Merge pull request #31 from sz3/mode-b-and-other-goodness

Support new cimbar format "mode B", minor UI change = version 0.6.0f

app/build.gradle

@@ -8,8 +8,8 @@ android {
         applicationId "org.cimbar.camerafilecopy"
         minSdkVersion 21
         targetSdkVersion 30
-        versionCode 11
-        versionName "0.5.15"
+        versionCode 13
+        versionName "0.6.0f"
         testInstrumentationRunner "android.support.test.runner.AndroidJUnitRunner"
         externalNativeBuild {
             cmake {

app/src/cpp/cfc-cpp/MultiThreadedDecoder.h

@@ -15,7 +15,7 @@
 class MultiThreadedDecoder
 {
 public:
-	MultiThreadedDecoder(std::string data_path, int color_bits);
+	MultiThreadedDecoder(std::string data_path, bool legacy_mode);
 
 	inline static clock_t bytes = 0;
 	inline static clock_t perfect = 0;
@@ -26,11 +26,10 @@ class MultiThreadedDecoder
 	inline static clock_t extractTicks = 0;
 
 	bool add(cv::Mat mat);
-	bool decode(const cv::Mat& img, bool should_preprocess);
 
 	void stop();
 
-	int color_bits() const;
+	bool legacy_mode() const;
 	unsigned num_threads() const;
 	unsigned backlog() const;
 	unsigned files_in_flight() const;
@@ -43,20 +42,20 @@ class MultiThreadedDecoder
 	void save(const cv::Mat& img);
 
 protected:
-	int _colorBits;
+	bool _legacyMode;
 	Decoder _dec;
 	unsigned _numThreads;
 	turbo::thread_pool _pool;
 	concurrent_fountain_decoder_sink<cimbar::zstd_decompressor<std::ofstream>> _writer;
 	std::string _dataPath;
 };
 
-inline MultiThreadedDecoder::MultiThreadedDecoder(std::string data_path, int color_bits)
-	: _colorBits(color_bits)
-	, _dec(cimbar::Config::ecc_bytes(), _colorBits)
+inline MultiThreadedDecoder::MultiThreadedDecoder(std::string data_path, bool legacy_mode)
+	: _legacyMode(legacy_mode)
+	, _dec(cimbar::Config::ecc_bytes(), cimbar::Config::color_bits(), legacy_mode? 0 : 1, legacy_mode)
 	, _numThreads(std::max<int>(((int)std::thread::hardware_concurrency()/2), 1))
 	, _pool(_numThreads, 1)
-	, _writer(data_path, cimbar::Config::fountain_chunk_size(cimbar::Config::ecc_bytes(), cimbar::Config::symbol_bits() + _colorBits))
+	, _writer(data_path, cimbar::Config::fountain_chunk_size(cimbar::Config::ecc_bytes(), cimbar::Config::symbol_bits() + cimbar::Config::color_bits(), legacy_mode))
 	, _dataPath(data_path)
 {
 	FountainInit::init();
@@ -97,7 +96,8 @@ inline bool MultiThreadedDecoder::add(cv::Mat mat)
 		// if extracted image is small, we'll need to run some filters on it
 		clock_t begin = clock();
 		bool should_preprocess = (res == Extractor::NEEDS_SHARPEN);
-		unsigned decodeRes = _dec.decode_fountain(img, _writer, should_preprocess);
+		int color_correction = _legacyMode? 1 : 2;
+		unsigned decodeRes = _dec.decode_fountain(img, _writer, should_preprocess, color_correction);
 		bytes += decodeRes;
 		++decoded;
 		decodeTicks += clock() - begin;
@@ -107,16 +107,6 @@ inline bool MultiThreadedDecoder::add(cv::Mat mat)
 	} );
 }
 
-inline bool MultiThreadedDecoder::decode(const cv::Mat& img, bool should_preprocess)
-{
-	return _pool.try_execute( [&, img, should_preprocess] () {
-		clock_t begin = clock();
-		bytes += _dec.decode_fountain(img, _writer, should_preprocess);
-		++decoded;
-		decodeTicks += clock() - begin;
-	} );
-}
-
 inline void MultiThreadedDecoder::save(const cv::Mat& mat)
 {
 	std::stringstream fname;
@@ -131,9 +121,9 @@ inline void MultiThreadedDecoder::stop()
 	_pool.stop();
 }
 
