tgl@g.gp.cs.cmu.edu (Tom Lane) (01/11/91)
In article <1051@gistdev.gist.com>, flint@gistdev.gist.com (Flint Pellett) writes: > cn@allgfx.agi.oz (Con Neri) writes: > >The JPEG (Joint Photographic Experts Group) draft standard implements a > >DCT based image compression algorithm. ... Typical compression ratios are > >around 30:1 for 24 bit RGB images with reasonably high resolution. > > This doesn't say how much time is required to do the uncompression. > (I could care less if it takes 20 minutes to compress it, as long as it > can be uncompressed rapidly.) Before JPEG can displace something like > GIF, it's going to have to be able to uncompress images in something > less than 5 seconds on a typical PC, (and obviously, if you want it to > handle animation, you're going to have to get down in the fractional > second range.) Gimme a break. Even GIF images usually take longer than 5 seconds to decompress, unless you are talking real small images (or maybe you have a 486?) Software implementations of JPEG *will* be a good bit slower than GIF. However, this is not a good reason to reject it for net posting purposes. Remember that JPEG-compressed files will also be a factor of 5 (more or less) smaller than comparable GIF files. In many cases this translates directly into time savings; for example, I have to download any net-posted image across a 2400bps modem link before I can view it. Assuming a GIF image size of 100Kb (which is on the small side), that takes at least 7 minutes. The same image in JPEG format might be about 20Kb = 1.5 minutes. So if it takes less than 5 minutes to decompress the JPEG image, I have come out ahead on time, and that doesn't even consider the disk space and network bandwidth savings that are accrued all over the net. If I'm going to view the same image over and over, I probably wouldn't want to pay the price of JPEG decompression each time. No problem: convert it to GIF or something else that's cheap to display while I'm working on it. It's still worthwhile to use JPEG format for transmission and archival storage purposes. > I've not seen any concrete data on decompression speed > other than one article that quoted times around 2 minutes (yeech!) > by some package I don't remember the name of. Can anyone who knows > tell us what speed is available right now, both from software and from > hardware solutions? Thanks. The prototype JPEG code that my group is playing around with now takes maybe 3 or 4 minutes to process a typical image (300000 pixels or so) on medium-fast PC class hardware. We haven't made any serious effort to optimize for speed yet, so I think the final result will be significantly better; maybe 1 or 2 minutes. (Incidentally, decompression is about the same speed as compression, and there's no way to make it significantly faster 'cause the algorithm is symmetrical.) Hardware-based solutions will be lots faster, but still not video speed. JPEG is not intended for video applications; there is a separate standards effort (called MPEG) addressing the question of video compression. -- tom lane Internet: tgl@cs.cmu.edu UUCP: <your favorite internet/arpanet gateway>!cs.cmu.edu!tgl BITNET: tgl%cs.cmu.edu@cmuccvma CompuServe: >internet:tgl@cs.cmu.edu
drake@drake.almaden.ibm.com (01/13/91)
In article <11547@pt.cs.cmu.edu> tgl@g.gp.cs.cmu.edu (Tom Lane) writes: >Hardware-based solutions will be lots faster, but still not video speed. Not true; at the MultiMedia Expo at San Francisco in November two vendors showed full motion digital video in a window on the Mac using JPEG compression. Thirty frames per second from the hard disk, being decompressed and displayed in real time. The C-Cube chips are capable of compression and decompression at 30 fps. Sam Drake / IBM Almaden Research Center Internet: drake@ibm.com BITNET: DRAKE at ALMADEN Usenet: ...!uunet!ibmarc!drake Phone: (408) 927-1861
fpa@qualcomm.com (Franklin Antonio) (01/14/91)
In article <421@rufus.UUCP> drake@drake.almaden.ibm.com writes: >... at the MultiMedia Expo at San Francisco in November two vendors >showed full motion digital video in a window on the Mac using JPEG >compression. Does anybody know who these two venders were? I'd be interested in name, and phone number.
jeremy@ultima.socs.uts.edu.au (Jeremy Fitzhardinge) (01/14/91)
drake@drake.almaden.ibm.com writes: >In article <11547@pt.cs.cmu.edu> tgl@g.gp.cs.cmu.edu (Tom Lane) writes: >>Hardware-based solutions will be lots faster, but still not video speed. > >Not true; at the MultiMedia Expo at San Francisco in November two vendors >showed full motion digital video in a window on the Mac using JPEG >compression. Thirty frames per second from the hard disk, being decompressed >and displayed in real time. The C-Cube chips are capable of compression >and decompression at 30 fps. I'm pretty sure I read about Inmos producing a chip that can encode image data in television quality at 25 frames per second. Since its a British company, I guess thats a 625 line PAL image. I'm not sure if it was JPEG, but it certainly used a DCT algorithm. -- Jeremy Fitzhardinge:jeremy@ultima.socs.uts.edu.au jeremy@utscsd.csd.uts.edu.au QUESTION AUTHORITY. Sez who? -- Jeremy Fitzhardinge:jeremy@ultima.socs.uts.edu.au jeremy@utscsd.csd.uts.edu.au QUESTION AUTHORITY. Sez who?
george@hobbes.ncsu.edu (George Browning) (01/15/91)
Could someone please give me the phone number and address of C-Cube Microsytems? Any estimates on the price of their JPEG chip? Thanks george -- ------------------------------------------------------------------------ | o | George Browning george@catt.ncsu.edu | o | | o | NC State University Raleigh, NC | o | ------------------------------------------------------------------------
jwhitnell@cup.portal.com (Jerry D Whitnell) (01/18/91)
|In article <421@rufus.UUCP> drake@drake.almaden.ibm.com writes: |>... at the MultiMedia Expo at San Francisco in November two vendors |>showed full motion digital video in a window on the Mac using JPEG |>compression. | |Does anybody know who these two venders were? |I'd be interested in name, and phone number. SuperMac Technology was one. We also showed our Digital Film product at MacWorld San Francisco. Our number is (408) 245-2202. Digital Film, however, is currently only a prototype and is still under development. I don't know if we've annouced a ship date for it yet or not. Jerry Whitnell SuperMac Technology
hsi@netcom.UUCP (Handmade Software) (01/23/91)
In article <1991Jan14.204134.20850@ncsuvx.ncsu.edu>, george@hobbes.ncsu.edu (George Browning) writes: > > Could someone please give me the phone number and address > of C-Cube Microsytems? Any estimates on the price of their JPEG chip? > C-Cube Microsystems 399-A West Trimble Road San Jose, CA 95131 408/944-6300 408/944-6314 fax A good person to speak with is Clint Chao. The last price quote I got from C-Cube for small quantities was $550. marcos -- Handmade Software, Inc. 15951 Los Gatos Blvd, Suite 7 Los Gatos, CA 95032 hsi@netcom.uucp or {apple|claris}!netcom!hsi