[Android]-图片JNI（C++）高斯模糊的实现与比较

前几天一直在弄android上的图片模糊效果的实现！

一直找不到方法，看别人说都是调用JNI，但是JNI这个东西我还真不熟悉啊！

只好从零开始了！这里不讲JNI的平台搭建，只讲JNI的关键代码，具体的项目我会共享出来给大家！

对于JNI下使用C++来模糊图片这个我真的没找到，只好自己写C++的来实现了。

在国外的一个项目中找到了一个”堆栈模糊效果“，原型如下：

// Stack Blur v1.0
//
// Author: Mario Klingemann <mario@quasimondo.com>
// http://incubator.quasimondo.com // created Feburary 29, 2004

// This is a compromise between Gaussian Blur and Box blur
// It creates much better looking blurs than Box Blur, but is
// 7x faster than my Gaussian Blur implementation.
//
// I called it Stack Blur because this describes best how this
// filter works internally: it creates a kind of moving stack
// of colors whilst scanning through the image. Thereby it
// just has to add one new block of color to the right side
// of the stack and remove the leftmost color. The remaining
// colors on the topmost layer of the stack are either added on
// or reduced by one, depending on if they are on the right or
// on the left side of the stack.
//
// If you are using this algorithm in your code please add
// the following line:
//
// Stack Blur Algorithm by Mario Klingemann <mario@quasimondo.com>

PImage a;
PImage b;

void setup()
{
a=loadImage("dog.jpg");
size(a.width, a.height);
b=new PImage(a.width, a.height);
fill(255);
noStroke();
frameRate(25);
}

void draw()
{
System.arraycopy(a.pixels,0,b.pixels,0,a.pixels.length);
fastblur(b,mouseY/4);
image(b, 0, 0);
}

void fastblur(PImage img,int radius){

if (radius<1){
return;
}
int[] pix=img.pixels;
int w=img.width;
int h=img.height;
int wm=w-1;
int hm=h-1;
int wh=w*h;
int div=radius+radius+1;

int r[]=new int[wh];
int g[]=new int[wh];
int b[]=new int[wh];
int rsum,gsum,bsum,x,y,i,p,yp,yi,yw;
int vmin[] = new int[max(w,h)];

int divsum=(div+1)>>1;
divsum*=divsum;
int dv[]=new int[256*divsum];
for (i=0;i<256*divsum;i++){
dv[i]=(i/divsum);
}

yw=yi=0;

int[][] stack=new int[div][3];
int stackpointer;
int stackstart;
int[] sir;
int rbs;
int r1=radius+1;
int routsum,goutsum,boutsum;
int rinsum,ginsum,binsum;

for (y=0;y<h;y++){
rinsum=ginsum=binsum=routsum=goutsum=boutsum=rsum=gsum=bsum=0;
for(i=-radius;i<=radius;i++){
p=pix[yi+min(wm,max(i,0))];
sir=stack[i+radius];
sir[0]=(p & 0xff0000)>>16;
sir[1]=(p & 0x00ff00)>>8;
sir[2]=(p & 0x0000ff);
rbs=r1-abs(i);
rsum+=sir[0]*rbs;
gsum+=sir[1]*rbs;
bsum+=sir[2]*rbs;
if (i>0){
rinsum+=sir[0];
ginsum+=sir[1];
binsum+=sir[2];
} else {
routsum+=sir[0];
goutsum+=sir[1];
boutsum+=sir[2];
}
}
stackpointer=radius;

for (x=0;x<w;x++){

r[yi]=dv[rsum];
g[yi]=dv[gsum];
b[yi]=dv[bsum];

rsum-=routsum;
gsum-=goutsum;
bsum-=boutsum;

stackstart=stackpointer-radius+div;
sir=stack[stackstart%div];

routsum-=sir[0];
goutsum-=sir[1];
boutsum-=sir[2];

if(y==0){
vmin[x]=min(x+radius+1,wm);
}
p=pix[yw+vmin[x]];

sir[0]=(p & 0xff0000)>>16;
sir[1]=(p & 0x00ff00)>>8;
sir[2]=(p & 0x0000ff);

rinsum+=sir[0];
ginsum+=sir[1];
binsum+=sir[2];

rsum+=rinsum;
gsum+=ginsum;
bsum+=binsum;

