Image Marketing Methods for Submarine Manganese Nodule Statistics

Hongsheng Liu, Xinke Zhu, Yuliang Liu

Abstract


In order to improve statistics speed and accuracy of submarine manganese nodule particles, two image marking methods are discussed in this paper. One method is based on binary morphological segmentation depending on corrosion and expansion algorithms, where it marks edge pixels of the particle and regards the area enclosed by these marked pixels as that of manganese nodule particles. The other method is based on substitution-circle segmentation where the crude round nucleus shape feature of a manganese nodule particle is utilized, i.e. a so-called substitution circle is needed to replace a real particle approximately and its area is regarded as that of the manganese nodule particle. Finally Matlab software simulation is used to compare the two methods’ effectiveness. It is shown that statistics accuracy of both the methods is similar, while the second method is more feasible owing to its another advantage of less calculation amount.


DOI
10.12783/dtcse/iciti2018/29173

Full Text:

PDF

Refbacks

  • There are currently no refbacks.