JPEG原理分析及JPEG解码器的调试

最新推荐文章于 2022-03-17 22:52:04 发布

weixin_46805592

最新推荐文章于 2022-03-17 22:52:04 发布

阅读量157

点赞数

分类专栏：数据压缩

本文链接：https://blog.csdn.net/weixin_46805592/article/details/117745937

版权

数据压缩专栏收录该内容

10 篇文章 0 订阅

订阅专栏

JPEG原理分析及JPEG解码器的调试

实验目的
实验内容
- 基本思路
- 代码实现
输出结果

实验目的

掌握JPEG编解码系统的基本原理。初步掌握复杂的数据压缩算法实现，并能根据理论分析需要实现所对应数据的输出。

实验内容

基本思路

在这里插入图片描述

SOI & EOI

SOI ,Start of Image，图像开始
标记代码 2字节固定值0xFFD8
EOI，End of Image，图像结束 2字节
标记代码 2字节固定值0xFFD9

在这里插入图片描述

APP0 应用程序保留标记0

标记代码 2字节固定值0xFFE0
包含9个具体字段： ① 数据长度 2字节 ①~⑨9个字段的总长度 ② 标识符 5字节固定值0x4A46494600，即字符串“JFIF0”
③ 版本号 2字节一般是0x0102，表示JFIF的版本号1.2
④ X和Y的密度单位 1字节只有三个值可选 0：无单位；1：点数/英寸；2：点数/厘米
⑤ X方向像素密度 2字节取值范围未知
⑥ Y方向像素密度 2
字节取值范围未知
⑦ 缩略图水平像素数目 1字节取值范围未知
⑧ 缩略图垂直像素数目 1字节取值范围未知
⑨ 缩略图RGB位图长度可能是3的倍数缩略图RGB位图数据

在这里插入图片描述

DQT 定义量化表

标记代码 2字节固定值0xFFDB
包含9个具体字段： ① 数据长度 2字节字段①和多个字段②的总长度 ② 量化表数据长度-2字节
a) 精度及量化表ID 1字节
高4位：精度，只有两个可选值 0：8位；1：16位低4位：量化表ID，取值范围为0～3
b) 表项 (64×(精度+1))字节
例如8位精度的量化表,其表项长度为64×（0+1）=64字节
本标记段中，字段②可以重复出现，表示多个量化表，但最多只能出现4次
在这里插入图片描述
DHT，定义哈夫曼表

标记代码 2字节固定值0xFFC4
包含2个具体字段：
① 数据长度 2字节
② huffman表数据长度-2字节
表ID和表类型 1字节
高4位：类型，只有两个值可选
0：DC直流；1：AC交流低4位：哈夫曼表ID，
注意，DC表和AC表分开编码
不同位数的码字数量 16字节
编码内容 16个不同位数的码字数量之和（字节）本标记段中，字段②可以重复出现（一般4次），也可以只出现1次。

SOS 扫描开始

标记代码 2字节固定值0xFFDA
包含2个具体字段： ①数据长度 2字节 ①~④两个字段的总长度 ②颜色分量数 1字节应该和SOF中的字段⑤的值相同，即： 1：灰度图是；3： YCrCb或YIQ；4：CMYK。
③颜色分量信息 a) 颜色分量ID 1字节 b) 直流/交流系数表号 1字节
高4位：直流分量使用的哈夫曼树编号低4位：交流分量使用的哈夫曼树编号
④ 压缩图像数据 a)谱选择开始 1字节固定值0x00 b)谱选择结束 1字节固定值0x3F c)谱选择 1字节在基本JPEG中总为00

SOF0 帧图像开始

标记代码 2字节固定值0xFFC0
包含9个具体字段：
① 数据长度 2字节 ①~⑥六个字段的总长度
② 精度 1字节每个数据样本的位数通常是8位，一般软件都不支持 12位和16位
③ 图像高度 2字节图像高度（单位：像素）
④ 图像宽度 2字节图像宽度（单位：像素）
⑤ 颜色分量数 1字节只有3个数值可选 1：灰度图；3：YCrCb或YIQ；4：CMYK 而JFIF中使用YCrCb，故这里颜色分量数恒为3
⑥颜色分量信息颜色分量数×3字节（通常为9字节） a)颜色分量ID 1字节
b)水平/垂直采样因子 1字节
高4位：水平采样因子低4位：垂直采样因子 c) 量化表 1字节当前分量使用的量化表的ID

JPEG格式二进制可转换后对应找到相应固定模式和数据

在这里插入图片描述

代码实现

3个结构体

huffman_table.h
component.h
jdec_private.h

// Huffman码表结构体
struct huffman_table
{
  /* Fast look up table, using HUFFMAN_HASH_NBITS bits we can have directly the symbol,
   * if the symbol is <0, then we need to look into the tree table */
   //快速查找到权值对应的码字
  short int lookup[HUFFMAN_HASH_SIZE];
  /* code size: give the number of bits of a symbol is encoded */
  //码长对应的权值
  unsigned char code_size[HUFFMAN_HASH_SIZE];
  /* some place to store value that is not encoded in the lookup table 
   * FIXME: Calculate if 256 value is enough to store all values
   */
  uint16_t slowtable[16-HUFFMAN_HASH_NBITS][256];
};
// 分量结构体：代表当前正在处理的某个分量的8x8块
struct component 
{
  unsigned int Hfactor;//水平采样因子
  unsigned int Vfactor;//垂直采样因子
  float *Q_table;		/* Pointer to the quantisation table to use */
  struct huffman_table *AC_table;//指向该宏块交流系数的Huffman码表
  struct huffman_table *DC_table;//指向该宏块直交流系数的Huffman码表
  short int previous_DC;	/* Previous DC coefficient *///前一个块的DC系数
  short int DCT[64];		/* DCT coef *///该块的DCT系数，其中DCT[0]为该块直流，其他为交流
#if SANITY_CHECK
  unsigned int cid;
#endif
};
// 文件解码信息结构体
struct jdec_private
{
  /* Public variables */
  //分别指向YUV分量结构体的指针数组
  uint8_t *components[COMPONENTS];
  // 图像的宽高
  unsigned int width, height; /* Size of the image */
  unsigned int flags;

