Registration number, date, time, sum and tax are the information that the API was going to be able to deliver. In this thesis there is also a deepening of the technology OCR (optical character recognition) that transforms pictures and documents to text. The thesis was performed for Flex Applications AB.

Ce travail de thèse a pour objectif de proposer plusieurs méthodes d'identification non-supervisées des personnes présentes dans les flux télévisés à l'aide des noms écrits à l'écran. Comme l'utilisation de modèles biométriques pour reconnaître les personnes présentes dans de larges collections de vidéos est une solution peu viable sans connaissance a priori des personnes à identifier, plusieurs méthodes de l'état de l'art proposent d'employer d'autres sources d'informations pour obtenir le nom des personnes présentes. Ces méthodes utilisent principalement les noms prononcés comme source de noms. Cependant, on ne peut avoir qu'une faible confiance dans cette source en raison des erreurs de transcription ou de détection des noms et aussi à cause de la difficulté de savoir à qui fait référence un nom prononcé. Les noms écrits à l'écran dans les émissions de télévision ont été peu utilisés en raison de la difficulté à extraire ces noms dans des vidéos de mauvaise qualité. Toutefois, ces dernières années ont vu l'amélioration de la qualité des vidéos et de l'incrustation des textes à l'écran. Nous avons donc ré-évalué, dans cette thèse, l'utilisation de cette source de noms. Nous avons d'abord développé LOOV (pour Lig Overlaid OCR in Vidéo), un outil d'extraction des textes sur-imprimés à l'image dans les vidéos. Nous obtenons avec cet outil un taux d'erreur en caractères très faible. Ce qui nous permet d'avoir une confiance importante dans cette source de noms. Nous avons ensuite comparé les noms écrits et les noms prononcés dans leurs capacités à fournir le nom des personnes présentes dans les émissions de télévisions. Il en est ressorti que deux fois plus de personnes sont nommables par les noms écrits que par les noms prononcés extraits automatiquement. Un autre point important à noter est que l'association entre un nom et une personne est intrinsèquement plus simple pour les noms écrits que pour les noms prononcés. Cette très bonne source de noms nous a donc permis de développer plusieurs méthodes de nommage non-supervisé des personnes présentes dans les émissions de télévision. Nous avons commencé par des méthodes de nommage tardives où les noms sont propagés sur des clusters de locuteurs. Ces méthodes remettent plus ou moins en cause les choix fait lors du processus de regroupement des tours de parole en clusters de locuteurs. Nous avons ensuite proposé deux méthodes (le nommage intégré et le nommage précoce) qui intègrent de plus en plus l'information issue des noms écrits pendant le processus de regroupement. Pour identifier les personnes visibles, nous avons adapté la méthode de nommage précoce pour des clusters de visages. Enfin, nous avons aussi montré que cette méthode fonctionne aussi pour nommer des clusters multi-modaux voix-visage. Avec cette dernière méthode, qui nomme au cours d'un unique processus les tours de paroles et les visages, nous obtenons des résultats comparables aux meilleurs systèmes ayant concouru durant la première campagne d'évaluation REPERE / In this thesis we propose several methods for unsupervised person identification in TV broadcast using the names written on the screen. As the use of biometric models to recognize people in large video collections is not a viable option without a priori knowledge of people present in this videos, several methods of the state-of-the-art proposes to use other sources of information to get the names of those present. These methods mainly use the names pronounced as source of names. However, we can not have a good confidence in this source due to transcription or detection names errors and also due to the difficulty of knowing to who refers a pronounced name. The names written on the screen in TV broadcast have not be used in the past due to the difficulty of extracting these names in low quality videos. However, recent years have seen improvements in the video quality and overlay text integration. We therefore re-evaluated in this thesis, the use of this source of names. We first developed LOOV (for LIG Overlaid OCR in Video), this tool extract overlaid texts written in video. With this tool we obtained a very low character error rate. This allows us to have an important confidence in this source of names. We then compared the written names and pronounced names in their ability to provide the names of person present in TV broadcast. We found that twice persons are nameable by written names than by pronounced names with an automatic extraction of them. Another important point to note is that the association between a name and a person is inherently easier for written names than for pronounced names. With this excellent source of names we were able to develop several unsupervised naming methods of people in TV broadcast. We started with late naming methods where names are propagated onto speaker clusters. These methods question differently the choices made during the diarization process. We then proposed two methods (integrated naming and early naming) that incorporate more information from written names during the diarization process. To identify people appear on screen, we adapted the early naming method for faces clusters. Finally, we have also shown that this method also works for multi-modal speakers-faces clusters. With the latter method, that named speech turn and face during a single process, we obtain comparable score to the best systems that contribute during the first evaluation REPERE

Master’s thesis is point to the innovation the data collecting of testing machine of selective circuit breakers. New solution of data collection don’t affect the operations of testing machine. The cost calculation of new solution is included. Master’s thesis also included program solution of SPC methods and application of it to the process of testing the selective circuit breakers.

