A procedure for semi-automatic segmentation in OBIA based on the maximization of a comparison index

摘要: In an Object Based Image Analysis Classification (OBIA) process, the quality of classification results are highly dependent on segmentation. However, a high number studies that make use OBIA process find segmentation parameters by making trial-and-error methods. It is clear lack structured procedure to determine produces unquantified errors in classification. This paper aims quantify effects using semi-automatic approach optimal parameters. To this end, performed classify land cover types produced both manual and automatic Even though outperforms segmentation, difference only 2%. Since with parameters, accurately those must be minimize error misjudgment step.