Detecting and segmenting un-occluded items by actively casting shadows
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Hi-index | 0.00 |
In this paper, we propose a novel hardware approach to image segmentation, specifically in the case of overlapping particles. Our research is based on Multi-Flash Imaging (MFI), originally developed to detect depth discontinuities. Multiple images captured with different illumination conditions provide additional information about a scene compared to conventional segmentation techniques. Shadows are used to identify true object edges and underlying particles. We applied the new approach in automated particle size analysis and evaluated it against the watershed and canny edge detection techniques. Evaluation results confirm that MFI can be applied in image segmentation and reveals the superiority of the approach against conventional techniques in the case of overlapping particles.