Image processing 从编码图像和视频中提取DCT系数
有没有一种方法可以轻松地从编码图像和视频中提取DCT系数(和量化参数)?任何解码器软件都必须使用它们来解码块DCT编码的图像和视频。所以我很确定解码器知道它们是什么。有没有办法让使用解码器的人知道 我正在实现一些直接在DCT域工作的视频质量评估算法。目前,我的大部分代码都使用OpenCV,因此如果有人知道使用该框架的解决方案,那就太好了。我不介意使用其他库(可能是libjpeg,但这似乎只适用于静态图像),但我主要关心的是尽可能少地做特定于格式的工作(我不想重新发明轮子并编写自己的解码器)。我希望能够打开OpenCV可以打开的任何视频/图像(H.264、MPEG、JPEG等),如果是块DCT编码的,则可以获得DCT系数 在最坏的情况下,我知道我可以编写自己的块DCT代码,通过它运行解压缩的帧/图像,然后我就会回到DCT域。这不是一个优雅的解决方案,我希望我能做得更好 目前,我使用相当常见的OpenCV样板打开图像:Image processing 从编码图像和视频中提取DCT系数,image-processing,opencv,video-processing,dct,Image Processing,Opencv,Video Processing,Dct,有没有一种方法可以轻松地从编码图像和视频中提取DCT系数(和量化参数)?任何解码器软件都必须使用它们来解码块DCT编码的图像和视频。所以我很确定解码器知道它们是什么。有没有办法让使用解码器的人知道 我正在实现一些直接在DCT域工作的视频质量评估算法。目前,我的大部分代码都使用OpenCV,因此如果有人知道使用该框架的解决方案,那就太好了。我不介意使用其他库(可能是libjpeg,但这似乎只适用于静态图像),但我主要关心的是尽可能少地做特定于格式的工作(我不想重新发明轮子并编写自己的解码器)。我希
IplImage *image = cvLoadImage(filename);
// Run quality assessment metric
我在视频中使用的代码同样微不足道:
CvCapture *capture = cvCaptureFromAVI(filename);
while (cvGrabFrame(capture))
{
IplImage *frame = cvRetrieveFrame(capture);
// Run quality assessment metric on frame
}
cvReleaseCapture(&capture);
在这两种情况下,我都得到了BGR格式的3通道
IplImage
。还有什么办法可以得到DCT系数吗?好吧,我读了一些书,我最初的问题似乎是一厢情愿
基本上,不可能从H.264视频帧中获得DCT系数,原因很简单,H.264。它使用不同的变换(整数变换)。接下来,该变换的系数不一定会逐帧改变——H.264更聪明,因为它会将帧分割成片。应该可以通过一个特殊的解码器获得这些系数,但我怀疑OpenCV是否会向用户公开这些系数
对于JPEG来说,情况更乐观一些。正如我所怀疑的,为您公开DCT系数。我写了一个小应用程序来证明它是有效的(最后是源代码)。它使用每个块的DC项生成新图像。因为DC项等于块平均值(经过适当缩放后),所以DC图像是输入JPEG图像的下采样版本
编辑:修复了源中的缩放
原始图像(512 x 512):
DC图像(64x64):luma Cr Cb RGB
来源(C++):
#包括
#包括
#包括
#包括
外部“C”
{
#包括“jpeglib.h”
#包括
}
#定义调试0
#定义输出图像1
/*
*从指定组件中提取DC项。
*/
IplImage*
提取dc(解压cinfo,解压barray,解压系数,整数ci)
{
jpeg_component_info*ci_ptr=&cinfo->comp_info[ci];
CvSize size=CvSize(ci_ptr->宽度_in_块,ci_ptr->高度_in_块);
IplImage*dc=cvCreateImage(大小,IPL_深度_8U,1);
