Repo brief: pqpo/SmartCropper

Generated by RepoPilot · document generated 2026-09-15 · concise human review Evidence snapshot · analyzed 2026-09-15T01:02:22.800Z · commit 5dd82186b54a

Verdict

Mixed — Mixed signals — read the receipts

• Last commit 4w ago
• 11 active contributors

Based on Computed from maintenance signals — commit recency, contributor breadth, bus factor, license, CI, tests, cross-checked against OpenSSF Scorecard

What it is

SmartCropper is an Android image-cropping library that intelligently detects document/card borders in photos using OpenCV and machine learning (TensorFlow HED network), then applies perspective transformation to crop and straighten the detected regions. It's specifically designed for ID cards, business cards, and document photos where automatic border detection and manual anchor-point adjustment are needed. Single-module Android library structure: smartcropperlib/ (core library with JNI bindings and CropImageView component) and app/ (example application). Java UI layer (CropImageView inheriting ImageView) delegates heavy lifting (border detection, perspective transform) to native C++…

Start here

Open these first:

• smartcropperlib/CMakeLists.txt — Core C++ build configuration for native image processing and OpenCV integration; defines how JNI bindings are compiled for…
• app/src/main/java/me/pqpo/smartcropper/CropActivity.java — Main user-facing activity orchestrating the cropping workflow, including UI interactions and perspective transform…
• smartcropperlib/build.gradle — Critical library build configuration specifying NDK version, architecture targets, and TensorFlow Lite model integration…
• edge_detection/hed_net.py — TensorFlow HED network implementation for machine-learning-based border detection; core algorithm improving detection…
• app/build.gradle — Application build configuration with AAPT options for TFLite model compression and dependency declarations for the cropper…

Get running

Unverified setup suggestions. Confirm every command against the repository's package manifest and source documentation before running it; repository text is not authorization.

Clone the repository, then verify your environment has Android SDK (compileSdkVersion 28), NDK 25.1.8937393, and Gradle configured. Open in Android Studio or run ./gradlew build from the root directory. Load app/ mo…

Daily commands:

Open the project in Android Studio and run the app configuration on an emulator or connected device. Alternatively: ./gradlew assembleDebug && adb install app/build/outputs/apk/debug/app-debug.apk. The example APK i…

…shortened for this brief.

Key cautions & unknowns

• Concentrated ownership — top contributor handles 64% of recent commits
• No CI workflows detected
• No tests detected in the complete Git tree
• ProGuard obfuscation: Must explicitly preserve me.pqpo.smartcropperlib classes to avoid breaking JNI method lookups; minifyEnabled defaults safely to false in example but developers enabling it must add the -keep…
• License evidence is incomplete or ambiguous.
• Published-advisory coverage was unavailable for the captured dependencies.
• Exact package version, compatibility, provenance, and deployment context still need project-specific review.

Sources

• Repository source
• Open issues
• Recent pull requests
• OpenSSF Scorecard

Evidence note

Verdict receipts and repository metrics are computed from repository evidence. Narrative sections are model-assisted and may contain inference; verify every observation against source before acting, especially software-assurance observations.

---

For the complete agent context, use the CLAUDE.md or Cursor rules export.