TY - GEN
T1 - Automatic price calculation of consumer products using SURF with texture matching
AU - Hnoohom, Narit
AU - Tippanun, Sasithorn
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/6/8
Y1 - 2018/6/8
N2 - Many department stores in Thailand do not fully pass-through payments to check the total price before a purchase is made. The adoption of automatic price calculation can help to overcome this problem in future, and the customers can move their shopping cart to pass-through over a self-service payment. This paper presents an automatic price calculation of consumer products as images using an integration of the Speeded Up Robust Features (SURF) with texture matching. Various consumer products with several shapes were taken by the researcher to create a Consumer Product (CP) database, comprising 116 images. This database included three main different types of product: snacks, face care, and skin care. In order to evaluate the performance of the proposed algorithm, two experiments as non-overlapping and 20% overlapping were conducted in this study to test the accuracy of the calculation of total consumer product prices. Results indicated that the accuracy of the proposed algorithm is 100%.
AB - Many department stores in Thailand do not fully pass-through payments to check the total price before a purchase is made. The adoption of automatic price calculation can help to overcome this problem in future, and the customers can move their shopping cart to pass-through over a self-service payment. This paper presents an automatic price calculation of consumer products as images using an integration of the Speeded Up Robust Features (SURF) with texture matching. Various consumer products with several shapes were taken by the researcher to create a Consumer Product (CP) database, comprising 116 images. This database included three main different types of product: snacks, face care, and skin care. In order to evaluate the performance of the proposed algorithm, two experiments as non-overlapping and 20% overlapping were conducted in this study to test the accuracy of the calculation of total consumer product prices. Results indicated that the accuracy of the proposed algorithm is 100%.
KW - Consumer product
KW - Speeded Up Robust Features
KW - Texture matching
UR - https://www.scopus.com/pages/publications/85049940865
U2 - 10.1109/ECTI-NCON.2018.8378284
DO - 10.1109/ECTI-NCON.2018.8378284
M3 - Conference contribution
AN - SCOPUS:85049940865
T3 - 1st International ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI-NCON 2018
SP - 69
EP - 73
BT - 1st International ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI-NCON 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1st International ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, ECTI-NCON 2018
Y2 - 25 February 2018 through 28 February 2018
ER -