Image MIME Reference
EDMICS-MMR
Fuji Xerox EDMICS-MMR
image/vnd.fujixerox.edmics-mmr
VS
JPEG AI Image Sequence
image/jais
JPEG-AI-Sequence
A complete technical comparison of Fuji Xerox EDMICS-MMR and JPEG AI Image Sequence — covering compression, feature support, browser compatibility, magic bytes, and when to choose each format.
Equal browser support
Feature Support
| Feature | EDMICS-MMR | JPEG-AI-Sequence |
|---|---|---|
| Transparency (Alpha) | ✕ No | Yes |
| Animation Support | ✕ No | Yes |
| Progressive Loading | ✕ No | Yes |
| HDR Support | ✕ No | Yes |
| EXIF Metadata | ✕ No | Yes |
| ICC Color Profile | ✕ No | Yes |
Fuji Xerox EDMICS-MMR
image/vnd.fujixerox.edmics-mmr
Extension
.mmr.edm
Container
Fuji Xerox EDMICS Wrapper
Compression
Modified Modified READ (MMR / Group 4 Fax)
Algorithm
MMR (ITU-T T.6 / CCITT Group 4)
Color Depth
1-bit (Monochrome / Bi-level)
Developed by
Fuji Xerox Co., Ltd.
Released
1990s
Magic Bytes
Unknown (Proprietary Container wrapped around MMR bitstream)
JPEG AI Image Sequence
image/jais
Extension
.jais
Container
ISOBMFF / HEIF Image Sequence
Compression
Lossy (Variational Autoencoder / Neural Network)
Algorithm
Deep Neural Network (Variational Autoencoder with Hyperpriors)
Color Depth
8-bit, 10-bit, 12-bit, 16-bit, Wide-gamut & HDR
Developed by
Joint Photographic Experts Group (ISO/IEC JTC 1 / ITU-T)
Released
2025
Magic Bytes
.. .. .. .. 66 74 79 70 6A 61 69 73 (Size + ftypjais)
Browser Support Comparison
| Browser | EDMICS-MMR | JPEG-AI-Sequence |
|---|---|---|
Chrome
|
✕ | ✕ |
Firefox
|
✕ | ✕ |
Safari
|
✕ | ✕ |
Edge
|
✕ | ✕ |
IE (Legacy)
|
✕ | ✕ |
EDMICS-MMR
EDMICS-MMR Strengths
- Utilized the highly efficient MMR (Group 4) algorithm, which allowed massive, E-size engineering blueprints to be compressed into tiny file sizes suitable for 1990s hard drives and networks
- Deeply integrated into Fuji Xerox hardware and database systems for seamless scan-to-archive workflows
Limitations
- Completely proprietary and closed-source, making modern archival extraction and migration extremely difficult
- No support in modern image processing libraries like ImageMagick, libvips, or standard TIFF viewers without first stripping the proprietary header
- Strictly limited to 1-bit monochrome images
JPEG-AI-Sequence
JPEG-AI-Sequence Strengths
- Extends the state-of-the-art compression efficiency of JPEG AI to multi-frame image sequences and short animations
- Allows machine vision algorithms to process temporal sequences (like surveillance bursts) directly in the compressed latent domain, saving immense computational power
- Utilizes the robust, industry-standard ISOBMFF container for metadata, timing, and multi-track encapsulation
Limitations
- Lacks native decoding support in current web browsers, operating systems, and video players
- Decoding neural-network-compressed sequences requires significant compute overhead on hardware lacking dedicated AI accelerators (NPUs/GPUs)
- Adoption is hindered by competition with established sequence formats like AVIF, HEVC (HEICS), and modern video codecs
When to choose which format
EDMICS-MMR
Use EDMICS-MMR when…
- Fuji Xerox EDMICS Enterprise Systems
- Archival of Large-Format Engineering Drawings
- Legacy Corporate Document Scanning Pipelines
JPEG-AI-Sequence
Use JPEG-AI-Sequence when…
- Machine Vision and AI Video/Burst Workflows
- Cloud Storage Animation Optimization
- Focal Stacks and Medical Volumetric Slices
- Visual Surveillance Sequences