  /* Private variables */
  // 文件流的开始和结束
  const unsigned char *stream_begin, *stream_end;
  // 文件流的长度
  unsigned int stream_length;
  // 指向那个当前文件流
  const unsigned char *stream;	/* Pointer to the current stream */
  unsigned int reservoir, nbits_in_reservoir;

主要代码

#include <stdio.h>
#ifndef __JPEGDEC_H__
#define __JPEGDEC_H__
#define TINYJPEG_FLAGS_MJPEG_TABLE	(1<<1)
#ifdef __cplusplus
extern "C" {
#endif
#define  snprintf _snprintf
// 通过定义TRACE的值为0或1来打开和关闭TRACE
#define TRACE 1
#define  TRACEFILE "trace_jpeg.txt"
static const unsigned char zigzag[64];
struct jdec_private;
enum tinyjpeg_fmt {
   TINYJPEG_FMT_GREY = 1,
   TINYJPEG_FMT_BGR24,
   TINYJPEG_FMT_RGB24,
   TINYJPEG_FMT_YUV420P,
};
FILE *p_trace;//add by nxn
static char error_string[256];//add by nxn
struct jdec_private *tinyjpeg_init(void);
void tinyjpeg_free(struct jdec_private *priv);
int tinyjpeg_parse_header(struct jdec_private *priv, const unsigned char *buf, unsigned int size);
int tinyjpeg_decode(struct jdec_private *priv, int pixel_format);
const char *tinyjpeg_get_errorstring(struct jdec_private *priv);
void tinyjpeg_get_size(struct jdec_private *priv, unsigned int *width, unsigned int *height);
int tinyjpeg_get_components(struct jdec_private *priv, unsigned char **components);
int tinyjpeg_set_components(struct jdec_private *priv, unsigned char **components, unsigned int ncomponents);
int tinyjpeg_set_flags(struct jdec_private *priv, int flags);
static void outdcac(struct jdec_private *priv, FILE *DC_image, FILE *AC_image);
static void getdcac(struct jdec_private *priv);
#ifdef __cplusplus
}
#endif
#endif

int main(int argc, char *argv[])
{
// 初始化输出文件格式为YUV420P
  int output_format = TINYJPEG_FMT_YUV420P;
  char *output_filename, *input_filename;
  clock_t start_time, finish_time;
  unsigned int duration;
  int current_argument;
int benchmark_mode = 0;
// 通过在tinyjpeg.h文件中设置TRACE的值为1以及#if TRACE … #endif打开打开TRACE文件，TRACE是用来跟踪和记录解码过程，存放解码过程中得到的数据
#if TRACE
  p_trace=fopen(TRACEFILE,"w");
  if (p_trace==NULL)
  {
	  printf("trace file open error!");
  }
#endif
  if (argc < 3)
    usage();

  current_argument = 1;
  while (1)
   {
     if (strcmp(argv[current_argument], "--benchmark")==0)
       benchmark_mode = 1;
     else
       break;
     current_argument++;
   }

  if (argc < current_argument+2)
    usage();

  input_filename = argv[current_argument];
  if (strcmp(argv[current_argument+1],"yuv420p")==0)
    output_format = TINYJPEG_FMT_YUV420P;
  else if (strcmp(argv[current_argument+1],"rgb24")==0)
    output_format = TINYJPEG_FMT_RGB24;
  else if (strcmp(argv[current_argument+1],"bgr24")==0)
    output_format = TINYJPEG_FMT_BGR24;
  else if (strcmp(argv[current_argument+1],"grey")==0)
    output_format = TINYJPEG_FMT_GREY;
  else
    exitmessage("Bad format: need to be one of yuv420p, rgb24, bgr24, grey\n");
  output_filename = argv[current_argument+2];

  start_time = clock();

  if (benchmark_mode)
    load_multiple_times(input_filename, output_filename, output_format);
  else
    convert_one_image(input_filename, output_filename, output_format);

  finish_time = clock();
  duration = finish_time - start_time;
  snprintf(error_string, sizeof(error_string),"Decoding finished in %u ticks\n", duration);
#if TRACE
  fclose(p_trace);
#endif
  return 0;
}
convert_one_image：加载一幅jpeg图像，解压缩后存出结果
int convert_one_image(const char *infilename, const char *outfilename, int output_format)
{
  // 定义文件指针
  FILE *fp;
  // 保存文件大小
  unsigned int length_of_file;
  // 保存图像宽高
  unsigned int width, height;
  // 用来存储JPEG文件中的数据的缓冲区
  unsigned char *buf;
  struct jdec_private *jdec;
  unsigned char *components[3];
  fp = fopen(infilename, "rb");
  if (fp == NULL)
    exitmessage("Cannot open filename\n");
  // 获取文件大小
  length_of_file = filesize(fp);
  buf = (unsigned char *)malloc(length_of_file + 4);
  if (buf == NULL)
    exitmessage("Not enough memory for loading file\n");
  // 将文件中的数据读入缓存
  fread(buf, length_of_file, 1, fp);
  fclose(fp);
  jdec = tinyjpeg_init();
  if (jdec == NULL)
    exitmessage("Not enough memory to alloc the structure need for decompressing\n");
  // 解析 Segment Marker 
  if (tinyjpeg_parse_header(jdec, buf, length_of_file)<0)
    exitmessage(tinyjpeg_get_errorstring(jdec));

