@PHDTHESIS\{IMM2004-03196, author = "R. R. Paulsen", title = "Statistical Shape Analysis of the Human Ear Canal with Application to In-the-Ear Hearing Aid Design", year = "2004", school = "Informatics and Mathematical Modelling, Technical University of Denmark, {DTU}", address = "Richard Petersens Plads, Building 321, {DK-}2800 Kgs. Lyngby", type = "", note = "Supervised by Rasmus Larsen (IMM), S{\o}ren Laugesen (Oticon), Herve Delingette (INRIA), and Knut Conradsen (IMM)", url = "http://www.imm.dtu.dk/English.aspx", abstract = "This thesis is about the statistical shape analysis of the human ear canal with application to the mechanical design of in-the-ear hearing aids. Initially, it is described how a statistical shape model of the human ear canal is built based on a training set of laser-scanned ear impressions. A thin plate spline based approach creates a dense correspondence between the shapes in training set. In addition, a new flexible, non-rigid registration framework is proposed and used to optimise the correspondence field. The framework is based on Markov Random Field regularisation and is motivated by prior work on image restoration. It is shown how the method significantly improves the shape model. In the second part of the thesis, the shape model is used in software tools that mimic the skills of the expert hearing aid makers. The first result is that it is possible to learn an algorithm to cut an ear canal in order to produce an optimal in-the-ear hearing aid. Secondly, a framework for component placement using a coupling of stochastic optimisation and the results from the shape model is proposed. It is successfully, used to place the so-called faceplate with associated component on in-the-ear hearing aids. In addition, the idea of one-size-fits-most shells is explored. In Danish: Denne afhandling beskriver brugen af statistisk formanalyse af den menneskelige {\o}rekanal i det mekaniske design af i-{\o}ret h{\o}reapparater. F{\o}rst beskrives det hvordan en statistisk formmodel af den menneskelige {\o}re- kanal er lavet p{\aa} baggrund af et tr{\ae}ningss{\ae}t af laser-skannede {\o}re aftryk. En Thin Plate Spline baseret metode genererer en kompakt korrespondance mellem formerne i tr{\ae}ningss{\ae}ttet. Endvidere er en fleksibel, ikke-rigid registrerings- metode foresl{\aa}et og brugt til at optimere korrespondancefeltet. Metoden er baseret p{\aa} Markov Random Field regularisering og er motiveret af tidligere arbejde vedr{\o}rende billedeopretning. Det er vist hvordan metoden signifkant forbedrer formmodellen. I den anden del af afhandlingen, bruges formmodellen i programmer, der efter- ligner evnerne hos de bedste af dem der laver h{\o}reapparater. Det f{\o}rste resultat er, at det er muligt at l{\ae}re en algoritme at l{\ae}gge et snit i en scannet {\o}rekanal for at producere et optimalt i-{\o}ret h{\o}reapparat. Dern{\ae}st, foresl{\aa}s en metode til placering af komponenter. Metoden bruger en kombination af stokastisk optimering og resultater fra formmodellen. Den er succesfuldt brugt til at placere den s{\aa}kaldte faceplate med komponenter p{\aa} i-{\o}ret h{\o}reapparater. Derudover er ideen om en skal af en st{\o}rrelse og form, som passer de fleste forfulgt." }