-inline int MultiThreadedDecoder::color_bits() const
+inline bool MultiThreadedDecoder::legacy_mode() const
 {
-	return _colorBits;
+	return _legacyMode;
 }
 
 inline unsigned MultiThreadedDecoder::num_threads() const

app/src/cpp/cfc-cpp/jni.cpp

@@ -53,7 +53,7 @@ namespace {
 
 		cv::Scalar color = cv::Scalar(255,255,255);
 		if (in_progress == 1)
-			color = cv::Scalar(255,100,100);
+			color = cv::Scalar(255,244,94); // 0,191,255
 		else if (in_progress == 2)
 			color = cv::Scalar(0,255,0);
 		cv::Scalar outline = cv::Scalar(0,0,0);
@@ -123,8 +123,8 @@ namespace {
 	void drawDebugInfo(cv::Mat& mat, MultiThreadedDecoder& proc)
 	{
 		std::stringstream sstop;
-		sstop << "cfc using " << proc.num_threads() << " thread(s). " << proc.color_bits() << "..." << proc.backlog() << "? ";
-		sstop << (MultiThreadedDecoder::bytes / std::max<double>(1, MultiThreadedDecoder::decoded)) << "b v0.5.15";
+		sstop << "cfc using " << proc.num_threads() << " thread(s). " << proc.legacy_mode() << "..." << proc.backlog() << "? ";
+		sstop << (MultiThreadedDecoder::bytes / std::max<double>(1, MultiThreadedDecoder::decoded)) << "b v0.6.0f";
 		std::stringstream ssmid;
 		ssmid << "#: " << MultiThreadedDecoder::perfect << " / " << MultiThreadedDecoder::decoded << " / " << MultiThreadedDecoder::scanned << " / " << _calls;
 		std::stringstream ssperf;
@@ -162,20 +162,21 @@ namespace {
 
 extern "C" {
 jstring JNICALL
-Java_org_cimbar_camerafilecopy_MainActivity_processImageJNI(JNIEnv *env, jobject instance, jlong matAddr, jstring dataPathObj, jint colorBitsJ)
+Java_org_cimbar_camerafilecopy_MainActivity_processImageJNI(JNIEnv *env, jobject instance, jlong matAddr, jstring dataPathObj, jint modeInt)
 {
 	++_calls;
 
 	// get params from raw address
 	Mat &mat = *(Mat *) matAddr;
 	string dataPath = jstring_to_cppstr(env, dataPathObj);
-	int colorBits = (int)colorBitsJ;
+	int modeVal = (int)modeInt;
+	bool legacyMode = modeVal <= 8; // current scheme: old 4c = 4, old 8c = 8, new = bigger number
 
 	std::shared_ptr<MultiThreadedDecoder> proc;
 	{
 		std::lock_guard<std::mutex> lock(_mutex);
-		if (!_proc or _proc->color_bits() != colorBits)
-			_proc = std::make_shared<MultiThreadedDecoder>(dataPath, colorBits);
+		if (!_proc or _proc->legacy_mode() != legacyMode)
+			_proc = std::make_shared<MultiThreadedDecoder>(dataPath, legacyMode);
 		proc = _proc;
 	}
 

app/src/cpp/libcimbar/DETAILS.md

@@ -84,7 +84,7 @@ These properties may appear to be magical as you consider them more, and they do
 2. wirehair requires the file contents to be stored in RAM
 	* this relates to the size limit!
 
-This constraint is less of an obstacle than it may seem -- the fountain codes are essentially being used as a wire format, and the encoder and decoder could agree on a scheme to split up, and then reassemble, larger files. Cimbar does not (yet?) implement this, however!
+The size constraint is less of an obstacle than it may seem -- the fountain codes are essentially being used as a wire format, and the encoder and decoder could agree on a scheme to split up, and then reassemble, larger files. Cimbar does not (yet?) implement this, however!
 
