Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Algorithms for Selecting and Comparing Features of Digital Image Vectors Based on the Analysis of Local Extrema
Ist Teil von
Intelligent Human Computer Interaction, 2023, Vol.13741, p.540-546
Ort / Verlag
Switzerland: Springer International Publishing AG
Erscheinungsjahr
2023
Link zum Volltext
Quelle
Alma/SFX Local Collection
Beschreibungen/Notizen
The article proposes new algorithms for extracting recognizable features of one-dimensional vectors obtained from digital images and comparing them. Vectors store one byte, i.e. values in the range 0 ÷ 255 taken from a grayscale image. The features of hills located in the intervals of the local minima of the vector were taken as identification features. In particular, the area of the selected hill, its width, the coordinate of the local maximum located on this hill, etc. are taken.