Studies on the purification of training samples in supervised classification by mode filtering 利用眾數(shù)濾波對(duì)監(jiān)督分類(lèi)訓(xùn)練樣本純化的研究
The image of nanchuan in 2000 was interpreted using a multi - extracting method combining supervised classification with non - supervised classification 利用監(jiān)督分類(lèi)和非監(jiān)督分類(lèi)相結(jié)合的分層提取分類(lèi)方法對(duì)南川市2000年遙感影像進(jìn)行解譯。
The image of nanchuan in 2000 was interpreted using a multi - extracting method combining supervised classification with non - supervised classification 摘要利用監(jiān)督分類(lèi)和非監(jiān)督分類(lèi)相結(jié)合的分層提取分類(lèi)方法對(duì)南川市2000年遙感影像進(jìn)行解譯。
Supported by the analysis and advance process to the geographical data using gis software , the paper discusses the question that whether the accuracy of bayes supervised classification will be improved considering the influence of the prior probability 本文嘗試?yán)胓is軟件對(duì)地理數(shù)據(jù)進(jìn)行分析和預(yù)處理,對(duì)考慮先驗(yàn)概率是否提高bayes監(jiān)督分類(lèi)精度這一問(wèn)題作了探討。
The proportion based on the assistant data is used as the prior probability to replace the prior value in the conventional supervised classification ; the farther iterative prior probability is applied into classifying progress on landsat tm image 由輔助數(shù)據(jù)中計(jì)算各類(lèi)別面積比率作為先驗(yàn)概率,替換傳統(tǒng)監(jiān)督分類(lèi)中的先驗(yàn)值,并進(jìn)一步對(duì)先驗(yàn)概率進(jìn)行迭代,最后利用改進(jìn)的先驗(yàn)概率對(duì)landsattm影像進(jìn)行分類(lèi)實(shí)驗(yàn)。