A　reconstruction-based　image　processing　algorithm　is　developed　to　automatically　extract　feature　points　of　digitalized　2D　objects.　This　algorithm,　which　is　introduced　using　a　bumblebee　flight　case,　is　made　up　of　two　parts:　a　four-connected　dot　chasing　rearrangement　scheme　and　an　extreme　point　extraction　on　a　polarized　contour.　It　is　then　applied　to　a　dune　evolution　case　that　is　simulated　with　a　cellular　automation　model.　The　results　show　that　the　proposed　algorithm　is　effective　in　characterizing　individual　moving　objects.　An　additional　algorithm　is　developed　to　categorize　the　extracted　feature　points　of　a　bumblebee　with　translucent　wings.　©　2019　World　Scientific　Publishing　Company.