Direct against this kind of situation, the paper presents a method to estimate average size of closely packed particles based on edge density without explicit segmentation.

Given image sequences of closely packed particles, the topic is that of estimating average size (average diam-eter) of packed particles, applying edge density without explicit segmentation.

Its core idea was as follows: Firstly, we employed a rule-based method to recognize some musical entities with explicit rules in their context before word segmentation.