  /* Get the size of the image */
  tinyjpeg_get_size(jdec, &width, &height);

  snprintf(error_string, sizeof(error_string),"Decoding JPEG image...\n");
  // 文件解码
  if (tinyjpeg_decode(jdec, output_format) < 0)
    exitmessage(tinyjpeg_get_errorstring(jdec));
  /* 
   * Get address for each plane (not only max 3 planes is supported), and
   * depending of the output mode, only some components will be filled 
   * RGB: 1 plane, YUV420P: 3 planes, GREY: 1 plane
   */
  tinyjpeg_get_components(jdec, components);
 
  /* Save it */
  // 按要求输出文件
  switch (output_format)
   {
    case TINYJPEG_FMT_RGB24:
    case TINYJPEG_FMT_BGR24:
      write_tga(outfilename, output_format, width, height, components);
      break;
    case TINYJPEG_FMT_YUV420P:
      write_yuv(outfilename, width, height, components);
      break;
    case TINYJPEG_FMT_GREY:
      write_pgm(outfilename, width, height, components);
      break;
   }
  tinyjpeg_free(jdec);
  /* else called just free(jdec); */
  free(buf);
  return 0;
}
static void write_yuv(const char *filename, int width, int height, unsigned char **components)
{
  FILE *F;
char temp[1024];
  snprintf(temp, 1024, "%s.yuv", filename);
  F = fopen(temp, "wb");
  fwrite(components[0], width, height, F);
  fwrite(components[1], width*height / 4, 1, F);
  fwrite(components[2], width*height / 4, 1, F);
  fclose(F);
}

tinyjpeg.c
tinyjpeg_parse_header函数：解析 Segment Marker
int tinyjpeg_parse_header(struct jdec_private *priv, const unsigned char *buf, unsigned int size)
{
  int ret;
  if ((buf[0] != 0xFF) || (buf[1] != SOI))
    snprintf(error_string, sizeof(error_string),"Not a JPG file ?\n");
  // 如果是0xFFD8，则将文件流的开始向后移两个字节
  priv->stream_begin = buf+2;
  // 将文件的长度也减小两个字节
  priv->stream_length = size-2;
  // 定位到文件的最后
  priv->stream_end = priv->stream_begin + priv->stream_length;
  // 调用parse_JFIF函数解析文件头
  ret = parse_JFIF(priv, priv->stream_begin);

  return ret;
}
static int parse_JFIF(struct jdec_private *priv, const unsigned char *stream)
{
  int chuck_len;
  int marker;
  int sos_marker_found = 0;
  int dht_marker_found = 0;
  const unsigned char *next_chunck;

  /* Parse marker */
  // 循环一直读到扫描开始，即编码数据块
  while (!sos_marker_found)
   {
     if (*stream++ != 0xff)
       goto bogus_jpeg_format;
     /* Skip any padding ff byte (this is normal) */
     while (*stream == 0xff)
       stream++;

     marker = *stream++;
     chuck_len = be16_to_cpu(stream);
     next_chunck = stream + chuck_len;
     switch (marker)
      {
       case SOF:
	 if (parse_SOF(priv, stream) < 0)
	   return -1;
	 break;
       case DQT:
	 if (parse_DQT(priv, stream) < 0)
	   return -1;
	 break;
       case SOS:
	 if (parse_SOS(priv, stream) < 0)
	   return -1;
	 sos_marker_found = 1;
	 break;
       case DHT:
	 if (parse_DHT(priv, stream) < 0)
	   return -1;
	 dht_marker_found = 1;
	 break;
       case DRI:
	 if (parse_DRI(priv, stream) < 0)
	   return -1;
	 break;
       default:
#if TRACE
	fprintf(p_trace,"> Unknown marker %2.2x\n", marker);
	fflush(p_trace);
#endif
	 break;
      }
     stream = next_chunck;// 跳到下一个数据块，再判断
   }

  if (!dht_marker_found) {
#if TRACE
	  fprintf(p_trace,"No Huffman table loaded, using the default one\n");
	  fflush(p_trace);
#endif
    build_default_huffman_tables(priv);
  }

#ifdef SANITY_CHECK
  if (   (priv->component_infos[cY].Hfactor < priv->component_infos[cCb].Hfactor)
      || (priv->component_infos[cY].Hfactor < priv->component_infos[cCr].Hfactor))
    snprintf(error_string, sizeof(error_string),"Horizontal sampling factor for Y should be greater than horitontal sampling factor for Cb or Cr\n");
  if (   (priv->component_infos[cY].Vfactor < priv->component_infos[cCb].Vfactor)
      || (priv->component_infos[cY].Vfactor < priv->component_infos[cCr].Vfactor))
    snprintf(error_string, sizeof(error_string),"Vertical sampling factor for Y should be greater than vertical sampling factor for Cb or Cr\n");
  if (   (priv->component_infos[cCb].Hfactor!=1) 
      || (priv->component_infos[cCr].Hfactor!=1)
      || (priv->component_infos[cCb].Vfactor!=1)
      || (priv->component_infos[cCr].Vfactor!=1))
    snprintf(error_string, sizeof(error_string),"Sampling other than 1x1 for Cr and Cb is not supported");
#endif