stackpointer=(stackpointer+1)%div;
sir=stack[(stackpointer)%div];

routsum+=sir[0];
goutsum+=sir[1];
boutsum+=sir[2];

rinsum-=sir[0];
ginsum-=sir[1];
binsum-=sir[2];

yi++;
}
yw+=w;
}
for (x=0;x<w;x++){
rinsum=ginsum=binsum=routsum=goutsum=boutsum=rsum=gsum=bsum=0;
yp=-radius*w;
for(i=-radius;i<=radius;i++){
yi=max(0,yp)+x;

sir=stack[i+radius];

sir[0]=r[yi];
sir[1]=g[yi];
sir[2]=b[yi];

rbs=r1-abs(i);

rsum+=r[yi]*rbs;
gsum+=g[yi]*rbs;
bsum+=b[yi]*rbs;

if (i>0){
rinsum+=sir[0];
ginsum+=sir[1];
binsum+=sir[2];
} else {
routsum+=sir[0];
goutsum+=sir[1];
boutsum+=sir[2];
}

if(i<hm){
yp+=w;
}
}
yi=x;
stackpointer=radius;
for (y=0;y<h;y++){
pix[yi]=0xff000000 | (dv[rsum]<<16) | (dv[gsum]<<8) | dv[bsum];

rsum-=routsum;
gsum-=goutsum;
bsum-=boutsum;

stackstart=stackpointer-radius+div;
sir=stack[stackstart%div];

routsum-=sir[0];
goutsum-=sir[1];
boutsum-=sir[2];

if(x==0){
vmin[y]=min(y+r1,hm)*w;
}
p=x+vmin[y];

sir[0]=r[p];
sir[1]=g[p];
sir[2]=b[p];

rinsum+=sir[0];
ginsum+=sir[1];
binsum+=sir[2];

rsum+=rinsum;
gsum+=ginsum;
bsum+=binsum;

stackpointer=(stackpointer+1)%div;
sir=stack[stackpointer];

routsum+=sir[0];
goutsum+=sir[1];
boutsum+=sir[2];

rinsum-=sir[0];
ginsum-=sir[1];
binsum-=sir[2];

yi+=w;
}
}

img.updatePixels();
}

同时找到一个借鉴这个所改进后成为Java的代码，具体如下：

public static Bitmap doBlur(Bitmap sentBitmap, int radius, boolean canReuseInBitmap) {
// Stack Blur v1.0 from
// http://www.quasimondo.com/StackBlurForCanvas/StackBlurDemo.html //
// Java Author: Mario Klingemann <mario at quasimondo.com>
// http://incubator.quasimondo.com // created Feburary 29, 2004
// Android port : Yahel Bouaziz <yahel at kayenko.com>
// http://www.kayenko.com // ported april 5th, 2012

// This is a compromise between Gaussian Blur and Box blur
// It creates much better looking blurs than Box Blur, but is
// 7x faster than my Gaussian Blur implementation.
//
// I called it Stack Blur because this describes best how this
// filter works internally: it creates a kind of moving stack
// of colors whilst scanning through the image. Thereby it
// just has to add one new block of color to the right side
// of the stack and remove the leftmost color. The remaining
// colors on the topmost layer of the stack are either added on
// or reduced by one, depending on if they are on the right or
// on the left side of the stack.
//
// If you are using this algorithm in your code please add
// the following line:
//
// Stack Blur Algorithm by Mario Klingemann <mario@quasimondo.com>

Bitmap bitmap;
if (canReuseInBitmap) {
bitmap = sentBitmap;
} else {
bitmap = sentBitmap.copy(sentBitmap.getConfig(), true);
}

if (radius < 1) {
return (null);
}

int w = bitmap.getWidth();
int h = bitmap.getHeight();

int[] pix = new int[w * h];
bitmap.getPixels(pix, 0, w, 0, 0, w, h);

int wm = w - 1;
int hm = h - 1;
int wh = w * h;
int div = radius + radius + 1;

int r[] = new int[wh];
int g[] = new int[wh];
int b[] = new int[wh];
int rsum, gsum, bsum, x, y, i, p, yp, yi, yw;
int vmin[] = new int[Math.max(w, h)];

int divsum = (div + 1) >> 1;
divsum *= divsum;
int dv[] = new int[256 * divsum];
for (i = 0; i < 256 * divsum; i++) {
dv[i] = (i / divsum);
}

