PEG原理分析及JPEG解码器的调试
一、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。
二、实验内容
1.JPEG编解码原理
JPEG编码的过程如上图所示。解码是编码的逆过程。
- imput image:输入图像。
- level offset:零电平偏置。
- 8x8DCT:8x8DCT变换。
- uniform scalar quantization:量化。
- differential coding:差分编码。
- VLC:熵编码。
- zig-zag scan:之字形扫描
- run-level coding:游程编码。
- AC/DC huffman table:AC/DC霍夫曼码表。
- JPEG文件格式
JPEG文件格式
JPEG 在文件中以 Segment 的形式组织,它具有以下特点:
均以 0xFF 开始,后跟 1 byte 的 Marker 和 2 byte 的 Segment Length(包含表示 Length本身所占用的 2 byte,不含“0xFF” + “Marker” 所占用的 2 byte);采用 Motorola 序(相对于 Intel 序),即保存时高位在前,低位在后;Data部分中,0xFF 后若为 0x00,则跳过此字节不予处理;
三、实验步骤
1.逐步调试JPEG解码器程序。将输入的JPG文件进行解码,将输出文件保存为可供YUVViewer观看的YUV文件。
2. 程序调试过程中,应做到:
理解程序设计的整体框架
理解三个结构体的设计目的
• struct huffman_table
• struct component
• struct jdec_private
理解在视音频编解码调试中TRACE的目的和含义
• 会打开和关闭TRACE
• 会根据自己的要求修改TRACE
3.以txt文件输出所有的量化矩阵和所有的HUFFMAN码表。
4. 输出DC图像并统计其概率分布。
5. 输出某一个AC值图像并统计其概率分布。
四、实验结果
代码:
int main(int argc, char *argv[])//命令行参数
{
int output_format = TINYJPEG_FMT_YUV420P;//输出格式为420
char *output_filename, *input_filename;
clock_t start_time, finish_time;
unsigned int duration;
int current_argument;
int benchmark_mode = 0;
#if TRACE
p_trace=fopen(TRACEFILE,"w");
if (p_trace==NULL)
{
printf("trace file open error!");
}
#endif
if (argc < 3)//如果输入的参数小于3,那么输出一些提示命令提示如何输入命令行参数
usage();
current_argument = 1;//目前进行到的argument
while (1)
{
if (strcmp(argv[current_argument], "--benchmark")==0)//命令行参数的第一个输入项是否为“--benchmark”,如果是,令benchmark_mode=1,不是则current_argument加1。(解码模式的选择)
benchmark_mode = 1;
else
break;
current_argument++;
}
if (argc < current_argument+2)//如果调试界面的长度依然不符合标准,那么输出一些提示命令提示如何输入命令行参数
usage();
input_filename = argv[current_argument];//第一个命令行参数为输入文件的名字
if (strcmp(argv[current_argument+1],"yuv420p")==0)//第二个为输出模式的选择
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");//提示format错误
output_filename = argv[current_argument+2];//第三个参数为输出文件的名字
start_time = clock();
if (benchmark_mode)//判断benchmark_mode是否为1,选择解码模式
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);//将duration的值输入到error_string的缓冲区中
#if TRACE
fclose(p_trace);
#endif
return 0;
}
int convert_one_image(const char *infilename, const char *outfilename, int output_format)
{
FILE *fp;
unsigned int length_of_file;//文件大小
unsigned int width, height;//宽 高
unsigned char *buf;//读入数据的指针
struct jdec_private *jdec;//jdec_private类型的结构体指针
unsigned char *components[3];//指针数组
/* 将jpeg文件数据读入缓冲区 */
fp = fopen(infilename, "rb");
if (fp == NULL)
exitmessage("Cannot open filename\n");
length_of_file = filesize(fp);
buf = (unsigned char *)malloc(length_of_file + 4);
if (buf == NULL)
exitmessage("Not enough memory for loading file\n");
fread(buf, length_of_file, 1, fp);
fclose(fp);
/* Decompress it */
jdec = tinyjpeg_init();//初始化
if (jdec == NULL)
exitmessage("Not enough memory to alloc the structure need for decompressing\n");
/* 解析JPEG文件头 */
if (tinyjpeg_parse_header(jdec, buf, length_of_file)<0)
exitmessage(tinyjpeg_get_errorstring(jdec));
/* 得到图像宽高 */
tinyjpeg_get_size(jdec, &width, &height);
snprintf(error_string, sizeof(error_string),"Decoding JPEG image...\n");
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);
/* 按照指定的输出格式保存输出文件 */
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;
}
/* Only called this if the buffers were allocated by tinyjpeg_decode() */
tinyjpeg_free(jdec);
/* else called just free(jdec); */
free(buf);
return 0;
}
int tinyjpeg_parse_header(struct jdec_private *priv, const unsigned char *buf, unsigned int size)
{
int ret;
/* Identify the file */
if ((buf[0] != 0xFF) || (buf[1] != SOI)) // JPEG文件必须以SOI marker为起始,否则不是合法的JPEG文件
snprintf(error_string, sizeof(error_string),"Not a JPG file ?\n");
priv->stream_begin = buf+2; // 跳过标识符