 ## Implementation: Decoder
 

app/src/cpp/libcimbar/PERFORMANCE.md

@@ -4,36 +4,48 @@
 ## Numbers of note
 
 * The barcode is `1024x1024` pixels. The individual tiles are `8x8` in a `9x9` grid (there is an empty row/column of spacing on either side)
-* **7500** or 8750 bytes per cimbar image, after error correction
+* **7500** bytes per cimbar image, after error correction
 	* There are 16 possible symbols per tile, encoding 4 bits
 	* There are 4 or 8 possible colors, encoding an additional 2-3 bits per tile.
-	* These 6-7 bits per tile work out to a maximum of 9300-10850 bytes per barcode, though in practice this number is reduced by error correction.
+	* These 6 bits per tile work out to a maximum of 9300 bytes per barcode, though in practice this number is reduced by error correction.
 	* The default ecc setting is 30/155, which is how we go from 9300 -> 7500 bytes of real data for a 4-color cimbar image.
 		* Reed Solomon is not perfect for this use case -- specifically, it corrects byte errors, and cimbar errors tend to involve 1-3 bits at a time. However, since Reed Solomon implementations are ubiquitous, it is currently in use.
 
 ## Current sustained benchmark
 
-* 4-color cimbar with ecc=30:
+* `mode B` (8x8 4-color) cimbar with ecc=30/155:
+	* 4,689,084 bytes (after compression) in 44s -> 852 kilobits/s (~106 KB/s)
+	* mode B was introduced in 0.6.0, and should work in a wide variety of scenarios
+
+* *legacy* `mode 4C` (8x8 4-color) cimbar with ecc=30/155:
 	* 4,717,525 bytes (after compression) in 45s -> 838 kilobits/s (~104 KB/s)
+	* the original configuration. Mostly replaced by mode B.
 
-* 8-color cimbar with ecc=30:
+* *deprecated* `mode 8C` (8x8 8-color) cimbar with ecc=30/155:
 	* 4,717,525 bytes in 40s -> 943 kilobits/s (~118 KB/s)
+	* removed in 0.6.0. 8-color has always been inconsistent, and needs future research
+
+* *beta* `mode S` (5x5 4-color) cimbar with ecc=40/216 (note: not finalized, and requires a special build)
+	* safely >1 Mbit/s
+	* format still a WIP. To be continued...
 
 * details:
 	* cimbar has built-in compression using zstd. What's being measured here is bits over the wire, e.g. data after compression is applied.
-	* these numbers are using https://github.com/sz3/cfc, running with 4 CPU threads on a Qualcomm Snapdragon 625
-		* perhaps I will buy a new cell phone to inflate the benchmark numbers.
-	* the sender is the cimbar.org wasm implementation. An equivalent command line is `./cimbar_send /path/to/file -s`
+	* these numbers are using https://github.com/sz3/cfc, running with 4 CPU threads on a venerable Qualcomm Snapdragon 625
+		* more modern cell CPUs run the decoder more quickly, but it turns out that this does not benefit performance much: the camera is usually the bottleneck.
+	* the sender is the cimbar.org wasm implementation. An equivalent command line is `./cimbar_send /path/to/file`
 		* cimbar.org uses the `shakycam` option to allow the receiver to detect/discard "in between" frames as part of the scan step. This allows it to spend more processing time decoding real data.
 	* burst rate can be higher (or lower)
-		* to this end, lower ecc settings *can* provide better burst rates
-	* 4-color cimbar is currently preferred, and will give more consistent transfer speeds.
-	* 8-color cimbar should be considered a prototype within a prototype. It is considerably more sensitive to lighting conditions and color tints.
+		* to this end, lower ecc settings *can* provide better burst rates. I've aimed for a balance of performance and reliability.
+	* cimbar `mode B` is preferred, and should be the most reliable.
+	* The older `mode 4C` *may* give more consistent transfer speeds in certain scenarios, but is mostly included for backwards-compatibility reasons.
 
 * other notes:
-	* having better lighting in the frame often leads to better results -- this is why cimbar.org has a (mostly) white background. cfc uses android's auto-exposure, auto-focus, etc (it's a very simple app). Good ambient light -- or a white background -- can lead to more consitent quality frame capture.
+	* having better lighting in the frame often leads to better results -- this is why cimbar.org has a (mostly) white background. cfc uses android's auto-exposure, auto-focus, etc (it's a demo app). Good ambient light -- or a white background -- can lead to more consitent quality frame capture.
+		* screen brightness on the sender is good, but ambient light is better.
 	* because of the lighting/exposure question, landscape *may* be better than portrait.
-	* cfc currently has a low resolution, so the cimbar frame should take up as much of the display as possible (trust the guide brackets)
+	* the cimbar frame should take up as much of the display as possible (trust the guide brackets)
+		* the format is designed to decode at resolutions as low as 700x700, but performance may suffer.
 	* similarly, it's best to keep the camera angle straight-on -- instead of at an angle -- to decode the whole image successfully. Decodes should still happen at higher angles, but the "smaller" part of the image may have more errors than the ECC can deal with.
 	* other things to be wary of:
 		* glare from light sources.

app/src/cpp/libcimbar/README.md

@@ -5,10 +5,10 @@
 
 Behold: an experimental barcode format for air-gapped data transfer.
 
