Registration of ultrasound images is often complicated due to the inherent noise. Robust similarity metrics and optimiza- tion procedures are required to facilitate medical applicability. In this paper a novel hybrid procedure, incorporating global statistics and local textural features, is proposed for the registration of envelope detected Radio Frequency (RF) ultrasound data. On the global scale this achieved by Hellinger distance between distribution in images, and on the local scale by a statistics-based extension of Fuzzy Local Binary Patterns (FLBP). The proposed procedure is shown to outperform standard measures such as SSD and NCC, as well as Hellinger similarity and histogram matching of, standard and probabilistic versions of FLBP, in rigid registration experiments of enveloped detected RF data samples of the human neck.     «

Registration of ultrasound images is often complicated due to the inherent noise. Robust similarity metrics and optimiza- tion procedures are required to facilitate medical applicability. In this paper a novel hybrid procedure, incorporating global statistics and local textural features, is proposed for the registration of envelope detected Radio Frequency (RF) ultrasound data. On the global scale this achieved by Hellinger distance between distribution in images, and on the local scale by a sta...     »