THE GROVE MASTER (CAPSLOCK IS STUCK)
Summary:
A user interface that feels like smart paper. Combined with the goal of direct manipulation, you have the basis for this paper by Sezgin and company. The paper's focus is on the first step of the sketch recognition process- converting pixels into geometric shapes. This process is broken up into three phases:
1. Approximation: Minimize error and avoid overfitting.
The first part of approximation is vertex detection. Taking advantage of features such as slower speeds and increased curvature at corners, the authors find outliers above a computed threshold and treat them as potential vertices. Computed features are then combined in an attempt to further drop false positives.
The second part of approximation is curve handling... read that for yourself...2. Beautification: Modify output to be more visually appealing
This step is basically a line straightener. Lines that are in groups are rotated by their midpoints to try and maintain close connections at vertices.
3. Basic Object Recognition: Produce stroke interpretations
Ovals, circles, rectangles, and squares are basic objects. Template matching is employed to detect these geometric objects.
The authors found that people liked being able to use multiple strokes to draw a single object (go figure). The shapes used in the study were pretty crazy, thus proving the system was capable of being awesome.
Discussion:
I didn't really connect with this paper... I'm not sure why. Maybe they just didn't stress the impact that their system had enough for me to identify with it. Can anyone clear that up for me?
I have the same problem, not enough information on the recognition process. Much more details about just the preprocessing. It kind a feel abstract how they do the recognition.
ReplyDeleteBut I guess preprocessing is much more easier and detailed to understand and probably to use with a new design.
Hmmm.... Me too. I wrote the same problem to my blog. I need more information about that.
ReplyDeleteI agree with the connection issue. He focused a good deal of time in explaining the ins and outs of certain parts of his algorithm and glossed over others. Perhaps the main problem was that he didn't describe individual cases of the shapes in the results section. A little real-life detail would have gone a long way to connecting with the reader.
ReplyDeleteI guess according to the title of this paper, it focuses on the preprocessing algorithm, i.e., the stroke approximations for linear and curvy segments. The recognition algorithm used at the last stage, IMO can be any kind of famous recognition algorithm such as Rubine's.
ReplyDeleteRight, I'm also impressed by the crazy examples they had in page 8.
I am impressed by this paper, one of my favorate papers
ReplyDelete