JPEG XR是一種新型的影像壓縮技術，其目的在於解決隨著科技不斷的進步,越來越多的多媒體資料須要更有效的壓縮演算法提供更高的影像品質以及更低的運算複雜度於編解碼端的問題。在此一情形下，Microsoft提出了一個全新的靜態影像壓縮演算法，也就是現在廣為人知的HD photo，其內部採用了階層式架構，以block組成的macroblock作為基底方式作運算。其中最重要的頻率轉換被稱為Lapped Biorthobonal Transform (LBT)，是由photo overlap transform (POT)與photo core transform (PCT)為主所組成的轉換方式，可有效地消除邊界效應所帶來的困擾。
我們分析其演算法，可以發現LBT頻率轉換為演算法中最為複雜的部份,在探究其內部資料的相依性與資料運算的重疊部分之後，我們發現硬體所能達到的加速效果有限。本篇論文中改善POT與PCT的資料運作方式並以管線化架構進行硬體實作,有效地達到增加速度與降低成本的主要目的 。

JPEG XR is a novel image compression technology, which aims to solve problems that come from technological advances. In recent year, more and more multimedia data need to be effectively compressed with algorithm which provides higher image quality and lower computational complexity in the encoder amd decoder. In this situation, Microsoft made a new still image compression algorithm that is well-known as HD photo, its internal use of the hierarchical structure composed by macroblocks as block-based method in computing. One of the most important frequency transform is called Lapped Biorthobonal Transform (LBT ), mainly formed by the POT and the PCT and effective in eliminating the nuisance caused by boundary effects.
Analyzing the algorithm, it can be found that the LBT frequency conversion is the most complex part of the algorithm. To explore its internal data dependencies and data operations overlap, we find that hardware acceleration can achieve a limited effect. In our thesis we improve the PCT and the POT algorithm and use pipeline architecture in hardware implementation, effectively increase the speed and reduce costs to achieve the main purposes.

[1] ISO / IEC 10918-4:1999, "Information technology - Digital compression and coding of continuous-tone still images: Registration of JPEG profiles, SPIFF profiles, SPIFF tags, SPIFF colour spaces, APPn markers, SPIFF compression types and Registration Authorities (REGAUT) "
[2] ISO / IEC 10918-1:1994, "Information technology - digital compression and coding of continuous-tone still images - requirements and guidelines."
[3] ISO / IEC 29199-2, "JPEG XR image coding system - Part 2: Image coding specification".
[4] ISO / IEC 29199-3, "JPEG XR image coding system - Part 2: Motion JPEG XR".
[5] Ching-Yen Chien, Sheng-Chieh Huang, Shih-Hsiang Lin, Yu-Chieh Huang, Yi-Cheng Chen, Lei-Chun Chou1, Tzu-Der Chuang, Yu-Wei Chang, Chia-Ho Pan and Liang-Gee Chen, "A 100 MHZ 1920x1080 HD-PHOTO 20 FRAMES / SEC JPEG XR ENCODER DESIGN," IEEE International Conference on image Processing, 2008. ICIP 2008.
[6] Perra, C. and Giusto, D. "An image browsing application based on JPEG XR," IEEE Conf. International Workshop on Content-Based Multimedia Indexing, 2008. CBMI 2008.
[7] De Neve, W., Yang, S., Van Deursen, D., Kim, C., Ro, YM and Van de Walle, R. "Analysis of BSDL-based content adaptation for JPEG 2000 and HD Photo (JPEG XR), "IET Conf. International Conference on Visual Information Engineering, 2008.
[8] Michael Keating and Pierre Bricaud, "REUSE METHODOLOGY MANUAL FOR SYSTEM-ON-A-CHIP DESIGNS," Kluwer Academic Publishers, USA, pp.4, 1999.
[9] Giusto, DD and Onali, T. "Data Compression for Digital Photography: Performance comparison between proprietary solutions and standards," IEEE Conf. International Conference on Consumer Electronics, 2007. ICCE 2007.
[10] Koichi Hattori∗, Hiroshi Tsutsui†, Hiroyuki Ochi, and Yukihiro Nakamura, " A High-Throughput Pipelined Architecture forJPEG XR Encoding " Dept. of Communications and Computer Engineering.
[11] Jizheng Xu, Feng Wu, Jie Liang and Wenjun Zhang, "Directional Lapped Transforms for Image Coding" Data Compression Conference, 2008. DDC 2008.
[12] Sridhar Srinivasan, Chengjie Tu, Shankar L. Regunathan, and Gary J. Sullivan, "HD Photo: A new image coding technology for digital photography," Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA.
[13] Lang Yu, "Evaluating and Implementing JPEG XR Optimized for Video Surveillance," Report number: LiTH-ISY-EX--10/4300--SELinköping 1st March 2010
[14] Po Chao Fang, "Novel Architecture for POT and PCT in JPEG XR Encoder"