断言(dc!=NULL);
JQUANT\u TBL*TBL=ci\u ptr->quant\u table;
UINT16 dc_quant=tbl->quantval[0];
#如果调试
printf(“DCT方法:%x\n”,cinfo->DCT\u方法);
printf
(
“组件:%d(%d x%d个块)采样:(%d x%d)\n”,
ci,
ci_ptr->块中的宽度,
ci_ptr->高度(以块为单位),
ci_ptr->h_samp_因子,
ci_ptr->v_samp_因子
);
printf(“量化表:%d\n”,ci);
对于(int i=0;i数量[i]);
如果((i+1)%8==0)
printf(“\n”);
}
printf(“原始DC系数:\n”);
#恩迪夫
JBLOCKARRAY buf=
(cinfo->mem->access\u virt\u barray)
(
(j_common_ptr)cinfo,,
系数[ci],
0,
ci_ptr->v_samp_因子,
错误的
);
对于(int sf=0;(JDIMENSION)sfheight_in_blocks;++sf)
{
对于(JDIMENSION b=0;bwidth_in_blocks;++b)
{
int强度=0;
强度=buf[sf][b][0]*dc_-quant/DCTSIZE+128;
强度=最大值(0,强度);
强度=最小值(255,强度);
cvSet2D(dc,sf,(int)b,cvScalar(intensity));
#如果调试
printf(“%2d”,buf[sf][b][0]);
#恩迪夫
}
#如果调试
printf(“\n”);
#恩迪夫
}
返回dc;
}
IplImage*高档色度(IplImage*四分之一,CvSize全尺寸)
{
IplImage*full=cvCreateImage(全尺寸,IPL深度,1);
cvResize(四分之一、完整、CV_-INTER_-NN);
全额退还;
}
全球(国际)
读取JPEG文件(字符*文件名,IplImage**dc)
{
/*此结构包含JPEG解压缩参数和指向的指针
*工作空间(JPEG库根据需要分配)。
*/
结构jpeg\u解压缩\u结构cinfo;
结构jpeg\u错误\u管理器jerr;
/*更多的东西*/
文件*infle;/*源文件*/
/*在本例中,我们希望在执行任何其他操作之前打开输入文件,
*因此,下面的setjmp()错误恢复可以假定文件已打开。
*非常重要:如果您使用的机器
*需要它才能读取二进制文件。
*/
if((infle=fopen(文件名,“rb”))==NULL){
fprintf(stderr,“无法打开%s\n”,文件名);
返回0;
}
/*步骤1:分配并初始化JPEG解压缩对象*/
cinfo.err=jpeg\u std\u error(&jerr);
/*现在我们可以初始化JPEG解压缩对象*/
jpeg\u创建\u解压缩(&cinfo);
/*步骤2:指定数据源(例如,文件)*/
jpeg_stdio_src(&cinfo,infle);
/*步骤3:使用jpeg_read_头()读取文件参数*/
(void)jpeg_read_头(&cinfo,TRUE);
/*我们可以忽略jpeg_read_头的返回值,因为
*(a)stdio数据源无法暂停,以及
*(b)我们传递了TRUE,将拒绝仅表格JPEG文件作为错误。
*有关详细信息,请参阅libjpeg.txt。
*/
/*台阶
#include <stdio.h>
#include <assert.h>
#include <cv.h>
#include <highgui.h>
extern "C"
{
#include "jpeglib.h"
#include <setjmp.h>
}
#define DEBUG 0
#define OUTPUT_IMAGES 1
/*
* Extract the DC terms from the specified component.