  return 0;
bogus_jpeg_format:
#if TRACE
  fprintf(p_trace,"Bogus jpeg format\n");
  fflush(p_trace);
#endif
  return -1;
}
parse_DQT函数：解析DQT，得到量化表长度（可能包含多张量化表）、量化表的精度，得到及检查量化表的序号（只能是 0-3），得到量化表内容（64 个数据）
任务三：以txt文件输出所有的量化矩阵
// 解析DQT
static int parse_DQT(struct jdec_private *priv, const unsigned char *stream)
{
  int qi;
  //int count = 0;
  // 定义指向量化表的指针
  float *table;
  // 指向量化表结束的位置
  const unsigned char *dqt_block_end;
#if TRACE
  fprintf(p_trace,"> DQT marker\n");
  fflush(p_trace);
#endif
  // 得到量化表长度（可能包含多张量化表）
  dqt_block_end = stream + be16_to_cpu(stream);
  stream += 2;	/* Skip length 跳过两个字节的存储长度*/ 
   // 检查是否还有表 
  while (stream < dqt_block_end)
   {
     qi = *stream++;
#if SANITY_CHECK
     if (qi>>4)
       snprintf(error_string, sizeof(error_string),"16 bits quantization table is not supported\n");

	 if (qi>4)
       snprintf(error_string, sizeof(error_string),"No more 4 quantization table is supported (got %d)\n", qi);
#endif
	 
     table = priv->Q_tables[qi];
	 // 得到量化表内容
	 // 数据：64 字节的量化系数，（一个字节对应一个量化系数，对于 8*8 的宏块来说，共 8*8=64 个量化系数） 
     build_quantization_table(table, stream);
	 //count++;
	 /* 添加：以之字形扫描顺序输出量化矩阵*/
	 /* a：以“追加”方式打开文件
	    如果文件不存在，那么创建一个新文件
		如果文件存在，那么将写入的数据追加到文件的末尾（文件原有的内容保留）*/
	 FILE *fp = fopen("table.txt", "a");
	 if (fp == NULL) 
	 {
		 printf("Fail to open file!\n");
		 exit(0);  //退出程序（结束程序）
	 }

	 fprintf(fp, "量化表\n");
	 for (int i = 0; i < 64; i++)
	 {
		 if (i != 0 && i % 8 == 0)
			 fprintf(fp, "\n");
		 fprintf(fp, "%f\t   ", table[i]);
		 
	 }
	 printf(fp, "\n");
     stream += 64;
   }
#if TRACE
  fprintf(p_trace,"< DQT marker\n");
  fflush(p_trace);
#endif
  return 0;
}
static void build_quantization_table(float *qtable, const unsigned char *ref_table)
{

  int i, j;
  static const double aanscalefactor[8] = {
     1.0, 1.387039845, 1.306562965, 1.175875602,
     1.0, 0.785694958, 0.541196100, 0.275899379
  };
  const unsigned char *zz = zigzag;
  // 以 zig-zag 序存储 
  for (i=0; i<8; i++) {
     for (j=0; j<8; j++) {
       *qtable++ = ref_table[*zz++] * aanscalefactor[i] * aanscalefactor[j];
     }
   }

}
// 之字形扫描顺序
static const unsigned char zigzag[64] = 
{
   0,  1,  5,  6, 14, 15, 27, 28,
   2,  4,  7, 13, 16, 26, 29, 42,
   3,  8, 12, 17, 25, 30, 41, 43,
   9, 11, 18, 24, 31, 40, 44, 53,
  10, 19, 23, 32, 39, 45, 52, 54,
  20, 22, 33, 38, 46, 51, 55, 60,
  21, 34, 37, 47, 50, 56, 59, 61,
  35, 36, 48, 49, 57, 58, 62, 63
};
parse_SOF函数：解析SOF，得到每个 sample 的比特数、长宽、颜色分量数, 每个颜色分量的 ID、水平采样因子、垂直采样因子、使用的量化表序号（与 DQT 中序号对应） 
static int parse_SOF(struct jdec_private *priv, const unsigned char *stream)
{
  int i, width, height, nr_components, cid, sampling_factor;
  int Q_table;
  struct component *c;
#if TRACE
  fprintf(p_trace,"> SOF marker\n");
  fflush(p_trace);
#endif
  print_SOF(stream);
  // 得到当前图片的高度 
  height = be16_to_cpu(stream+3);
  // 得到当前图片的宽度 
  width  = be16_to_cpu(stream+5);
  // 得到颜色分量数（JFIF中使用YCrCb，故这里颜色分量数恒为3） 
  nr_components = stream[7];
#if SANITY_CHECK
  if (stream[2] != 8)
    snprintf(error_string, sizeof(error_string),"Precision other than 8 is not supported\n");
  if (width>JPEG_MAX_WIDTH || height>JPEG_MAX_HEIGHT)
    snprintf(error_string, sizeof(error_string),"Width and Height (%dx%d) seems suspicious\n", width, height);
  if (nr_components != 3)
    snprintf(error_string, sizeof(error_string),"We only support YUV images\n");
  if (height%16)
    snprintf(error_string, sizeof(error_string),"Height need to be a multiple of 16 (current height is %d)\n", height);
  if (width%16)
    snprintf(error_string, sizeof(error_string),"Width need to be a multiple of 16 (current Width is %d)\n", width);
#endif
  stream += 8;
  for (i=0; i<nr_components; i++) {
	 // 该颜色分量的ID
     cid = *stream++;
	 // 该分量的水平、垂直采样因子 
     sampling_factor = *stream++;
	 // 该分量使用的量化表序号 
     Q_table = *stream++;
	 // 指向该分量的结构体指针
     c = &priv->component_infos[i];
#if SANITY_CHECK
     c->cid = cid;
     if (Q_table >= COMPONENTS)
       snprintf(error_string, sizeof(error_string),"Bad Quantization table index (got %d, max allowed %d)\n", Q_table, COMPONENTS-1);
#endif
     c->Vfactor = sampling_factor&0xf; // 垂直采样因子（低四位）
     c->Hfactor = sampling_factor>>4; // 水平采样因子（高四位） 
     c->Q_table = priv->Q_tables[Q_table];
#if TRACE
     fprintf(p_trace,"Component:%d  factor:%dx%d  Quantization table:%d\n",
           cid, c->Hfactor, c->Hfactor, Q_table );
	 fflush(p_trace);
#endif

