Three-dimensional Wavelet Transform in Multi-dimensional Biomedical Volume Processing

Object detection and recognition is a common problem related to fault diagnosis in engineering or analysis of changes in biomedical data observations. As such data are often contaminated by noise it is necessary to reduce its effect during this process as well. The paper presents the application of wavelet transform to perform these task using the three dimensional wavelet decomposition, coefficients thresholding and object reconstruction. The proposed method is verified for simulated data at first and then applied for processing of backbone parts to emphasize its selected components. The goal of the paper is in (i) the presentation of the three-dimensional wavelet transform, (ii) discussion of its use for volume data de-nosing, and (iii) proposal of the following data extraction to allow their classification. The paper compares numerical results achieved by the use of different wavelet functions and thresholding methods with the experience of an expert to propose the best algorithmic approach to this problem.