The LJPEG-D core implements a Lossless JPEG (LJPEG) decoder in a compact, high-performance, stand-alone package ideal for applications where bit-by-bit accurate repro-duction of an image is essential.
The LJPEG-D decodes images that conform to the spatial (sequential) lossless encoding mode (SOF3) of the ISO/IEC 10918-1 standard (CCITT T.81 recommendation). Rather than the Discrete Cosine Transform (DCT) functions used for lossy JPEG compression - which can introduce round-off errors - the lossless part of the standard employs a reversible predictor function. The LJPEG-D core can thus decode images with no information loss, and requires a smaller physical implementation than what necessary for lossy JPEG image decoding.
Evaluation designs show that the core requires just 36K gates in an ASIC (0.09µ process / typical conditions) and that it also fits in a variety of low-end and high-end FPGA devices. Its optimized architecture also enables a high performance, reaching 500 MSamples/sec on ASICs and 95 MSamples/sec on FPGAs.
The LJPEG-D is a fully synchronous, strictly positive-edge design with no internal three-state buffers. Comprehensive documentation and a complete verification environment - including a bit-accurate model - help designers integrate and verify the core.
- Conforms to the spatial (sequential) lossless encoding mode (SOF3), of the ISO/IEC 10918-1 standard (CCITT T.81 recommendation).
- Standalone operation
- ISO/IEC 10918-1 JPEG stream input.
- Decoded pixel samples output.
- Self programmable through the standard JPEG markers.
- Programmable image dimensions
- Programmable image sample precision (2 - 16 bits/sample)
- Up to 4 stream-programmable Huffman coding tables
- Programmable Restart Interval
- Programmable Point Transform function
- Headers errors catch-up features
- Compact, high performance architecture.
- 36K gates achieving 500 MSamples/sec (TC 0.19µ ASIC)
- Also fits low-cost FPGAs (see FPGA version datasheets)
- Robust and simple to use:
- General purpose, fully stallable, streaming I/O interfaces.
- Limitations with respect to the ISO/IEC 10918-1 standard:
- Up to three image components are supported (Nf field of the SOF3 marker segment = 1 or 2 or 3)
- Single scan encoding (Only one SOS marker segment, with Ns field = Nf)
- No DNL marker support (Y field of the SOF3 marker segment > 0)
- Fixed parameters
- No sub-sampling (Hi and Vi fields of the SOF3 marker segment = 1)
- Prediction function is fixed to left-hand predictor (predictor 1) (Ss field of SOS marker segment = 1)
- Medical, military, and space imaging.
- Professional, studio quality cameras and editing suites.
- High-end film and photo scanners.
- Industrial machine vision systems.
Block Diagram of the Lossless JPEG Decoder