-It can sustain speeds of 943+ kilobits/s (~118 KB/s) using just a computer monitor and a smartphone camera!
+It can sustain speeds of 850 kilobits/s (~106 KB/s) using just a computer monitor and a smartphone camera!
 
 <p align="center">
-<img src="https://github.com/sz3/cimbar-samples/blob/v0.5/6bit/4cecc30f.png" width="70%" title="A non-animated cimbar code" >
+<img src="https://github.com/sz3/cimbar-samples/blob/v0.6/b/4cecc30f.png" width="70%" title="A non-animated mode-B cimbar code" >
 </p>
 
 ## Explain?
@@ -31,7 +31,7 @@ No internet/bluetooth/NFC/etc is used. All data is transmitted through the camer
 
 The code is written in C++, and developed/tested on amd64+linux, arm64+android (decoder only), and emscripten+WASM (encoder only). It probably works, or can be made to work, on other platforms.
 
-Crucially, because the encoder compiles to asmjs and wasm, it can run on anything with a modern web browser. There are [releases](https://github.com/sz3/libcimbar/releases/latest) if you wish to run the encoder locally instead of via cimbar.org.
+Crucially, because the encoder compiles to asmjs and wasm, it can run on anything with a modern web browser. For offline use, you can either install cimbar.org as a progressive web app, or [download the latest release](https://github.com/sz3/libcimbar/releases/latest) of `cimbar_js.html`, save it locally, and open it in your web browser.
 
 ## Library dependencies
 

app/src/cpp/libcimbar/TODO.md

@@ -10,6 +10,7 @@ Performance optimizations aside, there are a number of paths that might be inter
 * proper metadata/header information?
 	* would be nice to be able to determine ecc/#colors/#symbols from the cimbar image itself?
 	* The bottom right corner is the obvious place to reclaim space to make this possible.
+	* this is complicated by potential aspect ratio changes for future cimbar modes.
 * multi-frame decoding?
 	* when decoding a static cimbar image, it would be useful to be able to use prior (unsuccessful) decode attempts to inform a future decode, and -- hopefully -- increase the probability of success. Currently, all frames are decoded independently.
 		* there is already a granular confidence metric that could be reused -- the `distance` that's tracked when decoding symbol tiles...
@@ -18,18 +19,18 @@ Performance optimizations aside, there are a number of paths that might be inter
 	* there is surely a more optimal set -- a more rigorous approach should yield lower error rates!
 	* but, more importantly, it may be possible to go up to 32 symbols, and encode 5 symbol bits per tile?
 * optimal symbol size?
-	* the symbols that make up each cell on the cimbar grid are 8x8 (in a 9x9 grid).
-	* this is because imagehash was on 8x8 tiles!
-	* smaller sizes might also work?
+	* the symbols that make up each cell on the cimbar grid are 8x8 (in a 9x9 grid). this is because imagehash was on 8x8 tiles!
+	* smaller sizes might also work? I've been looking into 5x5 (in a 6x6 grid) as a starting point. It seems promising.
 	* the limiting factor is the hamming distance between each image hash "bucket", and the 9Xth percentile decoding errors.
 * optimal color set?
 	* the 4-color (2 bit) pallettes seem reasonable. 8-color, perhaps less so?
 	* this may be a limitation of the algorithm/approach, however. Notably, since each symbol is drawn with one pallette color, all colors need sufficient contrast against the backdrop (#000 or #FFF, depending). This constrains the color space somewhat, and less distinct colors == more errors.
-	* in addition to contrast, there is interplay (that I don't currently understand) between the overall brightness of the image and the exposure time needed for high framerate capture. More clean frames == more troughput.
+	* in addition to contrast, there is interplay between the overall brightness of the image and the exposure time needed for high framerate capture. More clean frames == more troughput.
+	* the camera framerate in the CFC app is limited by auto-exposure and auto-focus behavior. A newer/better decoder app might be helpful.
 * optimal grid size?
 	* 1024x1024 is a remnant of the early prototyping process. There is nothing inherently special about it (except that it fits on a 1920x1080 screen, which seems good)
 		* the tile grid itself is 1008x1008 (1008 == 9x112 -- there are 112 tile rows and columns)
-	* a smaller grid would be less information dense, but more resilient to errors. Probably.
+	* a smaller grid *could* be more resilient to errors, at the expense of data capacity.
 * optimal grid shape?
 	* it's a square because QR codes are square. That's it. Should it be?
 	* I'm strongly considering 4:3 for the next revision.
@@ -41,6 +42,8 @@ Performance optimizations aside, there are a number of paths that might be inter
 * proper GPU support (OpenCV + openCL) on android?
 	* It *might* be useful. [CFC]((https://github.com/sz3/cfc) is the current test bed for this.
 * wasm decoder?
+	* android is going to kick CFC out of the store! (testing requirement)
+		* so it might be time to write this...
 	* probably needs to use Web Workers
 	* in-browser GPGPU support would be interesting (but I'm not counting on it)
 * ???

