@@ -8,9 +8,10 @@
 A from-scratch Rust library for **decoding and encoding 1D and 2D barcodes**, aiming
 for the widest possible symbology coverage while preserving every variation of a code.
 
-**▶ [Live WASM demo](https://karpeleslab.github.io/anydcode/)** — encode to a canvas,
-decode an image, and run live-camera detection, all in the browser (the library
-compiled to WebAssembly, no wasm-bindgen).
+**▶ [Live WASM demo](https://karpeleslab.github.io/anydcode/)** — generate any
+symbology (Apple App Clip Codes included), decode an image, and run live-camera
+scanning with a tracked target-lock overlay, all in the browser (the library compiled
+to WebAssembly, no wasm-bindgen).
 
 ## Goals
 
@@ -79,10 +80,16 @@ Legend: ✅ done · 🚧 in progress · ⬜ planned.
 | Royal Mail Mailmark (Barcode C & L) | ✅ | ✅ | ⬜ |
 | Australia Post 4-State · Japan Post 4-State | ✅ | ✅ | ⬜ |
 
-¹ QR ships a full image sampler: Otsu binarization → finder-pattern detection →
-perspective recovery (via the bottom-right alignment pattern) → sub-pixel grid
-sampling → decode. Robust to any-angle rotation, moderate tilt, blur and noise
-(envelope documented in `tests/harness_image.rs`).
+¹ QR ships a hardened image sampler: a global-Otsu → adaptive (Bradley/Sauvola)
+binarization ladder, dual-axis finder detection with a synthesized-third-corner
+fallback, perspective recovery via the alignment pattern, and — for curved or
+degraded captures — a thin-plate-spline dewarp anchored on every finder, alignment
+pattern and timing-pattern crossing, biased module classification, and a
+Reed–Solomon-arbitrated brute force over all 32 format configurations when blur
+wrecks the format fields. Robust to any-angle rotation, tilt, blur, noise, uneven
+lighting and cylinder curvature; clean-render envelope in `tests/harness_image.rs`,
+real-capture envelope (bottle and can labels down to ≈4.6 px/module) in
+`tests/real_world.rs`.
 
 ² 1D detection is the shared **`scan1d`** luminance front-end (edge detection →
 run-length → normalized `LinearPattern`), feeding each symbology's decoder. The
@@ -143,7 +150,12 @@ assert_eq!(encoder.encode(&decoded).unwrap(), encoding);
 For a camera feed you rarely want to fully decode every frame. The `detect` module
 provides a fast, symbology-agnostic **locator** that returns the *position* of every
 code (a bounding quad + coarse family guess) in a single downscaled pass, **without
-decoding** — the cheap stage of the two-stage `Detect` → `Analyze` pipeline:
+decoding** — the cheap stage of the two-stage `Detect` → `Analyze` pipeline. It is
+recall-biased but structurally picky: concentric-finder detection backs matrix
+guesses, scene-sized merged blobs, text rows/columns masquerading as barcodes and
+non-code ink densities are gated out, overlapping duplicates of one physical code are
+suppressed, and a close-up code that defeats the texture pass is still reported from
+its finder hits alone:
 
 ```rust
 use anyd::detect::{locate, LocateOptions};
@@ -158,17 +170,24 @@ for c in &candidates {
 Benchmark (`cargo bench --bench detect`, dependency-free, `std::time::Instant`),
 locating **all** codes of all families per frame vs. a full QR decode:
 
-| resolution | locate median | locate FPS | full-decode FPS | detect speedup |
-|-----------:|--------------:|-----------:|----------------:|---------------:|
-| 640×480    | 0.30 ms | ~3350 | ~1725 | 1.9× |
-| 1280×720   | 0.83 ms | ~1200 | ~635  | 1.9× |
-| 1920×1080  | 1.85 ms | ~545  | ~310  | 1.8× |
+| resolution | locate median | locate FPS | full QR decode | detect speedup |
+|-----------:|--------------:|-----------:|---------------:|---------------:|
+| 640×480    | 0.29 ms | ~3400 | 12.1 ms | ~41× |
+| 1280×720   | 0.70 ms | ~1430 | 14.1 ms | ~20× |
+| 1920×1080  | 1.53 ms | ~650  | 17.4 ms | ~11× |
 
 Recall 100% and false-positive rate 0% on the benchmark's planted-code frames.
 Locating is comfortably real-time at every resolution; decoding then runs only on the
 regions the locator hands off (and `Hints` lets already-decoded codes be skipped
 across frames).
 
+The demo page shows the intended live wiring: the main thread runs `locate` on a
+half-resolution grab ~30×/s, a crop worker decodes located regions off-thread —
+routed by family, so linear crops take the fast 1D path (`scan_1d` is
+rotation-complete via mirrored patterns and gradient-orientation derotation) — a
+second worker sweeps the full frame for self-localizing 2D codes, and decoded locks
+are position-tracked across frames so the overlay follows the code between reads.
+
 ## Command-line tool (`anyd`)
 
 An optional binary is bundled behind the **`cli`** feature, so the library itself
@@ -184,7 +203,8 @@ $ anyd encode qr "https://example.com" --format png --out qr.png --scale 8
 $ anyd encode ean13 5901234123457 --format svg --out barcode.svg
 $ anyd encode qr "HELLO" --format unicode          # half-block art in the terminal
 
-# Decode a PNG (tries QR, Data Matrix, PDF417, and the 1D front-end)
+# Decode a PNG (tries QR, Data Matrix, PDF417, App Clip Code, and the
+# rotation-complete 1D front-end)
 $ anyd decode qr.png
 QR Code: https://example.com
 
@@ -212,9 +232,10 @@ Live video:  GrayFrame ──▶ Detect ──▶ Candidate ──▶ Analyze
 ```
 
 Supporting modules: **`imgproc`** (Otsu/adaptive binarization, connected components,
-4-point homography, sub-pixel grid sampling — the 2D sampler toolkit), **`scan1d`**
-(generic 1D luminance front-end), **`render`** (Encoding → grayscale) and
-**`transform`** (rotation/perspective/blur/noise) for the test harness.
+4-point homography, thin-plate-spline warps, dominant-orientation estimation,
+sub-pixel grid sampling — the 2D sampler toolkit), **`scan1d`** (generic 1D luminance
+front-end), **`render`** (Encoding → grayscale) and **`transform`**
+(rotation/perspective/blur/noise) for the test harness.
 
 Correctness is anchored to independent reference vectors, not self-consistency: the
 ISO/IEC 18004 QR example, the ISO/IEC 16022 Data Matrix example, ISO/IEC 15438 +