Computer vision techniques for early detection of skin cancer
This thesis investigates the problem of developing new computer vision techniques for early detection of skin cancer. The first part of this work presents a novel methodology to correct color reproduction in dermatological images when different cameras and/or dermoscopes are used. Next, the problem...
| Autor: | |
|---|---|
| Formato: | tesis doctoral |
| Estado: | Versión publicada |
| Fecha de publicación: | 2012 |
| País: | España |
| Recursos: | CBUC, CESCA |
| Repositorio: | TDR. Tesis Doctorales en Red |
| OAI Identifier: | oai:www.tdx.cat:10803/82072 |
| Acesso em linha: | http://hdl.handle.net/10803/82072 |
| Access Level: | acceso abierto |
| Palavra-chave: | Skin cancer Càncer de pell Cáncer de pell Melanoma Computer vision Visió per ordinador Visión por ordenador 3D scanner Color calibration Mosaicing 68 |
| Resumo: | This thesis investigates the problem of developing new computer vision techniques for early detection of skin cancer. The first part of this work presents a novel methodology to correct color reproduction in dermatological images when different cameras and/or dermoscopes are used. Next, the problem of automatic full body mapping is addressed by proposing a mosaicing method based on an on-the-shelf digital compact camera and a set of markers. This method increases the possibilities of total body photography by taking the low-resolution images of a whole body exploration and automatically combining them into a high-resolution photomosaic. The third contribution of this work consists of the development of a full body scanner for acquiring cutaneous images. On one hand, the scanner reduces the long time-consuming examinations done in dermoscopy explorations, and on the other hand, it increases the resolution of total body photography systems. |
|---|