A novel markerless near infrared (NIR) laser-based head tracking system was recently proposed to resolve patient's head motion problem during cranial radiotherapy. Although previous research showed that we could track the patient's head position with the sub-millimetre range accuracy, the tracking performance strongly relied on the accuracy of the tissue thickness estimation. We noticed the factors that inuence the ROI features extracted from the backscattering images were the NIR laser power fluctuation and inconsistency. Therefore, the propose of this paper was to investigate the relationship between these parameters and determine a laser power independent feature transformation. We set up our head tracking system to project the pulsed NIR laser beam onto a single point on subject's forehead and observed the changes of the 5-ROI feature values on the different laser power level. The scatter plots between each ROI feature values and the laser power showed distinctive straight lines with similar slopes while applying linear regression to each scatter plot indicated that the slope of each ROI feature was also in the same range. According to the results, we could transform the data by subtracting the feature value of each ROI from their average slope value and the laser power. This new feature is laser power noise tolerance and could be used to enhance the tissue thickness estimation accuracy.
We propose a new biometric approach where the tissue thickness of a person's forehead is used as a biometric feature. Given that the spatial registration of two 3D laser scans of the same human face usually produces a low error value, the principle of point cloud registration and its error metric can be applied to human classification techniques. However, by only considering the spatial error, it is not possible to reliably verify a person's identity. We propose to use a novel near-infrared laser-based head tracking system to determine an additional feature, the tissue thickness, and include this in the error metric. Using MRI as a ground truth, data from the foreheads of 30 subjects was collected from which a 4D reference point cloud was created for each subject. The measurements from the near-infrared system were registered with all reference point clouds using the ICP algorithm. Afterwards, the spatial and tissue thickness errors were extracted, forming a 2D feature space. For all subjects, the lowest feature distance resulted from the registration of a measurement and the reference point cloud of the same person.
The combined registration error features yielded two clusters in the feature space, one from the same subject and another from the other subjects. When only the tissue thickness error was considered, these clusters were less distinct but still present. These findings could help to raise safety standards for head and neck cancer patients and lays the foundation for a future human identification technique.