# Image Compression Performance
**URL:** https://discourse.itk.org/t/image-compression-performance/5570
**Category:** Engineering
**Tags:** compression
**Created:** [December 13, 2022, 1:34pm UTC](https://discourse.itk.org/t/image-compression-performance/5570 "2022-12-13T13:34:59Z")
**Posts on this page:** 5
**Page:** 1
### Author:  [@blowekamp](https://discourse.itk.org/u/blowekamp)
#### Post date: [December 13, 2022, 1:34pm UTC](https://discourse.itk.org/t/image-compression-performance/5570/1 "2022-12-13T13:34:59Z")
I have encountered a situations where using gzip level 9 to compress an image is taking ~40x longer (depending on the image content) than writing the image without compression
@dzenanz I recall you did some performance analysis of various compression algorithms and level. Is this analysis still available on line some place?
Thanks!
---
### Author:  [@dzenanz](https://discourse.itk.org/u/dzenanz)
#### Post date: [December 13, 2022, 1:49pm UTC](https://discourse.itk.org/t/image-compression-performance/5570/2 "2022-12-13T13:49:08Z")
I can’t find it now, but I do have some spreadsheets with the benchmarks.
[zlib-ng-announcement.xlsx](https://discourse.itk.org/uploads/short-url/em8gB8CEQsw6tO0GbkYFDitI4nd.xlsx) (22.8 KB)
[zlib-comparison.xlsx](https://discourse.itk.org/uploads/short-url/akCkDNalG54GaiK51tH3hdDxJlu.xlsx) (24.6 KB)
---
### Author:  [@dzenanz](https://discourse.itk.org/u/dzenanz)
#### Post date: [December 13, 2022, 1:52pm UTC](https://discourse.itk.org/t/image-compression-performance/5570/3 "2022-12-13T13:52:51Z")
Also, here are some older experiments I conducted. They compare Blosc+LZ (blosc’s default), blosc+zstd, zstd used directly, and zlib.
[CBCT.tsv](https://discourse.itk.org/uploads/short-url/4DggsFwz6pxke91ONvb3RP3JnGR.tsv) (1.2 KB)
[mra.tsv](https://discourse.itk.org/uploads/short-url/ebQfBgXD7kfNfFqgyJl2Nb4PkOw.tsv) (1.2 KB)
[mraSingle.tsv](https://discourse.itk.org/uploads/short-url/edWVhcIZaUVI0H4pr2ymrh2zD5t.tsv) (1.2 KB)
[us1.tsv](https://discourse.itk.org/uploads/short-url/ySoMM3VXbnXoq2RW1kdVa6cGpeY.tsv) (1.2 KB)
[us2.tsv](https://discourse.itk.org/uploads/short-url/r9LUJMgX2iGVwob4cEAq1U23yfK.tsv) (1.2 KB)
[wb.tsv](https://discourse.itk.org/uploads/short-url/2aEX66PA3mwArc56hyMbJNVmppl.tsv) (1.2 KB)
[wbPET1.tsv](https://discourse.itk.org/uploads/short-url/kvYGA9Z9mXsXl9SJEniHUrBFyBo.tsv) (1.2 KB)
[wbPET2.tsv](https://discourse.itk.org/uploads/short-url/kiKLtlyIf21HLhtEK7yvcVbzv4E.tsv) (1.2 KB)
[wbPET8.tsv](https://discourse.itk.org/uploads/short-url/6la0liYZsFfGt6CaQYo7qI4TxeT.tsv) (1.2 KB)
[wb-seg.tsv](https://discourse.itk.org/uploads/short-url/qB9Tcf6WpjxbW0rg3PVkgF2qjKi.tsv) (1.2 KB)
---
### Author:  [@blowekamp](https://discourse.itk.org/u/blowekamp)
#### Post date: [December 13, 2022, 2:05pm UTC](https://discourse.itk.org/t/image-compression-performance/5570/4 "2022-12-13T14:05:25Z")
Thank you very much for sharing that. It is very useful! I see one case where zlib level 9 takes ~10x longer than level 1, but does not yield even 1% more compression ratio.
---
### Author:  [@dzenanz](https://discourse.itk.org/u/dzenanz)
#### Post date: [December 13, 2022, 2:28pm UTC](https://discourse.itk.org/t/image-compression-performance/5570/5 "2022-12-13T14:28:21Z")
That’s why we chose a relatively low default compression level.