  }
  priv->width = width;
  priv->height = height;
#if TRACE
  fprintf(p_trace,"< SOF marker\n");
  fflush(p_trace);
#endif
  return 0;
}
parse_DHT函数：解析DHT，得到 Huffman 表的类型（AC、DC）、序号, 依据数据重建 Huffman 表
任务四：以txt文件输出所有的HUFFMAN码表
static int parse_DHT(struct jdec_private *priv, const unsigned char *stream)
{
  unsigned int count, i;
  // 定义存储码长从1至16的码字个数的数组
  unsigned char huff_bits[17];
  int length, index;
  // 表长(减去标记代码所占字节数后的表长，可能包含多张表) 
  length = be16_to_cpu(stream) - 2;
  stream += 2;	/* Skip length */
#if TRACE
  fprintf(p_trace,"> DHT marker (length=%d)\n", length);
  fflush(p_trace);
#endif
  // 是否还有表 
  while (length>0) {
     index = *stream++;
     /* We need to calculate the number of bytes 'vals' will takes */
     huff_bits[0] = 0;
     count = 0;
     for (i=1; i<17; i++) 
	 {
		// 各码长的码字个数分别赋值
    	     huff_bits[i] = *stream++;
		// 总码字数
		// count个字节对应的就是每个字符对应的权值
		// 这些权值的含义即为DC系数经DPCM编码后幅度值的位长
	    count += huff_bits[i];
     }
#if SANITY_CHECK
     if (count >= HUFFMAN_BITS_SIZE)
       snprintf(error_string, sizeof(error_string),"No more than %d bytes is allowed to describe a huffman table", HUFFMAN_BITS_SIZE);
     if ( (index &0xf) >= HUFFMAN_TABLES)
       snprintf(error_string, sizeof(error_string),"No more than %d Huffman tables is supported (got %d)\n", HUFFMAN_TABLES, index&0xf);
#if TRACE
     fprintf(p_trace,"Huffman table %s[%d] length=%d\n", (index&0xf0)?"AC":"DC", index&0xf, count);
	 fflush(p_trace);
#endif
#endif
	 /* 添加：以txt文件输出所有的HUFFMAN码表 */
	 FILE *fp = fopen("huffman.txt", "a");
	 if (fp == NULL)
	 {
		 printf("Fail to open file!\n");
		 exit(0);  //退出程序（结束程序）
	 }
	 if (index & 0xf0)
	 // (index&0xf)获得Huffman表序号 
	 {
		 fprintf(fp, "huffman_table	AC%d号表\n", (index & 0xf));
		 build_huffman_table(huff_bits, stream, &priv->HTAC[index & 0xf]);
	 }
	 // 高四位为0是DC表 
	 else
	 {
		 fprintf(fp, "huffman_table	DC%d号表\n", (index & 0xf));
		 build_huffman_table(huff_bits, stream, &priv->HTDC[index & 0xf]);
	 }
     length -= 1;
     length -= 16;
     length -= count;
     stream += count;
  }
#if TRACE
  fprintf(p_trace,"< DHT marker\n");
  fflush(p_trace);
#endif
  return 0;
}
static void build_huffman_table(const unsigned char *bits, const unsigned char *vals, struct huffman_table *table)
{
  unsigned int i, j, code, code_size, val, nbits;
  unsigned char huffsize[HUFFMAN_BITS_SIZE+1], *hz;
  unsigned int huffcode[HUFFMAN_BITS_SIZE+1], *hc;
  int next_free_entry;

  /*
   * Build a temp array 
   *   huffsize[X] => numbers of bits to write vals[X]
   */
  hz = huffsize;
  // 码长为1-16
  for (i=1; i<=16; i++)
   {
	 // 码长为1-16的码字个数
     for (j=1; j<=bits[i]; j++)
		// 每个码字的长度
       *hz++ = i;
   }
  *hz = 0;

  memset(table->lookup, 0xff, sizeof(table->lookup));
  for (i=0; i<(16-HUFFMAN_HASH_NBITS); i++)
    table->slowtable[i][0] = 0;
  // 第一个码字必定为0
  code = 0;
  hc = huffcode;
  hz = huffsize;
  nbits = *hz;
  while (*hz)
   {
     while (*hz == nbits)
     {
		*hc++ = code++;
		hz++;
     }
     code <<= 1;
     nbits++;
   }

