| Presentation | 1995/9/29 Extraction of Feature Points from Curves and Figure Recognition Teruyuki KANEKO, Ryuzo TAKIYAMA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Methods for information compression and recognition of line drawings(curves) are proposed. For information compression, very smaller number of points(pixels), in comparison with the number of pixels consisting of a digital curve, are extracted, which are called feature points. The feature points extracted in this paper are zero points of a smoothed curvature function as well as points where the function takes maximum absolute values between adjacent zero points. We see that these points can be extracted stably. By using only the feature points line drawings are recognized in position, scaling and rotation invariant manner. To this end the method developed by authors - a method applying algebraic equations - is adopted. The method has several advantages over. those proposed so far. Experimental results are also shown. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Figure recognition / Feature points / Position-scaling-rotational invariant recognition / Coefficients of an algebraic equation / Curvature function / Identification |
| Paper # | PRU95-131 |
| Date of Issue |
| Conference Information | |
| Committee | PRU |
|---|---|
| Conference Date | 1995/9/29(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Pattern Recognition and Understanding (PRU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Extraction of Feature Points from Curves and Figure Recognition |
| Sub Title (in English) | |
| Keyword(1) | Figure recognition |
| Keyword(2) | Feature points |
| Keyword(3) | Position-scaling-rotational invariant recognition |
| Keyword(4) | Coefficients of an algebraic equation |
| Keyword(5) | Curvature function |
| Keyword(6) | Identification |
| 1st Author's Name | Teruyuki KANEKO |
| 1st Author's Affiliation | Kyushu Institute of Design() |
| 2nd Author's Name | Ryuzo TAKIYAMA |
| 2nd Author's Affiliation | Kyushu Institute of Design |
| Date | 1995/9/29 |
| Paper # | PRU95-131 |
| Volume (vol) | vol.95 |
| Number (no) | 279 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |