Re-ranking approach to mobile landmark recognition

Abstract

In recent years, landmark image recognition has been a developing application on computer. In order to improve the recognition rate, we propose a re-ranking method for mobile landmark recognition systems. The query feature vector is modified identifying important features and non-important features. These are conducted from the ranked feature vectors according to feature selection criteria. Positive and negative weighting schemes are applied for the modification of the query to recognize the target landmark image. The experimental results show that the re-ranking method can improve the recognition rate, as compared to the previously proposed methods that utilize saliency weighting and scalable vocabulary tree encoding.

NU-LiteNet: Mobile Landmark Recognition using Convolutional Neural Networks

“…In the past, landmark recognition [1,2,3,4,5] utilized the capability of computers. These computing devices can cope with the large size of databases and the computational complexity, with sufficient resources to operate the application.…”