Extending the image ray transform for shape detection and extraction

Abstract

A conventional approach to image analysis is to separately perform feature extraction at a low level (such as edge detection) and follow this with high level feature extraction to determine structure (e.g. by collecting edge points) using the Hough transform. The original image Ray Transform (IRT) demonstrated capability to extract structures at a low level. Here we extend the IRT to add shape specificity that makes it select specific shapes rather than just edges; the new capability is achieved by addition of a single parameter that controls which shape is selected by the extended IRT. The extended approach can then perform low-and high-level feature extraction simultaneously. We show how the IRT process can be extended to focus on chosen shapes such as lines and circles. Histogram patterns, which are an extension to this new capability, can describe extracted features showing that the extracted patterns are robust to change in orientation, position and scale. We confirm the new capability by using conventional methods for exact shape location, such as the Hough transform. We analyse performance with images from the Caltech-256 dataset and show that the new approach can indeed select chosen shapes. Further research will aim to capitalise on the new extraction ability to extend descriptive capability.