Face Liveness Detection Returns Low Confidence Scores in Bright Sunlight.

Face Liveness Detection yields significantly lower confidence scores (<80%) in environments with bright sunlight, despite achieving near-perfect scores (99.99%) in normal indoor lighting. This behavior appears to result from overexposure or glare interfering with the camera input, reducing the model’s ability to assess liveness accurately.

**Expected behavior**
Confidence scores should remain consistently high (>90%) across varying lighting conditions. Alternatively, the SDK should guide users to adjust their environment (e.g., move to shade or avoid backlighting) to improve detection reliability.

**Found on : Latest version**
com.amplifyframework.ui:authenticator v1.5.0
com.amplifyframework.ui:liveness v1.4.2

Start by reproducing the liveness check in bright sunlight and indoors using com.amplifyframework.ui:authenticator v1.5.0 and com.amplifyframework.ui:liveness v1.4.2, then compare confidence scores and camera conditions. Determine whether the SDK can improve reliability or should provide environmental guidance; done means reliable scores above 90% or clear user guidance across the reported lighting conditions.

Written by the indexing model from the issue text.