priv->stream_length = size-2;
priv->stream_end = priv->stream_begin + priv->stream_length;
ret = parse_JFIF(priv, priv->stream_begin); // 开始解析JPEG
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 */
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++;// 获取0xFF后的一个字节(即为marker标识符)
chuck_len = be16_to_cpu(stream);//FF E0 的下一个字节,即FF E0块的大小
next_chunck = stream + chuck_len;
switch (marker)// 判断marker类型
{
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;// 解析下一个marker
}
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;
}
static int parse_DQT(struct jdec_private *priv, const unsigned char *stream)
{
int qi; // 量化表ID
float *table; // 指向量化表
const unsigned char *dqt_block_end; // 指向量化表结束位置
dqt_block_end = stream + be16_to_cpu(stream);
stream += 2; // 跳过长度字段
while (stream < dqt_block_end) // 检查是否还有量化表
{
qi = *stream++; // 将量化表中系数逐个赋给qi
table = priv->Q_tables[qi];
build_quantization_table(table, stream);
stream += 64;
}
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
}; // 比例因子
const unsigned char *zz = zigzag;
for (i=0; i<8; i++) {
for (j=0; j<8; j++) {
*qtable++ = ref_table[*zz++] * aanscalefactor[i] * aanscalefactor[j];
}
}
}
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
};
static int parse_DHT(struct jdec_private *priv, const unsigned char *stream)
{
unsigned int count, i;
unsigned char huff_bits[17]; // 码长1~16
int length, index;
length = be16_to_cpu(stream) - 2;
stream += 2; // 跳过长度字段
while (length>0) { // 检查是否还有表
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++) {
huff_bits[i] = *stream++;
count += huff_bits[i];
}
if (index & 0xf0 )
build_huffman_table(huff_bits, stream, &priv->HTAC[index&0xf]); // 建立交流表
else
build_huffman_table(huff_bits, stream, &priv->HTDC[index&0xf]); // 建立直流表
length -= 1;
length -= 16;
length -= count;
stream += count;
}
return 0;
}
static void build_huffman_table(const unsigned char *bits, const unsigned char *vals, struct huffman_table *table) // bits为各个位数码字的数量,val为Huffval,table为要建立的Huffman表
{
unsigned int i, j, code, code_size, val, nbits;
unsigned char huffsize[HUFFMAN_BITS_SIZE + 1]; // 每个码字的长度
unsigned char* hz;
unsigned int huffcode[HUFFMAN_BITS_SIZE + 1]; // 每个码字
unsigned char* hc;
int next_free_entry;
/* 初始化 */
hz = huffsize;
for (i=1; i<=16; i++)
{
for (j=1; j<=bits[i]; j++)
*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;
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.
*/
next_free_entry = -1;
for (i=0; huffsize[i] != 0; i++)
{
/* 得到Huffval、每个码字、每个码字的长度*/
val = vals[i];
code = huffcode[i];
code_size = huffsize[i];
table->code_size[val] = code_size; // Huffval(权值)
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; // 得到Huffval长度的查找表
}
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 */
}
}
}
static int parse_SOS(struct jdec_private *priv, const unsigned char *stream)
{
unsigned int i, cid, table;
unsigned int nr_components = stream[2]; // 颜色分量数
stream += 3;
for (i=0;i<nr_components;i++) {
/* 得到使用的Huffmann表号 */
cid = *stream++;
table = *stream++;
priv->component_infos[i].AC_table = &priv->HTAC[table&0xf];
priv->component_infos[i].DC_table = &priv->HTDC[table>>4];
}
priv->stream = stream+3;
return 0;
}
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;
print_SOF(stream);
height = be16_to_cpu(stream+3); // 图像高度
width = be16_to_cpu(stream+5); // 图像宽度
nr_components = stream[7]; // 颜色分量数
stream += 8;
for (i=0; i<nr_components; i++) {
/* 分别解析各分量 */
cid = *stream++; // 分量ID
sampling_factor = *stream++; // 采样因子
Q_table = *stream++;
c = &priv->component_infos[i];
c->Vfactor = sampling_factor&0xf; // 垂直采样因子
c->Hfactor = sampling_factor>>4; // 水平采样因子
c->Q_table = priv->Q_tables[Q_table]; // 使用的量化表
}
priv->width = width;
