TY - GEN
T1 - Optimization of the keypoint density-based region proposal for R-CNN
AU - Rodríguez Espejo, Luis
AU - Garciá Vázquez, Mireya Saraí
AU - Ramírez Acosta, Alejandro
N1 - Publisher Copyright:
© 2018 SPIE.
PY - 2018
Y1 - 2018
N2 - In areas such as computer vision, the content recognition of an image is a topic of interest in applications such as search engines, biometric security and autonomous cars, among others, since the computer must recognize all the objects that an image can have, which arises as the challenge of localizing and classifying different objects inside a single image in an efficient way. In recent years, this challenge has been approached with the use of region-based convolutional neuronal networks (R-CNN) which are systems that learn to recognize different objects by their representation in a series of images. The proposal of regions is essential for the performance of R-CNN when locating the individual objects of the image with accuracy and in the shortest time. In this article we propose a modification to a method for region proposal based on the density of SIFT like feature points that describe the objects within the image. The selection of regions is made through a decision based on the values of the cumulative distribution function of the normal distribution constructed using points density. The obtained results show a significant reduction in the processing time required for the localization of objects; having slight variations in the classification accuracy with respect to using methods such as KDRP and selective search.
AB - In areas such as computer vision, the content recognition of an image is a topic of interest in applications such as search engines, biometric security and autonomous cars, among others, since the computer must recognize all the objects that an image can have, which arises as the challenge of localizing and classifying different objects inside a single image in an efficient way. In recent years, this challenge has been approached with the use of region-based convolutional neuronal networks (R-CNN) which are systems that learn to recognize different objects by their representation in a series of images. The proposal of regions is essential for the performance of R-CNN when locating the individual objects of the image with accuracy and in the shortest time. In this article we propose a modification to a method for region proposal based on the density of SIFT like feature points that describe the objects within the image. The selection of regions is made through a decision based on the values of the cumulative distribution function of the normal distribution constructed using points density. The obtained results show a significant reduction in the processing time required for the localization of objects; having slight variations in the classification accuracy with respect to using methods such as KDRP and selective search.
KW - Keypoint Density Region Proposal (KDRP)
KW - Object Detection
KW - Region Proposal
KW - Regionbased Convolutional Neural Networks (R-CNN)
KW - Segmentation
KW - Segmented Keypoint Density Region Proposal (SKDRP)
UR - http://www.scopus.com/inward/record.url?scp=85054695692&partnerID=8YFLogxK
U2 - 10.1117/12.2321346
DO - 10.1117/12.2321346
M3 - Contribución a la conferencia
AN - SCOPUS:85054695692
SN - 9781510620735
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Optics and Photonics for Information Processing XII
A2 - Iftekharuddin, Khan M.
A2 - Diaz-Ramirez, Victor H.
A2 - Vazquez, Mireya Garcia
A2 - Awwal, Abdul A. S.
A2 - Marquez, Andres
PB - SPIE
T2 - Optics and Photonics for Information Processing XII 2018
Y2 - 19 August 2018 through 20 August 2018
ER -