摘 要 JPEG2000是新一代静止图像压缩国际标准，具有优越的图像压缩性能和高的图像质量，不仅克服了传统JPEG静止图像压缩标准在高压缩时出现方块效应的缺点，还提供了图像渐进传输、图像质量可伸缩及感兴趣区域编码等特性，可以应用于数码相机、医疗图像、数字图书馆、网络传输等方面。JPEG2000的这些特性主要来源于小波变换、基于优化截断的嵌入式块编码(EBCOT)技术。由于这些技术的引入，JPEG2000的算法复杂度也相应提高，且在一定程度上限制了JPEG2000的应用。 在对静止图像压缩编码的必要性、理论依据及技术标准的发展做了较全面论述的基础上，本文对JPEG2000标准的编码流程、所使用的算法、码流语法和文件格式等进行了较深入的分析，重点对决定编码器性能的核心算法离散小波变换(DWT)和EBCOT算法进行了研究。首先选用提升算法在VC6.0环境下用C语言实现了离散小波变换，其次针对8bit灰度图像编码对原有标准的EBCOT算法中的位平面编码进行了两点改进：第一，低位平面清除通道扫描省略；第二，高位平面一次扫描。并基于PC机在VC6.0环境下完成C代码的实现。在P4/2.4G/512M上，对512 512的barbabra、lena等图像进行了有损编解码测试，在较低码率下，重构图像主观视觉良好。在保证图像质量的前提下，压缩编码时间缩短8%到12%，解码时间缩短2%到5%。最后以TI公司的新型数字多媒体处理器TMS320DM642为硬件平台，将代码移植到DM642EVM评估板上并进行了相应的结构调整和代码优化。

ABSTRACT JPEG2000 is the lasted generation of international still image compression standard. With excellent image compression performance and superior image quality, it not only addresses a number of weaknesses in the exiting JEPG standard, such as block effect, but also provides several features like image progressive transmission by pixel accuracy and resolution, scalable image quality, lossless/loss compression, region of interest coding, etc. Due to the excellent coding performance and attractive features, JPEG2000 has a large rang of applications such as digital camera, medical imaging, digital library, network transferring and so on. However, it needs high performance processing ability to implement JPEG2000 codec for its complexity algorithms (wavelet transform, embedded block coding with optimized truncation). As a result, a certain extent, the advanced technologies limit the JPEG2000 applications. Analyzed the necessity of still image encode, theoretical and the development of standard in technique completely. The paper researched the standard of JPEG2000 that includes the encoding process, algorithm, coding stream grammar and file format. Here, the main point was to research core algorithm discrete wavelet transform (DWT) and embedded block coding with optimized truncation (EBCOT) which decided the function of the encoder. First the paper realized DWT in VC6.0 on PC with lifting scheme. Then the paper given two methods to improve standard algorithm aim to 8 bit gray images which is eliding clean pass’s scanning of lower bit plane and once scanning for higher bit plane. It realized in VC6.0 with C language. In the P4/2.4G/512M,the paper tested the lossy encoder and decoder with Barbara and Lena (512 512) images. In lower bit rate, the sense of vision felt good in the whole. With the necessary condition to ensure the coding image quality, the encoding of lossy compression time shortened by 8% to 12% and the decoding time shortened by 2% to 5%.Finally, transplanted the source code into the platform of DM642 to adjust and optimize. Then this paper paid attention to the new arithmetic medium processor DM642 as the hardware platform of the company of TI and realized the core algorithm on DSP.