Edge Detection for Color Medical Image Based on Quaternion and SOFM-NN
Liang Hua, Hao Feng, KeanYu, Yuqing Liu, Lijun Ding, Juping Gu · International Journal of Advancements in Computing Technology · 2013
The image edge detection is rather difficult due to its natures of diversity and complexity. For retaining correlations between the three color components of color medical images and avoiding human intervention such as setting threshold of image edge judgment, a novel edge detection method for color medical images has been proposed in this paper. The approach proposed here combines the self-organizing feature map (SOFM) neural network and quaternion. Based on the rotation characteristic of quaternion in 3D vector space and reprocessing results by calculating the Euclidean distance, an edge characteristic vector has been constructed. The SOFM neural network is trained by the vector and subsequently used for edge detection. The experimental results demonstrate the method has stronger retention capacity of the details. The noise can be removed based on the method when 30 or more neurons network is adopted.