TY - CHAP
T1 - Template matching using a physical inspired algorithm
AU - Oliva, Diego
AU - Cuevas, Erik
PY - 2017/1/1
Y1 - 2017/1/1
N2 - Template matching (TM) plays an important role in several image processing applications such as feature tracking, object recognition, stereo matching and remote sensing. In a TM approach, it is sought the point in which it is proposed the best possible resemblance between a sub-image known as template and its coincident region within a source image. TM involves two critical aspects: similarity measurement and search strategy. The simplest available TM method finds the best possible coincidence between the images through an exhaustive computation of the Normalized cross-correlation (NCC) values (similarity measurement) for all elements of the source image (search strategy). In this chapter, a new algorithm based on the Electromagnetism-Like algorithm (EMO) is presented to reduce the number of search locations in the TM process. The algorithm uses an enhanced EMO version where a modification of the local search procedure is incorporated in order to accelerate the exploitation process. The number of NCC evaluations is also reduced by considering a memory which stores the NCC values previously visited in order to avoid the re-evaluation of the same search locations (particles). Conducted simulations show that the proposed method achieves the best balance over other TM algorithms, in terms of estimation accuracy and computational cost.
AB - Template matching (TM) plays an important role in several image processing applications such as feature tracking, object recognition, stereo matching and remote sensing. In a TM approach, it is sought the point in which it is proposed the best possible resemblance between a sub-image known as template and its coincident region within a source image. TM involves two critical aspects: similarity measurement and search strategy. The simplest available TM method finds the best possible coincidence between the images through an exhaustive computation of the Normalized cross-correlation (NCC) values (similarity measurement) for all elements of the source image (search strategy). In this chapter, a new algorithm based on the Electromagnetism-Like algorithm (EMO) is presented to reduce the number of search locations in the TM process. The algorithm uses an enhanced EMO version where a modification of the local search procedure is incorporated in order to accelerate the exploitation process. The number of NCC evaluations is also reduced by considering a memory which stores the NCC values previously visited in order to avoid the re-evaluation of the same search locations (particles). Conducted simulations show that the proposed method achieves the best balance over other TM algorithms, in terms of estimation accuracy and computational cost.
UR - http://www.scopus.com/inward/record.url?scp=84997235739&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84997235739&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-48550-8_5
DO - 10.1007/978-3-319-48550-8_5
M3 - Chapter
AN - SCOPUS:84997235739
T3 - Intelligent Systems Reference Library
SP - 93
EP - 111
BT - Intelligent Systems Reference Library
PB - Springer Science and Business Media Deutschland GmbH
ER -