yw = yi = 0;

int[][] stack = new int[div][3];
int stackpointer;
int stackstart;
int[] sir;
int rbs;
int r1 = radius + 1;
int routsum, goutsum, boutsum;
int rinsum, ginsum, binsum;

for (y = 0; y < h; y++) {
rinsum = ginsum = binsum = routsum = goutsum = boutsum = rsum = gsum = bsum = 0;
for (i = -radius; i <= radius; i++) {
p = pix[yi + Math.min(wm, Math.max(i, 0))];
sir = stack[i + radius];
sir[0] = (p & 0xff0000) >> 16;
sir[1] = (p & 0x00ff00) >> 8;
sir[2] = (p & 0x0000ff);
rbs = r1 - Math.abs(i);
rsum += sir[0] * rbs;
gsum += sir[1] * rbs;
bsum += sir[2] * rbs;
if (i > 0) {
rinsum += sir[0];
ginsum += sir[1];
binsum += sir[2];
} else {
routsum += sir[0];
goutsum += sir[1];
boutsum += sir[2];
}
}
stackpointer = radius;

for (x = 0; x < w; x++) {

r[yi] = dv[rsum];
g[yi] = dv[gsum];
b[yi] = dv[bsum];

rsum -= routsum;
gsum -= goutsum;
bsum -= boutsum;

stackstart = stackpointer - radius + div;
sir = stack[stackstart % div];

routsum -= sir[0];
goutsum -= sir[1];
boutsum -= sir[2];

if (y == 0) {
vmin[x] = Math.min(x + radius + 1, wm);
}
p = pix[yw + vmin[x]];

sir[0] = (p & 0xff0000) >> 16;
sir[1] = (p & 0x00ff00) >> 8;
sir[2] = (p & 0x0000ff);

rinsum += sir[0];
ginsum += sir[1];
binsum += sir[2];

rsum += rinsum;
gsum += ginsum;
bsum += binsum;

stackpointer = (stackpointer + 1) % div;
sir = stack[(stackpointer) % div];

routsum += sir[0];
goutsum += sir[1];
boutsum += sir[2];

rinsum -= sir[0];
ginsum -= sir[1];
binsum -= sir[2];

yi++;
}
yw += w;
}
for (x = 0; x < w; x++) {
rinsum = ginsum = binsum = routsum = goutsum = boutsum = rsum = gsum = bsum = 0;
yp = -radius * w;
for (i = -radius; i <= radius; i++) {
yi = Math.max(0, yp) + x;

sir = stack[i + radius];

sir[0] = r[yi];
sir[1] = g[yi];
sir[2] = b[yi];

rbs = r1 - Math.abs(i);

rsum += r[yi] * rbs;
gsum += g[yi] * rbs;
bsum += b[yi] * rbs;

if (i > 0) {
rinsum += sir[0];
ginsum += sir[1];
binsum += sir[2];
} else {
routsum += sir[0];
goutsum += sir[1];
boutsum += sir[2];
}

if (i < hm) {
yp += w;
}
}
yi = x;
stackpointer = radius;
for (y = 0; y < h; y++) {
// Preserve alpha channel: ( 0xff000000 & pix[yi] )
pix[yi] = (0xff000000 & pix[yi]) | (dv[rsum] << 16) | (dv[gsum] << 8) | dv[bsum];

rsum -= routsum;
gsum -= goutsum;
bsum -= boutsum;

stackstart = stackpointer - radius + div;
sir = stack[stackstart % div];

routsum -= sir[0];
goutsum -= sir[1];
boutsum -= sir[2];

if (x == 0) {
vmin[y] = Math.min(y + r1, hm) * w;
}
p = x + vmin[y];

sir[0] = r[p];
sir[1] = g[p];
sir[2] = b[p];

rinsum += sir[0];
ginsum += sir[1];
binsum += sir[2];

rsum += rinsum;
gsum += ginsum;
bsum += binsum;

stackpointer = (stackpointer + 1) % div;
sir = stack[stackpointer];

routsum += sir[0];
goutsum += sir[1];
boutsum += sir[2];

rinsum -= sir[0];
ginsum -= sir[1];
binsum -= sir[2];

yi += w;
}
}

bitmap.setPixels(pix, 0, w, 0, 0, w, h);
return (bitmap);
}

借鉴于此我弄了一个C的代码，基本上的整体过程都没有变化，只是改变成了C（C++也可已）的而已：

文件名：ImageBlur.c

/*************************************************
Copyright:  Copyright QIUJUER 2013.
Author:		Qiujuer
Date:		2014-04-18
Description:实现图片模糊处理
**************************************************/
#include<malloc.h>

