Learning Near Duplicate Image Pairs using Convolutional Neural Networks

Yi Zhang
2018 International Journal of Performability Engineering  
In this paper, we illustrate how to learn a general straightforward similarity function from raw image pairs, which is a fundamental task in computer vision. To encode the function, inspired by the recent achievements of deep learning methods, we explore several deep neural networks and adopt one of the suitable networks to our task encoding implementation with several models on benchmark datasets UKBench and Holidays. The adopted network achieves comparable overall results and especially
more » ... ts the excellent learning ability for global-similar data. Compared to previous approaches, this function eliminates the complex handcrafted features extraction, and utilizes pairwise correlation information by the jointly processing.
doi:10.23940/ijpe.18.01.p18.168177 fatcat:dhmantppd5gqflrgslfxlwampe