*/
IplImage *
extract_dc(j_decompress_ptr cinfo, jvirt_barray_ptr *coeffs, int ci)
{
jpeg_component_info *ci_ptr = &cinfo->comp_info[ci];
CvSize size = cvSize(ci_ptr->width_in_blocks, ci_ptr->height_in_blocks);
IplImage *dc = cvCreateImage(size, IPL_DEPTH_8U, 1);
assert(dc != NULL);
JQUANT_TBL *tbl = ci_ptr->quant_table;
UINT16 dc_quant = tbl->quantval[0];
#if DEBUG
printf("DCT method: %x\n", cinfo->dct_method);
printf
(
"component: %d (%d x %d blocks) sampling: (%d x %d)\n",
ci,
ci_ptr->width_in_blocks,
ci_ptr->height_in_blocks,
ci_ptr->h_samp_factor,
ci_ptr->v_samp_factor
);
printf("quantization table: %d\n", ci);
for (int i = 0; i < DCTSIZE2; ++i)
{
printf("% 4d ", (int)(tbl->quantval[i]));
if ((i + 1) % 8 == 0)
printf("\n");
}
printf("raw DC coefficients:\n");
#endif
JBLOCKARRAY buf =
(cinfo->mem->access_virt_barray)
(
(j_common_ptr)cinfo,
coeffs[ci],
0,
ci_ptr->v_samp_factor,
FALSE
);
for (int sf = 0; (JDIMENSION)sf < ci_ptr->height_in_blocks; ++sf)
{
for (JDIMENSION b = 0; b < ci_ptr->width_in_blocks; ++b)
{
int intensity = 0;
intensity = buf[sf][b][0]*dc_quant/DCTSIZE + 128;
intensity = MAX(0, intensity);
intensity = MIN(255, intensity);
cvSet2D(dc, sf, (int)b, cvScalar(intensity));
#if DEBUG
printf("% 2d ", buf[sf][b][0]);
#endif
}
#if DEBUG
printf("\n");
#endif
}
return dc;
}
IplImage *upscale_chroma(IplImage *quarter, CvSize full_size)
{
IplImage *full = cvCreateImage(full_size, IPL_DEPTH_8U, 1);
cvResize(quarter, full, CV_INTER_NN);
return full;
}
GLOBAL(int)
read_JPEG_file (char * filename, IplImage **dc)
{
/* This struct contains the JPEG decompression parameters and pointers to
* working space (which is allocated as needed by the JPEG library).
*/
struct jpeg_decompress_struct cinfo;
struct jpeg_error_mgr jerr;
/* More stuff */
FILE * infile; /* source file */
/* In this example we want to open the input file before doing anything else,
* so that the setjmp() error recovery below can assume the file is open.
* VERY IMPORTANT: use "b" option to fopen() if you are on a machine that
* requires it in order to read binary files.
*/
if ((infile = fopen(filename, "rb")) == NULL) {
fprintf(stderr, "can't open %s\n", filename);
return 0;
}
/* Step 1: allocate and initialize JPEG decompression object */
cinfo.err = jpeg_std_error(&jerr);
/* Now we can initialize the JPEG decompression object. */
jpeg_create_decompress(&cinfo);
/* Step 2: specify data source (eg, a file) */
jpeg_stdio_src(&cinfo, infile);
/* Step 3: read file parameters with jpeg_read_header() */
(void) jpeg_read_header(&cinfo, TRUE);
/* We can ignore the return value from jpeg_read_header since
* (a) suspension is not possible with the stdio data source, and
* (b) we passed TRUE to reject a tables-only JPEG file as an error.
* See libjpeg.txt for more info.
*/
/* Step 4: set parameters for decompression */
/* In this example, we don't need to change any of the defaults set by
* jpeg_read_header(), so we do nothing here.
*/
jvirt_barray_ptr *coeffs = jpeg_read_coefficients(&cinfo);
IplImage *y = extract_dc(&cinfo, coeffs, 0);
IplImage *cb_q = extract_dc(&cinfo, coeffs, 1);
IplImage *cr_q = extract_dc(&cinfo, coeffs, 2);
IplImage *cb = upscale_chroma(cb_q, cvGetSize(y));
IplImage *cr = upscale_chroma(cr_q, cvGetSize(y));
cvReleaseImage(&cb_q);
cvReleaseImage(&cr_q);
#if OUTPUT_IMAGES
cvSaveImage("y.png", y);
cvSaveImage("cb.png", cb);
cvSaveImage("cr.png", cr);
#endif
*dc = cvCreateImage(cvGetSize(y), IPL_DEPTH_8U, 3);
assert(dc != NULL);
cvMerge(y, cr, cb, NULL, *dc);
cvReleaseImage(&y);
cvReleaseImage(&cb);
cvReleaseImage(&cr);
/* Step 7: Finish decompression */
(void) jpeg_finish_decompress(&cinfo);
/* We can ignore the return value since suspension is not possible
* with the stdio data source.
