Mercury Cloud
English
English
  • Introduction
  • Release Notes
  • User Manual
    • Revision History
    • Overview
  • OpenAPI Manual
    • Revision History
    • 1 Overview
    • 2 API References
    • 3 How to call
    • 4 Feature & Image
    • 5 Face Detection Quickstart Guide
    • 6 Face Verification (1:1) Quickstart Guide
    • 7 Face Identification (1:N) Quickstart Guide
    • 8 Guidance to Advanced Users
Powered by GitBook
On this page

Was this helpful?

Export as PDF

Release Notes

This page provides the release notes of Mercury Cloud.

PreviousIntroductionNextUser Manual

Last updated 3 years ago

Was this helpful?

The update schedule will be announced on the .

Date
Version
Release notes

2022/05/11

V1.5.0

  • Added the update extra_info API

2021/12/08

V1.4.3

  • Fixed several API bugs and documentation errors

2021/09/29

V1.4.0

  • Added the auto-rotation function of input images.

2021/08/11

V1.3.0

  • Added optimal image rotation angle as an output to the Quality Check API.

2021/07/21

V1.2.5

  • Added the Face Quality Check API.

  • Added trace_id to the Get System Info API.

2021/06/15

V1.1.0

  • Added attributes detection to feature-related APIs.

2021/05/17

V1.0.1

  • Changed OpenAPI’s credential headers from “date” to “ x-date” to enable more clients to access.

2021/05/17

V1.0.0

  • Beta released for customer trial only.

  • Applied OpenAPIs.

  • Supported multiple tenants to access with AKSK authentication.

Known Issues

  • When uploading an image with multiple faces in the Face Detection API, not all faces can be detected. Suggest using images with only one face or trim the image to contain one face only before using this API.

  • When using the quality check API to detect the optimal rotation angle, some images may return the wrong rotation angle. We are currently working on modifying the algorithm to improve the accuracy.

  • If the same image is added and deleted over 5 times in a feature database with max_size larger than 100K, the cross-database search (1vN) API has the possibility to get an empty set, even if there are similar features registered. To prevent this issue, create a feature database with a smaller size or avoid adding and deleting the same image multiple times.

status dashboard