  /*
   * Build the lookup table, and the slowtable if needed.
   */
   /* 添加：以txt文件输出所有的HUFFMAN码表 */
  FILE *fp = fopen("huffman.txt", "a");
  if (fp == NULL)
  {
	  printf("Fail to open file!\n");
	  exit(0);  //退出程序（结束程序）
  }
  next_free_entry = -1;
  for (i=0; huffsize[i]; i++)
   {
	 // 每个码字的权值，即解码时需要再读入的bit位数
     val = vals[i];
	 // 码字
     code = huffcode[i];
	 // 码长
	 code_size = huffsize[i];
	#if TRACE
     fprintf(p_trace,"val=%2.2x code=%8.8x codesize=%2.2d\n", val, code, code_size);
	 fflush(p_trace);

	 fprintf(fp, "val=%2.2x code=%8.8x codesize=%2.2d\n", val, code, code_size);
	 fflush(fp);
    #endif
     table->code_size[val] = code_size;
     if (code_size <= HUFFMAN_HASH_NBITS)
      {
	/*
	 * Good: val can be put in the lookup table, so fill all value of this
	 * column with value val 
	 */
	int repeat = 1UL<<(HUFFMAN_HASH_NBITS - code_size);
	code <<= HUFFMAN_HASH_NBITS - code_size;
	while ( repeat-- )
	  table->lookup[code++] = val;
      }
     else
      {
	/* Perhaps sorting the array will be an optimization */
	uint16_t *slowtable = table->slowtable[code_size-HUFFMAN_HASH_NBITS-1];
	while(slowtable[0])
	  slowtable+=2;
	slowtable[0] = code;
	slowtable[1] = val;
	slowtable[2] = 0;
	/* TODO: NEED TO CHECK FOR AN OVERFLOW OF THE TABLE */
      }
   } 
}
parse_SOS函数：解析SOS，得到解析每个颜色分量的 DC、AC 值所使用的 Huffman 表序号（与 DHT 中序号对应）
static int parse_SOS(struct jdec_private *priv, const unsigned char *stream)
{
  unsigned int i, cid, table;
  // 得到颜色分量数 
  unsigned int nr_components = stream[2];
#if TRACE
  fprintf(p_trace,"> SOS marker\n");
  fflush(p_trace);
#endif

#if SANITY_CHECK
  if (nr_components != 3)
    snprintf(error_string, sizeof(error_string),"We only support YCbCr image\n");
#endif

  stream += 3;
  // 对所有分量
  for (i=0;i<nr_components;i++) {
	 // 得到ID
     cid = *stream++;
     table = *stream++;
#if SANITY_CHECK
     if ((table&0xf)>=4)
	snprintf(error_string, sizeof(error_string),"We do not support more than 2 AC Huffman table\n");
     if ((table>>4)>=4)
	snprintf(error_string, sizeof(error_string),"We do not support more than 2 DC Huffman table\n");
     if (cid != priv->component_infos[i].cid)
        snprintf(error_string, sizeof(error_string),"SOS cid order (%d:%d) isn't compatible with the SOF marker (%d:%d)\n",
	      i, cid, i, priv->component_infos[i].cid);
#if TRACE
     fprintf(p_trace,"ComponentId:%d  tableAC:%d tableDC:%d\n", cid, table&0xf, table>>4);
	 fflush(p_trace);
#endif
#endif
	 // Huffman表序号，高四位：DC 低四位：AC 
     priv->component_infos[i].AC_table = &priv->HTAC[table&0xf];
     priv->component_infos[i].DC_table = &priv->HTDC[table>>4];
  }
  // 指向熵编码数据流的开始
  priv->stream = stream+3;
#if TRACE
  fprintf(p_trace,"< SOS marker\n");
  fflush(p_trace);
#endif
  return 0;
}
Tinyjpeg_decode函数：依据每个分量的水平、垂直采样因子计算 MCU 的大小，并得到每个 MCU 中 8*8 宏块的个数
任务五：输出DC图像和某一个AC值图像并分别统计其概率分布（使用第三个实验中的Huffman编码器）
// 定义两个文件指针分别打开两个yuv文件：DC图像和AC图像
// add
  FILE *DC_image = fopen("DCimage.yuv", "wb");
  FILE *AC_image = fopen("ACimage.yuv", "wb");
  // 为创建的指针分配空间
  // 每个8x8的块只有一个直流分量
  priv->dc = (int *)malloc(sizeof(int) * (priv->width * priv->height) / 64);
  // 因为只输出某一AC值图像，所以AC和DC所占空间相同
  priv->ac = (int *)malloc(sizeof(int) * (priv->width * priv->height) / 64);
  
  //add
// 初始化为 4:4:4 时的情况，即MCU的宽和高均为8x8
  xstride_by_mcu = ystride_by_mcu = 8;
  // 如果Y分量的垂直和水平采样因子相等，则每个MCU就包括1个Y分量
  if ((priv->component_infos[cY].Hfactor | priv->component_infos[cY].Vfactor) == 1) {
	  // 4:4:4   
	  decode_MCU = decode_mcu_table[0];
      convert_to_pixfmt = colorspace_array_conv[0];
#if TRACE
     fprintf(p_trace,"Use decode 1x1 sampling\n");
	 fflush(p_trace);
#endif
  } else if (priv->component_infos[cY].Hfactor == 1) {

     decode_MCU = decode_mcu_table[1];
     convert_to_pixfmt = colorspace_array_conv[1];
	 // 一个 MCU 的高为 16 
     ystride_by_mcu = 16;
#if TRACE
     fprintf(p_trace,"Use decode 1x2 sampling (not supported)\n");
	 fflush(p_trace);
#endif
  } else if (priv->component_infos[cY].Vfactor == 2) {
	 // 如果水平采样因子为2，垂直为2，则每个MCU包含4个Y分量
     decode_MCU = decode_mcu_table[3];
     convert_to_pixfmt = colorspace_array_conv[3];
	 // 一个 MCU 的宽为 16 
     xstride_by_mcu = 16;
	 // 一个 MCU 的高为 16 
     ystride_by_mcu = 16;
#if TRACE 
	 fprintf(p_trace,"Use decode 2x2 sampling\n");
	 fflush(p_trace);
#endif
  } else {
	 // 如果水平采样因子为2，垂直为1，则每个MCU包含2个Y分量
     decode_MCU = decode_mcu_table[2];
     convert_to_pixfmt = colorspace_array_conv[2];
	 // 一个 MCU 的宽为 16 
     xstride_by_mcu = 16;
#if TRACE
     fprintf(p_trace,"Use decode 2x1 sampling\n");
	 fflush(p_trace);
#endif
  }

  resync(priv);

