有没有一种方法可以轻松地从编码的图像和视频中提取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。有没有办法将它们暴露给正在使用解码器的任何人？
我正在实现一些可直接在DCT域中工作的视频质量评估算法。目前，我的大多数代码都使用OpenCV，因此如果有人知道使用该框架的解决方案，那将是很好的。我不介意使用其他库(也许是libjpeg，但这似乎仅用于静态图像)，但是我主要关心的是尽可能少地进行特定于格式的工作(我不想重新发明轮子并编写代码我自己的解码器)。我希望能够打开OpenCV可以打开的任何视频/图像(H.264，MPEG，JPEG等)，并且如果将其进行DCT编码，则可以获取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，然后回到DCT域。那不是一个很好的解决方案，我希望我能做得更好。
目前，我使用相当普通的OpenCV样板打开图像:
IplImage *image = cvLoadImage(filename);
// Run quality assessment metric
我用于视频的代码也很简单:
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，我都会以BGR格式获得3通道
IplImage。有什么办法可以获取DCT系数吗？ 最佳答案
好吧，我做了一些阅读，最初的问题似乎是一厢情愿的例子。
基本上，由于H.264 doesn't use DCT的简单原因，不可能从H.264视频帧中获得DCT系数。它使用不同的变换(整数变换)。接下来，用于该变换的系数不一定在逐帧的基础上发生变化-H.264更聪明，因为它将帧分成多个片段。应该可以通过特殊的解码器来获得这些系数，但是我怀疑OpenCV会为用户公开它。
对于JPEG来说，情况要乐观一些。正如我所怀疑的，libjpeg为您公开了DCT系数。我写了一个小应用程序来证明它有效(最后是源代码)。它使用每个块中的DC项生成新图像。因为DC项等于块平均(在适当缩放后)，所以DC图像是输入JPEG图像的降采样版本。
编辑:修复了源代码中的缩放比例
原始图片(512 x 512):
DC图像(64x64):亮度Cr Cb RGB
来源(C++):
#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;
}
关于image-processing - 从编码的图像和视频中提取DCT系数，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/4470107/