Editing 1425: Tasks
Warning: You are not logged in. Your IP address will be publicly visible if you make any edits. If you log in or create an account, your edits will be attributed to your username, along with other benefits.
The edit can be undone.
Please check the comparison below to verify that this is what you want to do, and then save the changes below to finish undoing the edit.
Latest revision | Your text | ||
Line 8: | Line 8: | ||
==Explanation== | ==Explanation== | ||
− | [[Cueball]] appears to be asking [[Ponytail]] to write an app that determines if a given picture is | + | {{incomplete|Explain why it is so difficult to identify a particular object in an image. Better background needed on title text.}} |
+ | [[Cueball]] appears to be asking [[Ponytail]] to write an app that determines if a given picture is of a bird in a national park. These two requirements, while seemingly about equally hard to a human, vary greatly in difficulty in computer science (CS). | ||
− | In order to determine whether the user is in a national park, Ponytail plans to determine the | + | In order to determine whether the user is in a national park, Ponytail plans to determine the the users location, presumably using a GPS or some method of {{w|Mobile phone tracking|mobile phone tracking}}. This location will then be cross checked with a {{w|Geographic information system|GIS (Geographic Information System)}} which will be able to determine whether the co-ordinates lie within a national park boundary. |
+ | |||
+ | Determining whether an image is of a particular object is far more difficult. This task falls into the area of {{w|Computer vision|computer vision}}. One of the goals in computer vision is to detect and classify objects within an image. This is a very challenging task since there is a large variability in the object's appearance and background composition. Furthermore, the object might only be partially visible or occluded. In the case of a living bird additional complication arises from the bird's pose (flying, sitting in a tree, etc.) since it is not a static object (e.g. street sign). The task is especially difficult when the photo quality may be low. | ||
+ | |||
+ | Today's state-of-the-art algorithms for solving this kind of task mostly use local features (e.g. {{w|Scale-invariant feature transform|SIFT}} or {{w|SURF|SURF}} in combination with a {{w|Support vector machine|Support vector machine}} or {{w|Convolutional neural network|Convolutional Neural Networks}}. | ||
+ | |||
+ | The title text mentiones [http://dspace.mit.edu/bitstream/handle/1721.1/6125/AIM-100.pdf The Summer Vision Project] from {{w|Marvin Minsky}} from MIT. In summer 1966 he asked his undergraduate student {{w|Gerald Jay Sussman}} to "spend the summer linking a camera to a computer and getting the computer to describe what it saw" ([http://szeliski.org/Book/]). The project schedule allocated one summer for the completion of this task. This estimation was obviously far underestimated since today dozens of research groups around the world are still working on this topic. | ||
+ | |||
+ | ==Transcript== | ||
+ | :[Ponytail sitting at a computer with Cueball standing behind her] | ||
+ | :Cueball: When a user takes a photo, the app should check whether they're in a national park... | ||
+ | :Ponytail: Sure, easy GIS lookup. Gimme a few hours. | ||
+ | :Cueball: ...and check whether the photo is of a bird. | ||
+ | :Ponytail: I'll need a research team and five years. | ||
+ | :In CS, it can be hard to explain the difference between the easy and the virtually impossible | ||
+ | |||
+ | {{comic discussion}} | ||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
==Transcript== | ==Transcript== | ||
− | :[Ponytail sitting at a computer with Cueball standing behind her | + | :[Ponytail sitting at a computer with Cueball standing behind her] |
:Cueball: When a user takes a photo, the app should check whether they're in a national park... | :Cueball: When a user takes a photo, the app should check whether they're in a national park... | ||
:Ponytail: Sure, easy GIS lookup. Gimme a few hours. | :Ponytail: Sure, easy GIS lookup. Gimme a few hours. | ||
:Cueball: ...and check whether the photo is of a bird. | :Cueball: ...and check whether the photo is of a bird. | ||
:Ponytail: I'll need a research team and five years. | :Ponytail: I'll need a research team and five years. | ||
− | + | :In CS, it can be hard to explain the difference between the easy and the virtually impossible | |
− | |||
− | :In CS, it can be hard to explain the difference between the easy and the virtually impossible | ||
− | |||
{{comic discussion}} | {{comic discussion}} | ||
− | |||
− | |||
− | |||
− | |||
− | |||
− |