#define ABS(a) ((a)<(0)?(-a):(a))
#define MAX(a,b) ((a)>(b)?(a):(b))
#define MIN(a,b) ((a)<(b)?(a):(b))

/*************************************************
Function:		StackBlur(堆栈模糊)
Description:    使用堆栈方式进行图片像素模糊处理
Calls:          malloc
Table Accessed: NULL
Table Updated:	NULL
Input:          像素点集合，图片宽，图片高，模糊半径
Output:         返回模糊后的像素点集合
Return:         返回模糊后的像素点集合
Others:         NULL
*************************************************/
static int* StackBlur(int* pix, int w, int h, int radius) {
int wm = w - 1;
int hm = h - 1;
int wh = w * h;
int div = radius + radius + 1;

int *r = (int *)malloc(wh * sizeof(int));
int *g = (int *)malloc(wh * sizeof(int));
int *b = (int *)malloc(wh * sizeof(int));
int rsum, gsum, bsum, x, y, i, p, yp, yi, yw;

int *vmin = (int *)malloc(MAX(w,h) * sizeof(int));

int divsum = (div + 1) >> 1;
divsum *= divsum;
int *dv = (int *)malloc(256 * divsum * sizeof(int));
for (i = 0; i < 256 * divsum; i++) {
dv[i] = (i / divsum);
}

yw = yi = 0;

int(*stack)[3] = (int(*)[3])malloc(div * 3 * sizeof(int));
int stackpointer;
int stackstart;
int *sir;
int rbs;
int r1 = radius + 1;
int routsum, goutsum, boutsum;
int rinsum, ginsum, binsum;

for (y = 0; y < h; y++) {
rinsum = ginsum = binsum = routsum = goutsum = boutsum = rsum = gsum = bsum = 0;
for (i = -radius; i <= radius; i++) {
p = pix[yi + (MIN(wm, MAX(i, 0)))];
sir = stack[i + radius];
sir[0] = (p & 0xff0000) >> 16;
sir[1] = (p & 0x00ff00) >> 8;
sir[2] = (p & 0x0000ff);

rbs = r1 - ABS(i);
rsum += sir[0] * rbs;
gsum += sir[1] * rbs;
bsum += sir[2] * rbs;
if (i > 0) {
rinsum += sir[0];
ginsum += sir[1];
binsum += sir[2];
}
else {
routsum += sir[0];
goutsum += sir[1];
boutsum += sir[2];
}
}
stackpointer = radius;

for (x = 0; x < w; x++) {

r[yi] = dv[rsum];
g[yi] = dv[gsum];
b[yi] = dv[bsum];

rsum -= routsum;
gsum -= goutsum;
bsum -= boutsum;

stackstart = stackpointer - radius + div;
sir = stack[stackstart % div];

routsum -= sir[0];
goutsum -= sir[1];
boutsum -= sir[2];

if (y == 0) {
vmin[x] = MIN(x + radius + 1, wm);
}
p = pix[yw + vmin[x]];

sir[0] = (p & 0xff0000) >> 16;
sir[1] = (p & 0x00ff00) >> 8;
sir[2] = (p & 0x0000ff);

rinsum += sir[0];
ginsum += sir[1];
binsum += sir[2];

rsum += rinsum;
gsum += ginsum;
bsum += binsum;

stackpointer = (stackpointer + 1) % div;
sir = stack[(stackpointer) % div];

routsum += sir[0];
goutsum += sir[1];
boutsum += sir[2];

rinsum -= sir[0];
ginsum -= sir[1];
binsum -= sir[2];

yi++;
}
yw += w;
}
for (x = 0; x < w; x++) {
rinsum = ginsum = binsum = routsum = goutsum = boutsum = rsum = gsum = bsum = 0;
yp = -radius * w;
for (i = -radius; i <= radius; i++) {
yi = MAX(0, yp) + x;

sir = stack[i + radius];