  /* Don't forget to that block can be either 8 or 16 lines */
  bytes_per_blocklines[0] *= ystride_by_mcu;
  bytes_per_blocklines[1] *= ystride_by_mcu;
  bytes_per_blocklines[2] *= ystride_by_mcu;

  bytes_per_mcu[0] *= xstride_by_mcu/8;
  bytes_per_mcu[1] *= xstride_by_mcu/8;
  bytes_per_mcu[2] *= xstride_by_mcu/8;
  
   /* Just the decode the image by macroblock (size is 8x8, 8x16, or 16x16) */
   // 行循环 
  for (y=0; y < priv->height/ystride_by_mcu; y++)
   {
     //trace("Decoding row %d\n", y);
     priv->plane[0] = priv->components[0] + (y * bytes_per_blocklines[0]);
     priv->plane[1] = priv->components[1] + (y * bytes_per_blocklines[1]);
     priv->plane[2] = priv->components[2] + (y * bytes_per_blocklines[2]);
	 // 列循环
	 for (x=0; x < priv->width; x+=xstride_by_mcu)
     {
// 解码（Huffman 解码 + IDCT） 
// 每解码一个8x8的宏块，调用getdcac函数将DC（DCT[0]）和AC（这里是DCT[1]）写入内存
	getdcac(priv);
	decode_MCU(priv);
	convert_to_pixfmt(priv);
	priv->plane[0] += bytes_per_mcu[0];
	priv->plane[1] += bytes_per_mcu[1];
	priv->plane[2] += bytes_per_mcu[2];
	if (priv->restarts_to_go>0)
	 {
	   priv->restarts_to_go--;
	   if (priv->restarts_to_go == 0)
	    {
	      priv->stream -= (priv->nbits_in_reservoir/8);
		  // 清空 preDC（所有颜色分量） 
	      resync(priv);
		  // 查找 RST 标记 
	      if (find_next_rst_marker(priv) < 0)
		return -1;
	    }
	 }
      }
   }
  
#if TRACE
  fprintf(p_trace,"Input file size: %d\n", priv->stream_length+2);
  fprintf(p_trace,"Input bytes actually read: %d\n", priv->stream - priv->stream_begin + 2);
  fflush(p_trace);
#endif
   //反DCT之后的DC取值最大可达到8*256,
   
 outdcac(priv, DC_image, AC_image);
  
  return 0;
}
static void getdcac(struct jdec_private *priv)
{
	static int i = 0;
	if (i < priv->width * priv->height / 64)
	{
		priv->dc[i] = priv->component_infos[0].DCT[0];
		priv->ac[i] = priv->component_infos[0].DCT[1];
	}
	i++;
}
static void outdcac(struct jdec_private *priv,FILE *DC_image, FILE *AC_image)
{
	priv->outdc = (unsigned char*)malloc(sizeof(unsigned char) * (priv->width * priv->height) / 64);
	priv->outac = (unsigned char*)malloc(sizeof(unsigned char) * (priv->width * priv->height) / 64);
	// 添加
	int dcmax = priv->dc[0];
	int acmax = priv->ac[0];
	int dcmin = priv->dc[0];
	int acmin = priv->ac[0];

	for (int j = 0; j < priv->width * priv->height / 64; j++)
	{
		if (priv->dc[j] > dcmax)
			dcmax = priv->dc[j];
		if (priv->dc[j] < dcmin)
			dcmin = priv->dc[j];
		if (priv->ac[j] > acmax)
			acmax = priv->ac[j];
		if (priv->ac[j] < acmin)
			acmin = priv->ac[j];
	}
     }
	// 归一化处理
	for (int k = 0; k < priv->width * priv->height / 64; k++)
	{
		priv->outdc[k] = (unsigned char)(255 * (priv->dc[k] - dcmin) / (dcmax - dcmin));
		priv->outac[k] = (unsigned char)(255 * (priv->ac[k] - acmin) / (acmax - acmin));
	}

	fwrite(priv->outdc, 1, priv->width * priv->height / 64, DC_image);
	fwrite(priv->outac, 1, priv->width * priv->height / 64, AC_image);
}
//对每个 MCU 解码（依照各分量水平、垂直采样因子对 MCU 中每个分量宏块解码） 
//1. 对每个宏块进行 Huffman 解码，得到 DCT 系数 
//2. 对每个宏块的 DCT 系数进行 IDCT，得到 Y、Cb、Cr 
//3. 遇到 Segment Marker RST 时，清空之前的 DC DCT 系数
// 4:4:4
static void decode_MCU_1x1_3planes(struct jdec_private *priv)
{
  // Y
  // 以 8x8 宏块为单位进行 Huffman 解码 
  process_Huffman_data_unit(priv, cY);
  // 对得到的 DCT 系数进行 IDCT   
  IDCT(&priv->component_infos[cY], priv->Y, 8);
  
  // Cb
  process_Huffman_data_unit(priv, cCb);
  IDCT(&priv->component_infos[cCb], priv->Cb, 8);

