University of Twente Student Theses
Covariance Model Based Keypoint Detector Development
Indrawijaya, K.R. (2021) Covariance Model Based Keypoint Detector Development.
|
PDF
4MB |
| Abstract: | Model-based approaches for image reconstruction, analysis and interpretation have been very popular in the past. However, in the last decade, with the availability of large amounts of imaging data and the increase in computing power, machine learning, in particular deep learning, has become more popular. Within a deep learning network, in standard descriptions of convolutional neural networks, the first layer is considered as an image feature extractor. Often, it is assumed that they extract features like edge, line, and spots. Despite this assumption, the kernels of these networks usually do not really resemble an edge, line, and spots detection. This thesis revisits a novel statistical approach to keypoint, specifically line and edge detection, using the covariance model based image feature detector. This research explores the implementation of covariance model-based image feature detection and any of its intermediate results in combination with deep learning approaches. The result shows that incorporating such prior information is useful in making more robust, non-spurious detections. Moreover, in the exploration of the CVM operator, a feature descriptor was designed that makes use of the CVM convolution kernels. This descriptor shows a rotation and limited scale invariant capability, which has shown to be useful for keypoint matching. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Programme: | Embedded Systems MSc (60331) |
| Link to this item: | https://purl.utwente.nl/essays/86670 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page