software

n implementation of TGV methodology published in TGV searches for an optimal setting of a computer vision system or of its sub-system. Within the system/sub-system must be implemented a weighted means grayscale conversion method. This implementation of TGV is based on one-stage grid-search algorithm supervised by a computer vision expert. The expert assesses settings proposed by the grid-searc method using WECIA graphs. One WECIA graph displays dependence of the system performance on setting of the grayscale conversion weights for one specific setting of the remaining adjustable parameters of the system/sub-system. The performance of the system/sub-system can be evaluated using one or more objective functions where only one of these function is used as a primary objective function, i.e. the grid-search algorihm uses this function for the selection of the optimal parameter setting. The expert can use all the objective functions while assessing a setting proposed by the grid-search algorithm, i.e. nJ WECIA graph are displeyed for one assesed setting where nJ is the number of the objective functions.

Computer vision; Parameter optimization; Performance evaluationl WECIA graph; Weighted means grayscale conversion

1. 9. 2022

https://www.sciencedirect.com/science/article/pii/S0141938222001044#mmc1

K využití výsledku jiným subjektem je vždy nutné nabytí licence

Poskytovatel licence na výsledek požaduje licenční poplatek

https://www.sciencedirect.com/science/article/pii/S0141938222001044#mmc1