app/src/cpp/libcimbar/WASM.md

@@ -4,16 +4,30 @@
 
 ## Releases
 
-wasm and asm.js releases are available [here](https://github.com/sz3/libcimbar/releases/latest). The wasm build is what cimbar.org uses. The asm.js build can be downloaded, extracted, and run in a local web browser.
+wasm and asm.js releases are available [here](https://github.com/sz3/libcimbar/releases/latest). The wasm build is what cimbar.org uses. [cimbar_js.html](https://github.com/sz3/libcimbar/releases/latest/cimbar_js.html) can be downloaded and opened/run in a local web browser -- no install required.
 
 ## Build
 
-To build opencv.js (and the static libraries we'll need to build against opencv)...
+To build, use the `package-wasm.sh` script in a docker container:
+
+```
+docker run --mount type=bind,source="$(pwd)",target="/usr/src/app" -it emscripten/emsdk:3.1.39
+```
+Then, inside the container:
+```
+bash /usr/src/app/package-wasm.sh
+```
+
+## Alternative build for the adventurous
+
+Alternatively, if you have a local emscripten setup, you can try to run the package-wasm.sh commands piecemeal:
+
+To build opencv.js:
 ```
 cd /path/to/opencv
 mkdir opencv-build-wasm
 cd opencv-build-wasm
-python ../platforms/js/build_js.py build_wasm --build_wasm --emscripten_dir=/path/to/emscripten
+python3 ../platforms/js/build_js.py build_wasm --build_wasm --emscripten_dir=/path/to/emscripten
 ```
 
 With opencv.js built:
@@ -22,7 +36,7 @@ mkdir build-wasm
 cd build-wasm
 source /path/to/emscripten/emsdk/emsdk_env.sh
 emcmake cmake .. -DUSE_WASM=1 -DOPENCV_DIR=/path/to/opencv
-make -j7 install
+make -j5 install
 ```
 
 (do `-DUSE_WASM=2` to use asm.js instead of wasm)

app/src/cpp/libcimbar/package-wasm.sh

@@ -7,17 +7,20 @@ apt update
 apt install python3 -y
 
 cd opencv4/
-mkdir opencv-build-wasm && cd opencv-build-wasm
+mkdir opencv-build-wasm
+cd opencv-build-wasm
 python3 ../platforms/js/build_js.py build_wasm --build_wasm --emscripten_dir=/emsdk/upstream/emscripten
 
 cd /usr/src/app
-mkdir build-wasm && cd build-wasm
+mkdir build-wasm
+cd build-wasm
 emcmake cmake .. -DUSE_WASM=1 -DOPENCV_DIR=/usr/src/app/opencv4
 make -j5 install
 (cd ../web/ && tar -czvf cimbar.wasm.tar.gz cimbar_js.* index.html main.js)
 
 cd /usr/src/app
-mkdir build-asmjs && cd build-asmjs
+mkdir build-asmjs
+cd build-asmjs
 emcmake cmake .. -DUSE_WASM=2 -DOPENCV_DIR=/usr/src/app/opencv4
 make -j5 install
 (cd ../web/ && zip cimbar.asmjs.zip cimbar_js.js index.html main.js)