AGS estimation#
The AGS (Approximate Garbage Score) estimation calculates a score indicating the suitability of the source image for descriptor extraction and matching. The output is a normalized float score ranging from 0 to 1. A score closer to 1 indicates better matching results for the image.
Value range#
The AGS estimation value must be between the minimal and maximum values:
| Platform | Minimum value configuration | Maximum value configuration |
|---|---|---|
| LUNA ID for Android | public const val AGS_MIN: Float = 0F |
public const val AGS_MAX: Float = 1F |
| LUNA ID for iOS | LCLunaConfiguration → bestShotConfiguration → estimationThreshold → ags = 0; |
LCLunaConfiguration → bestShotConfiguration → estimationThreshold → ags = 1; |
Default value#
By default, the AGS threshold is set to 0.5 in LUNA ID for Android and 0.2 in LUNA ID for iOS. We strongly do not recommend that you change the value.
| Platform | Configuration |
|---|---|
| LUNA ID for Android | public const val DEFAULT_AGS: Float = 0.5F |
| LUNA ID for iOS | LCLunaConfiguration → bestShotConfiguration → estimationThreshold → ags = 0.2; |
Implementation#
| Platform | Implementation |
|---|---|
| LUNA ID for Android | public val ags: Float = DEFAULT_AGS |
| LUNA ID for iOS | @property (nonatomic) CGFloat ags; |