sir[0] = r[yi];
sir[1] = g[yi];
sir[2] = b[yi];

rbs = r1 - ABS(i);

rsum += r[yi] * rbs;
gsum += g[yi] * rbs;
bsum += b[yi] * rbs;

if (i > 0) {
rinsum += sir[0];
ginsum += sir[1];
binsum += sir[2];
}
else {
routsum += sir[0];
goutsum += sir[1];
boutsum += sir[2];
}

if (i < hm) {
yp += w;
}
}
yi = x;
stackpointer = radius;
for (y = 0; y < h; y++) {
// Preserve alpha channel: ( 0xff000000 & pix[yi] )
pix[yi] = (0xff000000 & pix[yi]) | (dv[rsum] << 16) | (dv[gsum] << 8) | dv[bsum];

rsum -= routsum;
gsum -= goutsum;
bsum -= boutsum;

stackstart = stackpointer - radius + div;
sir = stack[stackstart % div];

routsum -= sir[0];
goutsum -= sir[1];
boutsum -= sir[2];

if (x == 0) {
vmin[y] = MIN(y + r1, hm) * w;
}
p = x + vmin[y];

sir[0] = r[p];
sir[1] = g[p];
sir[2] = b[p];

rinsum += sir[0];
ginsum += sir[1];
binsum += sir[2];

rsum += rinsum;
gsum += ginsum;
bsum += binsum;

stackpointer = (stackpointer + 1) % div;
sir = stack[stackpointer];

routsum += sir[0];
goutsum += sir[1];
boutsum += sir[2];

rinsum -= sir[0];
ginsum -= sir[1];
binsum -= sir[2];

yi += w;
}
}

free(r);
free(g);
free(b);
free(vmin);
free(dv);
free(stack);
return(pix);
}

在改为这个的过程中还遇到 了一个很喜剧的问题，我发现我使用这个来进行调用后结果程序内存一直增大，直到500多M，直接卡死。我知道是我写的有内存泄漏了！

然后找了一下，发现果然是。只好进行free了。然后一下就好了，发现内存占用的确比Java的要少，速度也是要快一些！

在JNI中的实现我使用了两种方案，一种是直接传递文件，一直是传递像素点集合进行模糊！分别如下：

/*
* Class:     com_accumulation_imageblurring_app_jni_ImageBlur
* Method:    blurIntArray
* Signature: ([IIII)V
*/
JNIEXPORT void JNICALL Java_com_accumulation_imageblurring_app_jni_ImageBlur_blurIntArray
(JNIEnv *, jclass, jintArray, jint, jint, jint);

/*
* Class:     com_accumulation_imageblurring_app_jni_ImageBlur
* Method:    blurBitMap
* Signature: (Landroid/graphics/Bitmap;I)V
*/
JNIEXPORT void JNICALL Java_com_accumulation_imageblurring_app_jni_ImageBlur_blurBitMap
(JNIEnv *, jclass, jobject, jint);

对应的Java调用：

/**
* Created by QIUJUER on 2014/4/19.
*/
public class ImageBlur {
public static native void blurIntArray(int[] pImg, int w, int h, int r);

public static native void blurBitMap(Bitmap bitmap, int r);

static {
System.loadLibrary("JNI_ImageBlur");
}
}

///////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////

此时我做了3种测试，一种是直接在Java层实现，一种是传递像素点集合模糊，还有就是直接传递图片进行模糊，结果如下：













通过上面的比较我们可以得出这样的结论：

1.Java的确最慢，但是其实也慢不了多少，虚拟机优化好了一样猛。

2.C中直接传递像素集合的速度最快（第一次启动）

3.在我多次切换界面后发现，直接传递像素点集合的耗时会增加，从60多到120多。

4.多次切换后发现，其实直接传递像素点的速度与传递图片过去的速度几乎一样。

5.多次操作后发现传递文件的波动较小，在100~138之间，其次是传递像素点集合的波动较大，java的波动最大！

以上就是我的结论，可能有些不正确，但是在我的机器上的确是这样！

注：勾选选择框“Downscale before blur”会先压缩图片后模糊然后放大图片，这样的情况下，模糊效果会稍微损失一些效果，但是其速度确实无法比拟的。

其耗时在：1~10ms内可运算完成。当然与你要模糊的大小有关系！

最后：项目地址：GitHub