Die Innenraumpositionierung kommt in der heutigen Zeit immer mehr Aufmerksamkeit zu teil. Neben der Navigation durch das Gebäude sind vor allem Location Based Services von Bedeutung, welche Zusatzinformationen zu spezifischen Objekten zur Verfügung stellen Da für eine Innenraumortung das GPS Signal jedoch zu schwach ist, müssen andere Techniken zur Lokalisierung gefunden werden. Neben der häufig verwendeten Positionierung durch Auswertung von empfangenen Funkwellen existieren Methoden zur optischen Lokalisierung mittels Landmarken. Das kamerabasierte Verfahren bietet den Vorteil, dass eine oft zentimetergenaue Positionierung möglich ist. In dieser Masterarbeit erfolgt die Bestimmung der Position im Gebäude mittels Detektion von ArUco-Markern und Türschildern aus Bilddaten. Als Evaluationsgeräte sind zum einen die Kinect v2 von Microsoft, als auch das Lenovo Phab 2 Pro Smartphone verwendet worden. Neben den Bilddaten stellen diese auch mittels Time of Flight Sensoren generierte Tiefendaten zur Verfügung. Durch den Vergleich von aus dem Bild extrahierten Eckpunkten der Landmarke, mit den aus einer Datenbank entnommenen realen geometrischen Maßen des Objektes, kann die Entfernung zu einer gefundenen Landmarke bestimmt werden. Neben der optischen Distanzermittlung wird die Position zusätzlich anhand der Tiefendaten ermittelt. Abschließend werden beiden Verfahren miteinander verglichen und eine Aussage bezüglich der Genauigkeit und Zuverlässigkeit des in dieser Arbeit entwickelten Algorithmus getroffen. / Indoor Positioning is receiving more and more attention nowadays. Beside the navigation through a building, Location Bases Services offer the possibility to get more information about certain objects in the enviroment. Because GPS signals are too weak to penetrate buildings, other techniques for localization must be found. Beneath the commonly used positioning via the evaluation of received radio signals, optical methods for localization with the help of landmarks can be used. These camera-based procedures have the advantage, that an inch-perfect positioning is possible. In this master thesis, the determination of the position in a building is chieved through the detection of ArUco-Marker and door signs in images gathered by a camera. The evaluation is done with the Microsoft Kinect v2 and the Lenovo Phab 2 Pro Smartphone. They offer depth data gained by a time of flight sensor beside the color images. The range to a detected landmark is calculated by comparing the object´s corners in the image with the real metrics, extracted from a database. Additionally, the distance is determined by the evaluation of the depth data. Finally, both procedures are compared with each other and a statement about the accuracy and responsibility is made.