priv->height = height;
return 0;
}
int tinyjpeg_decode(struct jdec_private *priv, int pixfmt) // pixfmt为输出格式
{
unsigned int x, y, xstride_by_mcu, ystride_by_mcu;
unsigned int bytes_per_blocklines[3], bytes_per_mcu[3];
decode_MCU_fct decode_MCU;
const decode_MCU_fct *decode_mcu_table;
const convert_colorspace_fct *colorspace_array_conv;
convert_colorspace_fct convert_to_pixfmt;
if (setjmp(priv->jump_state))
return -1;
/* To keep gcc happy initialize some array */
bytes_per_mcu[1] = 0;
bytes_per_mcu[2] = 0;
bytes_per_blocklines[1] = 0;
bytes_per_blocklines[2] = 0;
decode_mcu_table = decode_mcu_3comp_table;
switch (pixfmt) {
/* 根据不同的输出格式确定MCU */
case TINYJPEG_FMT_YUV420P:
colorspace_array_conv = convert_colorspace_yuv420p;
if (priv->components[0] == NULL)
priv->components[0] = (uint8_t *)malloc(priv->width * priv->height);
if (priv->components[1] == NULL)
priv->components[1] = (uint8_t *)malloc(priv->width * priv->height/4);
if (priv->components[2] == NULL)
priv->components[2] = (uint8_t *)malloc(priv->width * priv->height/4);
bytes_per_blocklines[0] = priv->width;
bytes_per_blocklines[1] = priv->width/4;
bytes_per_blocklines[2] = priv->width/4;
bytes_per_mcu[0] = 8;
bytes_per_mcu[1] = 4;
bytes_per_mcu[2] = 4;
break;
case TINYJPEG_FMT_RGB24:
colorspace_array_conv = convert_colorspace_rgb24;
if (priv->components[0] == NULL)
priv->components[0] = (uint8_t *)malloc(priv->width * priv->height * 3);
bytes_per_blocklines[0] = priv->width * 3;
bytes_per_mcu[0] = 3*8;
break;
case TINYJPEG_FMT_BGR24:
colorspace_array_conv = convert_colorspace_bgr24;
if (priv->components[0] == NULL)
priv->components[0] = (uint8_t *)malloc(priv->width * priv->height * 3);
bytes_per_blocklines[0] = priv->width * 3;
bytes_per_mcu[0] = 3*8;
break;
case TINYJPEG_FMT_GREY:
decode_mcu_table = decode_mcu_1comp_table;
colorspace_array_conv = convert_colorspace_grey;
if (priv->components[0] == NULL)
priv->components[0] = (uint8_t *)malloc(priv->width * priv->height);
bytes_per_blocklines[0] = priv->width;
bytes_per_mcu[0] = 8;
break;
default:
return -1;
}
xstride_by_mcu = ystride_by_mcu = 8; // 初始化:MCU的宽高均为8px(4:4:4)
if ((priv->component_infos[cY].Hfactor | priv->component_infos[cY].Vfactor) == 1) {
/* 水平、垂直采样因子均为1 */
decode_MCU = decode_mcu_table[0]; // MCU包含1个Y
convert_to_pixfmt = colorspace_array_conv[0];
} else if (priv->component_infos[cY].Hfactor == 1) {
/* 水平采样因子为1,垂直采样因子为2 */
decode_MCU = decode_mcu_table[1]; // MCU包含2个Y
convert_to_pixfmt = colorspace_array_conv[1];
ystride_by_mcu = 16; // MCU高16px,宽8px
} else if (priv->component_infos[cY].Vfactor == 2) {
/* 水平、垂直采样因子均为2 */
decode_MCU = decode_mcu_table[3]; // MCU包含4个Y
convert_to_pixfmt = colorspace_array_conv[3];
xstride_by_mcu = 16; // MCU宽16px
ystride_by_mcu = 16; // MCU高16px
} else {
/* 水平采样因子为2,垂直采样因子为1 */
decode_MCU = decode_mcu_table[2]; // MCU包含2个Y
convert_to_pixfmt = colorspace_array_conv[2];
xstride_by_mcu = 16; // MCU宽16px,高8px
}
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;
/* 对每个像块进行解码(8x8 / 8x16 / 16x16) */
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]);
for (x=0; x < priv->width; x+=xstride_by_mcu)
{
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);
resync(priv);
if (find_next_rst_marker(priv) < 0)
return -1;
}
}
}
}
return 0;
}
static const decode_MCU_fct decode_mcu_3comp_table[4] = {
decode_MCU_1x1_3planes,
decode_MCU_1x2_3planes,
decode_MCU_2x1_3planes,
decode_MCU_2x2_3planes,
};
static const decode_MCU_fct decode_mcu_1comp_table[4] = {
decode_MCU_1x1_1plane,
decode_MCU_1x2_1plane,
decode_MCU_2x1_1plane,
decode_MCU_2x2_1plane,
};
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);
}
txt形式输出霍夫曼码表:
输出量化矩阵:
输出DC图像和AC图像,统计概率分布: