Neural network approaches versus statistical methods in classification of multisource remote sensing data

J. A. Benediktsson, P. H. Swain, O. K. Ersoy

Rannsóknarafurð: Framlag á ráðstefnuVísindagreinritrýni

20 Tilvitnanir (Scopus)

Útdráttur

Neural network learning procedures are applied to the classification of multisource remote sensing data and statistical methods are used to classify the same data. Experimental results are given and a comparison is made between the two different approaches. The main emphasis in the comparison is in terms of classification accuracy, but other factors such as ease of implementation and speed of algorithms are also considered. Two methods show very good performance: statistical multisource analysis and in the neural network case, the generalized delta rule.

Upprunalegt tungumálEnska
Síður489-492
Síðufjöldi4
ÚtgáfustaðaÚtgefið - 1989
ViðburðurIGARSS'89 - Twelfth Canadian Symposium on Remote Sensing Part 2 (of 5) - Vancouver, BC, Can
Tímalengd: 10 júl. 198914 júl. 1989

Ráðstefna

RáðstefnaIGARSS'89 - Twelfth Canadian Symposium on Remote Sensing Part 2 (of 5)
Borg/bærVancouver, BC, Can
Tímabil10/07/8914/07/89

Fingerprint

Sökktu þér í rannsóknarefni „Neural network approaches versus statistical methods in classification of multisource remote sensing data“. Saman myndar þetta einstakt fingrafar.

Vitna í þetta