Sportmarknaden har växt kraftigt under en längre period och är nu en viktig industri där allt fler aktörer konkurrerar om individers åtråvärda tid. Således har marknaden blivit betydligt mer kommersiell och ett sätt att undvika denna konkurrens är att skapa en ny sport. I denna studie kommer etableringen av en ny rekreationssport undersökas samt hur internationaliseringsprocessen ser ut. Tidigare forskning har behandlat professionell sport men saknar studier som riktar sig mot rekreationssporter. För att bidra till forskningen om rekreationssport har denna studie testat applicerbarheten av teorierna Blue Ocean Strategy och Uppsalamodellen i syfte att ta reda på hur en sport grundas, vilka fördelar man har som first mover, hur man försvarar sig samt hur expansion till internationella marknader går till. Detta har genomförts med en kvalitativ metod där grundarna av två svenska företag som driver rekreationssporter, ÖTILLÖ och Tough Viking, har intervjuats. Empirin visar att grundandet av en sport kräver stor passion, viljan att testa något nytt och en hybrid som gör sporter enklare och mer tillgängliga. Efter grundandet har first movern fördelen att sätta standarden i form av regler, välja de bästa platserna för eventet samt att företaget associeras med sporten. Den tydligaste strategin för att försvara sig är att företaget agerar likt ett förbund i syfte att avväpna nya aktörer och i den processen samtidigt få sporten att växa. Internationalisering av företagen sker för att sprida sporten och många sportspecifika faktorer styr valet av marknad vilket skiljer sig från Uppsalamodellen. / The sports market has grown strongly over a longer period of time and is now an important industry where more and more actors are competing for individuals' desirable time. Thus, the market has become significantly more commercial and one way to avoid this competition is to create a new sport. In this study, the establishment of a new recreational sport will be examined and what the internationalization process looks like. Previous research has dealt with professional sports but lacks studies aimed at recreational sports. To contribute to research on recreational sports, this study has tested the applicability of the theories Blue Ocean Strategy and the Uppsala model in order to find out how a sport is founded, what advantages you have as a first mover, how to defend yourself and how to expand to international markets. This has been done with a qualitative method where the founders of two Swedish companies that run recreational sports, ÖTILLÖ and Tough Viking, have been interviewed. The empirical presentation shows that founding a sport requires great passion, the desire to try something new and a hybrid that makes sports easier and more accessible. After the founding, a first mover has the advantage of setting the standard in the form of rules, choosing the best venues for the event and that the company is associated with the sport. The most distinct strategy for defending itself is that the company acts like a sport federation in order to disarm new actors and in the same process make the sport grow. Internationalization of companies takes place to spread the sport and many sport-specific factors dictate the choice of market, which differs from the Uppsala model.

There are many more ways to automate the application process like using some commercial software’s that are used in big organizations to scan bills and forms, but this application is only for the static frames or formats. In our application, we are trying to automate the non-static frames as the study certificate we get are from different counties with different universities. Each and every university have there one format of certificates, so we try developing a very new application that can commonly work for all the frames or formats. As we observe many applicants are from same university which have a common format of the certificate, if we implement this type of tools, then we can analyze this sort of certificates in a simple way within very less time. To make this process more accurate we try implementing SVM and Clustering methods. With these methods we can accurately map courses in certificates to ASE study path if not to exclude list. A grade calculation is done for courses which are mapped to an ASE list by separating the data for both labs and courses in it. At the end, we try to award some points, which includes points from ASE related courses, work experience, specialization certificates and German language skills. Finally, these points are provided to the chair to select the applicant for master course ASE.

The usefulness of digitized documents is directly related to the quality of the extracted text. Optical Character Recognition (OCR) has reached a point where well-formatted and clean machine- printed documents are easily recognizable by current commercial OCR products; however, older or degraded machine-printed documents present problems to OCR engines resulting in word error rates (WER) that severely limit either automated or manual use of the extracted text. Major archives of historical machine-printed documents are being assembled around the globe, requiring an accurate transcription of the text for the automated creation of descriptive metadata, full-text searching, and information extraction. Given document images to be transcribed, ensemble recognition methods with multiple sources of evidence from the original document image and information sources external to the document have been shown in this and related work to improve output. This research introduces new methods of evidence extraction, feature engineering, and evidence combination to correct errors from state-of-the-art OCR engines. This work also investigates the success and failure of ensemble methods in the OCR error correction task, as well as the conditions under which these ensemble recognition methods reduce the Word Error Rate (WER), improving the quality of the OCR transcription, showing that the average document word error rate can be reduced below the WER of a state-of-the-art commercial OCR system by between 7.4% and 28.6% depending on the test corpus and methods. This research on OCR error correction contributes within the larger field of ensemble methods as follows. Four unique corpora for OCR error correction are introduced: The Eisenhower Communiqués, a collection of typewritten documents from 1944 to 1945; The Nineteenth Century Mormon Articles Newspaper Index from 1831 to 1900; and two synthetic corpora based on the Enron (2001) and the Reuters (1997) datasets. The Reverse Dijkstra Heuristic is introduced as a novel admissible heuristic for the A* exact alignment algorithm. The impact of the heuristic is a dramatic reduction in the number of nodes processed during text alignment as compared to the baseline method. From the aligned text, the method developed here creates a lattice of competing hypotheses for word tokens. In contrast to much of the work in this field, the word token lattice is created from a character alignment, preserving split and merged tokens within the hypothesis columns of the lattice. This alignment method more explicitly identifies competing word hypotheses which may otherwise have been split apart by a word alignment. Lastly, this research explores, in order of increasing contribution to word error rate reduction: voting among hypotheses, decision lists based on an in-domain training set, ensemble recognition methods with novel feature sets, multiple binarizations of the same document image, and training on synthetic document images.