Indian Journal of Science and Technology
DOI: 10.17485/ijst/2016/v9i17/92297
Year: 2016, Volume: 9, Issue: 17, Pages: 1-10
Original Article
Trinh Thi Phan1 , Thai-Nguyen Do Nguyen2 and Thai Hoang Le3
1Computer Science Department, Thu Duc Technology College, Ho Chi Minh City, Vietnam; [email protected] 2Computer Science Department, University of Pedagogy, Ho Chi Minh City, Vietnam; [email protected] 3Computer Science Department, University of Science, VNU - HCM, Vietnam; [email protected]
In this paper, we present a novel methodimage retrieval model for mobile product image searching system. For feature extraction, a method integrating Speeded Up Robust Features (SURF) and Local Binary Pattern (LBP) is proposed. SURF is invariant to rotation, scaling, translation and have low calculated cost, so SURF is quite suitable for mobile product image search model. However, SURF is not effective with the noisy images, blur images, illuminated images. Because LBP operator is invariant to changes in illumination and contrast of images, we use LBP to supplement for disadvantages of the SURF features. Our proposed method can improve accuracy and speed of the system. For query, a query model using K-NN Search with vector quantization is used. This model improve performance and reduce the cost of computation of the mobile product image searching system. The experimental results show the feasibility of our proposal model.
Keywords: Content-based Image Retrieval (CBIR), Feature Integration, K-Nearest Neighbor (K-NN), Local Binary Pattern (LBP), Mobile Product Image Search, Speeded Up Robust Features (SURF)
Subscribe now for latest articles and news.