  // Cr
  process_Huffman_data_unit(priv, cCr);
  IDCT(&priv->component_infos[cCr], priv->Cr, 8);
}

/*
 * Decode a 1x1 directly in 1 color
 */
static void decode_MCU_1x1_1plane(struct jdec_private *priv)
{
  // Y
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y, 8);
  
  // Cb
  process_Huffman_data_unit(priv, cCb);
  IDCT(&priv->component_infos[cCb], priv->Cb, 8);

  // Cr
  process_Huffman_data_unit(priv, cCr);
  IDCT(&priv->component_infos[cCr], priv->Cr, 8);
}


static void decode_MCU_2x1_3planes(struct jdec_private *priv)
{
  // Y
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y, 16);
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y+8, 16);

  // Cb
  process_Huffman_data_unit(priv, cCb);
  IDCT(&priv->component_infos[cCb], priv->Cb, 8);

  // Cr
  process_Huffman_data_unit(priv, cCr);
  IDCT(&priv->component_infos[cCr], priv->Cr, 8);
}


static void decode_MCU_2x1_1plane(struct jdec_private *priv)
{
  // Y
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y, 16);
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y+8, 16);

  // Cb
  process_Huffman_data_unit(priv, cCb);

  // Cr
  process_Huffman_data_unit(priv, cCr);
}


static void decode_MCU_2x2_3planes(struct jdec_private *priv)
{
  // Y
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y, 16);
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y+8, 16);
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y+64*2, 16);
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y+64*2+8, 16);

  // Cb
  process_Huffman_data_unit(priv, cCb);
  IDCT(&priv->component_infos[cCb], priv->Cb, 8);

  // Cr
  process_Huffman_data_unit(priv, cCr);
  IDCT(&priv->component_infos[cCr], priv->Cr, 8);
}


static void decode_MCU_2x2_1plane(struct jdec_private *priv)
{
  // Y
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y, 16);
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y+8, 16);
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y+64*2, 16);
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y+64*2+8, 16);

  // Cb
  process_Huffman_data_unit(priv, cCb);

  // Cr
  process_Huffman_data_unit(priv, cCr);
}


static void decode_MCU_1x2_3planes(struct jdec_private *priv)
{
  // Y
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y, 8);
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y+64, 8);

  // Cb
  process_Huffman_data_unit(priv, cCb);
  IDCT(&priv->component_infos[cCb], priv->Cb, 8);

  // Cr
  process_Huffman_data_unit(priv, cCr);
  IDCT(&priv->component_infos[cCr], priv->Cr, 8);
}


static void decode_MCU_1x2_1plane(struct jdec_private *priv)
{
  // Y
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y, 8);
  process_Huffman_data_unit(priv, cY);
  IDCT(&priv->component_infos[cY], priv->Y+64, 8);

  // Cb
  process_Huffman_data_unit(priv, cCb);

  // Cr
  process_Huffman_data_unit(priv, cCr);
}

//process_Huffman_data_unit函数：以 8x8 宏块为单位进行 Huffman 解码
static void process_Huffman_data_unit(struct jdec_private *priv, int component)
{
  unsigned char j;
  unsigned int huff_code;
  unsigned char size_val, count_0;
  struct component *c = &priv->component_infos[component];
  short int DCT[64];
  memset(DCT, 0, sizeof(DCT));
  huff_code = get_next_huffman_code(priv, c->DC_table);
  //trace("+ %x\n", huff_code);
  if (huff_code) {
	 // 查表的 DC DCT 系数（残值）
     get_nbits(priv->reservoir, priv->nbits_in_reservoir, priv->stream, huff_code, DCT[0]);
	 // DC系数采用差分编码，恢复原值 
	 DCT[0] += c->previous_DC;
     c->previous_DC = DCT[0];
  } else {
     DCT[0] = c->previous_DC;
  }
 
  /* AC coefficient decoding */
  j = 1;
  while (j<64)
   {
     huff_code = get_next_huffman_code(priv, c->AC_table);
     //trace("- %x\n", huff_code);
	 // Amplitude 幅度 
     size_val = huff_code & 0xF;
     count_0 = huff_code >> 4; 
     if (size_val == 0)
      { /* 零游程 */ 
	if (count_0 == 0)
	  break;	
	else if (count_0 == 0xF)
	  j += 16;	
      }
     else
      {
	j += count_0;	
	if (__unlikely(j >= 64)) 
	 {
	   snprintf(error_string, sizeof(error_string), "Bad huffman data (buffer overflow)");
	   break;
	 }
	get_nbits(priv->reservoir, priv->nbits_in_reservoir, priv->stream, size_val, DCT[j]);
	j++;
      }
   }
  for (j = 0; j < 64; j++)
    c->DCT[j] = DCT[zigzag[j]];
}

输出结果

test.jpg文件

在这里插入图片描述

输出AC、DC图像

在这里插入图片描述
输出矩阵形式：

在这里插入图片描述
AC、DC转化txt数据后概率分布图

在这里插入图片描述

weixin_46805592

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
JPEG原理分析及JPEG解码器的调试

JPEG原理分析及JPEG解码器的调试实验目的实验内容基本思路代码实现输出结果实验目的掌握JPEG编解码系统的基本原理。初步掌握复杂的数据压缩算法实现，并能根据理论分析需要实现所对应数据的输出。实验内容基本思路SOI & EOISOI ,Start of Image，图像开始标记代码 2字节固定值0xFFD8EOI，End of Image，图像结束 2字节标记代码 2字节固定值0xFFD9APP0 应用程序保留标记0标记代码 2字节固定值0xFFE0
复制链接

扫一扫