Category classification method
A category classification method includes: calculating function values corresponding to a relationship between a classification target and support vectors that contribute to a classification boundary, calculating an addition value in which the function value for each support vector has been added, and classifying that the classification target does not pertain to a specific category in case that the addition value is smaller than a threshold, wherein calculation of the addition value is carried out by adding function values having positive values, then adding function values having negative values, and the classification target is classified as not pertaining to the specific category, without adding the remaining function values, in case that the addition value has become smaller than the threshold.
1. A category classification method, comprising:
calculating function values corresponding to a relationship between a classification target and support vectors that contribute to a classification boundary,
calculating an addition value in which the function value for each support vector has been added,
wherein calculation of the addition value is carried out by adding function values having positive values, then adding function values having negative values until the addition value becomes smaller than a threshold, or no more function values remain, and
the classification target is classified as not pertaining to the specific category in case that the addition value has become smaller than the threshold.
2. A category classification method according to claim 1 ,
wherein a determination is performed as to whether or not the function value to be added to the addition value is a negative value, and
the classification target is classified as not pertaining to the specific category in case that the function value is a negative value and the addition value has become smaller than the threshold.
3. A category classification method according to claim 1 ,
wherein the function values having negative values are added to the addition value in order from those having larger absolute values.
4. A category classification method, comprising:
calculating function values corresponding to a relationship between a classification target and support vectors that contribute to a classification boundary,
calculating an addition value in which the function value for each support vector has been added,
wherein calculation of the addition value is carried out by adding function values having positive values, then adding function values having negative values until the addition value becomes smaller than or equal to a threshold, or no more function values remain, and
classifying that the classification target pertains to a specific category in case that the addition value is larger than a threshold after all negative function values have been added, and
it is determined that the classification target cannot be classified as pertaining to the specific category in case that the addition value has become equal to or lower than the threshold.
5. A category classification method according to claim 4 ,
wherein a determination is performed as to whether or not the function value to be added to the addition value is a negative value, and
a determination is made that the classification target cannot be classified as pertaining to the specific category in case that the function value is a negative value and the addition value has become equal to or less than the threshold.
6. A category classification method according to claim 4 ,
wherein the function values having negative values are added to the addition value in order from those having larger absolute values.
7. A category classification method, comprising:
calculating function values corresponding to a relationship between a classification target and support vectors that contribute to a classification boundary,
calculating an addition value in which the function value for each support vector has been added,
wherein calculation of the addition value is carried out by adding function values having negative values, then adding function values having positive values until the addition value becomes greater than a threshold or no more function values remain, and
the classification target is classified as pertaining to the specific category in case that the addition value has become larger than the threshold.
8. A category classification method according to claim 7 ,
wherein a determination is performed as to whether or not the function value to be added to the addition value is a positive value, and
the classification target is classified as pertaining to the specific category in case that the function value is a positive value and the addition value has become larger than the threshold.
9. A category classification method according to claim 7 ,
wherein the function values having positive values are added to the addition value in order from those having larger values.