Jump to content

atblakely

Active Members
  • Posts

    6
  • Joined

  • Last visited

Posts posted by atblakely

  1. The idea is interesting, but for SATA as a network, you'd defiantly have an interesting time with it. My guess is that you simply can't plug two computers together (if you did a null modem approach, maybe.) but then the issue is the SATA controller is expecting a SATA device, not another controller. You'd probably have to design some kind of device which emulates a SATA device on both ports then does the required IO multiplexing. If you'd like to actually make an implantation I'd start out by reading the SATA protocol spec. Who knows, there might be something in there that would make this easier.

  2. OpenVa is great place to start with. My advice is, go with a preexisting library that actually does most of the grunt work. Facial recognition is an exceedingly specialized field. Having already tried to roll my own, you're going to wish that you taken applied mathmatics in college (and if you did, kudos).

    Otherwise sounds like a great project. Does Hadoop include facerecognition?

    I'm not interested in rolling my own library, I can just imagine the nightmare of trying to write something like that. That's why I'm kinda looking at OpenCV. Hadoop does not include face recognition. It is a platform which is based off some google specs for their MapReduce and GFS implantations. Which is how Google is able to store data across multiple machines and process it using multiple machines.

    I want to use Hadoop because it can help scale this type of system to something for a social network. It's been reported that Hadoop has been able to process 1TB of data in less than one minute. I'm not sure the size of the cluster used for this and when this was but I can only imagine that there's been faster processing time on bigger sets of data as hadoop grows, and code optimization can help too. If I remember correctly I have seen reports of Hadoop clusters spanning up to 10,000 nodes or more which is impressive.

    But as you can see Hadoop would help with processing the face data. As for how it would determine which person is which I am not sure yet. I'm going to start doing some research in this topic soon and might write some test code.

  3. Sounds like a good project, you could try training a neural net to recognise faces in photos or try to identify key facial features and then use the ratios between them as a signature to identify people, or something else? Either way you should learn a lot from it.

    I'm going to see now Android does it's face recognition. That might shed some more light, but it's not meant for something that would be the scale of a social network. Does anyone have any opinions on the Hadoop project, I thought that might be good for maybe running this kind of thing. I'm not a Java dev by any means. I do more C, Perl, Node.js, and some assembly type work.

×
×
  • Create New...