TY - JOUR
T1 - Computer algorithm for archaeological projectile points automatic classification
AU - Flores, Fernando Castillo
AU - Ugalde, Francisco García
AU - Díaz, Jose Luis Punzo
AU - Navarro, Jesus Zarco
AU - Gastelum-Strozzi, Alfonso
AU - Del Pilar Angeles, María
AU - Miyatake, Mariko Nakano
N1 - Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/6
Y1 - 2019/6
N2 - The manual archaeological projectile point morphological classification is an extensive and complex process since it involves a large number of categories. This article presents an algorithm that automatically makes this process, based on the projectile point digital image and using a classification scheme according to global archaeological approaches. The algorithm supports different conditions such as changes in scale and quality of the image. Moreover, it requires only a uniform background and an approximate north-south projectile point orientation. The principal computer methods that compose the algorithm are the curvature scale space map (CSS-map), the gradient contour on the projectile point, and the support vector machines (SVM) algorithm. Finally, the classifier was trained and tested on a dataset of approximately 800 projectile points images, and the results have shown a better performance than other shape descriptors such as Pyramid of Histograms of Orientation Gradients (PHOG), Histogram of Orientation Shape Context (HOOSC) (both used in a bag-of-words context), and geometric moment invariants (Hu moments).
AB - The manual archaeological projectile point morphological classification is an extensive and complex process since it involves a large number of categories. This article presents an algorithm that automatically makes this process, based on the projectile point digital image and using a classification scheme according to global archaeological approaches. The algorithm supports different conditions such as changes in scale and quality of the image. Moreover, it requires only a uniform background and an approximate north-south projectile point orientation. The principal computer methods that compose the algorithm are the curvature scale space map (CSS-map), the gradient contour on the projectile point, and the support vector machines (SVM) algorithm. Finally, the classifier was trained and tested on a dataset of approximately 800 projectile points images, and the results have shown a better performance than other shape descriptors such as Pyramid of Histograms of Orientation Gradients (PHOG), Histogram of Orientation Shape Context (HOOSC) (both used in a bag-of-words context), and geometric moment invariants (Hu moments).
KW - Automatic classification
KW - CSS-map
KW - Computer vision
KW - Image analysis
KW - Lithic technology
KW - Pattern recognition
KW - Projectile points
UR - http://www.scopus.com/inward/record.url?scp=85067612719&partnerID=8YFLogxK
U2 - 10.1145/3300972
DO - 10.1145/3300972
M3 - Artículo
SN - 1556-4673
VL - 12
JO - Journal on Computing and Cultural Heritage
JF - Journal on Computing and Cultural Heritage
IS - 3
M1 - 3300972
ER -