*/
/* Step 8: Release JPEG decompression object */
/* This is an important step since it will release a good deal of memory. */
jpeg_destroy_decompress(&cinfo);
fclose(infile);
return 1;
}
int
main(int argc, char **argv)
{
int ret = 0;
if (argc != 2)
{
fprintf(stderr, "usage: %s filename.jpg\n", argv[0]);
return 1;
}
IplImage *dc = NULL;
ret = read_JPEG_file(argv[1], &dc);
assert(dc != NULL);
IplImage *rgb = cvCreateImage(cvGetSize(dc), IPL_DEPTH_8U, 3);
cvCvtColor(dc, rgb, CV_YCrCb2RGB);
#if OUTPUT_IMAGES
cvSaveImage("rgb.png", rgb);
#else
cvNamedWindow("DC", CV_WINDOW_AUTOSIZE);
cvShowImage("DC", rgb);
cvWaitKey(0);
#endif
cvReleaseImage(&dc);
cvReleaseImage(&rgb);
return 0;
}
#include <iostream>
#include <stdio.h>
#include <jpeglib.h>
#include <stdlib.h>
#include <setjmp.h>
#include <fstream>
#include <QVector>
int read_jpeg_file( char *filename, QVector<QVector<int> > &dct_coeff, QVector<unsigned short> &quant_tbl)
{
struct jpeg_decompress_struct cinfo;
struct jpeg_error_mgr jerr;
FILE * infile;
if ((infile = fopen(filename, "rb")) == NULL) {
fprintf(stderr, "can't open %s\n", filename);
return 0;
}
cinfo.err = jpeg_std_error(&jerr);
jpeg_create_decompress(&cinfo);
jpeg_stdio_src(&cinfo, infile);
(void) jpeg_read_header(&cinfo, TRUE);
jvirt_barray_ptr *coeffs_array = jpeg_read_coefficients(&cinfo);
for (int ci = 0; ci < 1; ci++)
{
JBLOCKARRAY buffer_one;
JCOEFPTR blockptr_one;
jpeg_component_info* compptr_one;
compptr_one = cinfo.comp_info + ci;
for (int by = 0; by < compptr_one->height_in_blocks; by++)
{
buffer_one = (cinfo.mem->access_virt_barray)((j_common_ptr)&cinfo, coeffs_array[ci], by, (JDIMENSION)1, FALSE);
for (int bx = 0; bx < compptr_one->width_in_blocks; bx++)
{
blockptr_one = buffer_one[0][bx];
QVector<int> tmp;
for (int bi = 0; bi < 64; bi++)
{
tmp.append(blockptr_one[bi]);
}
dct_coeff.push_back(tmp);
}
}
}
// coantization table
j_decompress_ptr dec_cinfo = (j_decompress_ptr) &cinfo;
jpeg_component_info *ci_ptr = &dec_cinfo->comp_info[0];
JQUANT_TBL *tbl = ci_ptr->quant_table;
for(int ci =0 ; ci < 64; ci++){
quant_tbl.append(tbl->quantval[ci]);
}
return 1;
}
int main()
{
QVector<QVector<int> > v;
QVector<unsigned short> quant_tbl;
char *infilename = "your_image.jpg";
std::ofstream out;
out.open("out_dct.txt");
if( read_jpeg_file( infilename, v, quant_tbl ) > 0 ){
for(int j = 0; j < v.size(); j++ ){
for (int i = 0; i < v[0].size(); ++i){
out << v[j][i] << "\t";
}
out << "---------------" << std::endl;
}
out << "\n\n\n" << std::string(10,'-') << std::endl;
out << "\nQauntization Table:" << std::endl;
for(int i = 0; i < quant_tbl.size(); i++ ){
out << quant_tbl[i] << "\t";
}
}
else{
std::cout << "Can not read, Returned With Error";
return -1;
}
out.close();
return 0;
}