TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Texture region detection by trained neural network

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko9th International Kharkiv Symposium on Physics and Engineering of Microwaves, Millimeter and Submillimeter Waves, MSMW 2016
KustantajaIEEE
ISBN (elektroninen)9781509022663
DOI - pysyväislinkit
TilaJulkaistu - 9 elokuuta 2016
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaINTERNATIONAL KHARKOV SYMPOSIUM ON PHYSICS AND ENGINEERING OF MICROWAVES, MILLIMETER AND SUBMILLIMETER WAVES -
Kesto: 1 tammikuuta 1900 → …

Conference

ConferenceINTERNATIONAL KHARKOV SYMPOSIUM ON PHYSICS AND ENGINEERING OF MICROWAVES, MILLIMETER AND SUBMILLIMETER WAVES
Ajanjakso1/01/00 → …

Tiivistelmä

In this paper we consider an important practical aspect of texture region detection in remote sensing images. One specific feature of our study is that we assume a processed image noisy with a priori known type and parameters of the noise. Another specific feature is that we try to detect textural regions for a wide variety of textures without having a priori knowledge of their properties. The considered task is solved by means of trained neural networks. In the paper, we analyze the aspects of choosing input local parameters used in detection (recognition) and carrying out training. The verification results provide valuable conclusions for these aspects.