Skip to content

Releases: tit-exe/OrangIdentifier_AndroidApp

Release list

v4

v4 Latest
Latest

Choose a tag to compare

View all tags
@tit-exe tit-exe released this 26 Jun 13:36
v4
835aedc

OrangIdentifier Android - V4.0

Release of the 4th major version of the OrangIdentifier Android companion app. This offline mobile application allows field users to photograph Bornean orangutans and identify them in real-time, completely without internet access.

Historical context: V1 used a ResNet closed-set classifier, V2 moved to ResNet embeddings, V3 introduced MegaDescriptor with a single centroid per individual. This V4 release integrates the V6 AI model and upgrades the gallery format and scoring system accordingly, using SubCenterArcFace training and a multi-exemplar representation for significantly improved recognition accuracy.

🌟 Key Changes from V3

  • Multi-exemplar gallery (model V6): Each individual is now represented by 25 exemplar vectors (768-dim each) instead of a single centroid. The recognition score is computed as max(dot(query, exemplar_i)) over all 25 exemplars, capturing natural appearance variability across angles and lighting conditions far better than an average vector.
  • New gallery: 15 known individuals, calibrated threshold of 0.5371, separability gap of 0.6711.
  • Gallery management: Full gallery export, per-individual patch sharing, automatic versioning with up to 20 restore points, and one-tap undo.
  • Field photos: Add photos to an existing individual's profile in the field. Stored separately from the training exemplars and merged at inference time.
  • Model hot-swap: Import a new backbone or detector as a .zip bundle via Settings without reinstalling the app.

🌟 Features

  • 100% Offline Inference: Runs entirely on-device using optimized TensorFlow Lite models.
  • V6 AI Pipeline (MegaDescriptor-T-224 + SubCenterArcFace): YOLO v2 face detector + Swin Transformer backbone producing 768-dim embeddings, matched against 25 exemplars per individual for open-set recognition.
  • Instant Onboarding: Add new individuals directly from the app with at least 5 photos. The prototype is computed and saved to the local gallery immediately, no retraining required.
  • Gallery Sharing: Export the full gallery or individual patches as JSON files and share them with other devices.
  • Automatic Backups: Every gallery modification creates a backup. Full restore history accessible from Settings.
  • Scan History: A local Room database keeps a log of all past identifications.

📥 Installation

  1. Download the app-release.apk attached to this release under Assets.
  2. Open the APK file on your Android device to install it. You may need to enable Install from unknown sources in your Android settings.

⚠️ Note for Developers

All models and the gallery are included directly in the repository. Clone the project, open it in Android Studio, sync Gradle, and build.

Assets 3
Loading

v3

v3

Choose a tag to compare

View all tags
@tit-exe tit-exe released this 04 Jun 13:57
release
04d78fa

OrangIdentifier Android - V3.0

Release of the 3rd major version of the OrangIdentifier Android companion app. This offline mobile application allows field rangers to photograph Bornean orangutans and identify them in real-time, completely without internet access.

Historical context: V1 used a ResNet closed-set classifier, V2 moved to ResNet embeddings. This V3 release introduces a major architectural upgrade with MegaDescriptor.

🌟 Key Features

  • 100% Offline Inference: Runs entirely on-device using optimized TensorFlow Lite models.
  • V3 Pipeline (MegaDescriptor): Uses the state-of-the-art V3 pipeline with a YOLO v2 face detector and a MegaDescriptor-T backbone for high-accuracy open-set recognition (reliably rejects unknown individuals).
  • Instant Onboarding: Add new individuals directly from the app in less than a minute. The embedding is immediately saved to the local gallery without any model retraining.
  • Scan History: A local Room database keeps a log of all past identifications.
  • Real-time Correction: Correct wrong predictions on the fly to continuously improve an individual's prototype vector.

📥 Installation Instructions

  1. Download the orangs_android_app_v3.apk attached to this release under Assets.
  2. Open the APK file on your Android device to install it. (You may need to enable "Install from unknown sources" in your Android settings).

⚠️ Note for Developers

This APK is ready to use. However, if you are building the project from source, remember that the heavy backbone model (megadesc_T_arcface_backbone.tflite, 112MB) is not included in the source code due to GitHub file size limits. You must download it manually from the HuggingFace repository and place it in the app/src/main/assets/ directory before building.

Loading