Visual Landmark Recognition from Internet Photo Collections: A Large-Scale Evaluation

TL;DR

This paper evaluates the performance of large-scale Internet photo collection-based landmark recognition systems, analyzing each pipeline component to identify limitations and potential improvements across various landmark types.

Contribution

It provides a comprehensive empirical analysis of landmark recognition from Internet photos, highlighting the effects of different methods and parameters on system performance.

Findings

Recognition performance varies significantly across landmark types.

Certain clustering and indexing methods improve recognition accuracy.

Semantic information extraction faces challenges depending on landmark categories.

Abstract

The task of a visual landmark recognition system is to identify photographed buildings or objects in query photos and to provide the user with relevant information on them. With their increasing coverage of the world's landmark buildings and objects, Internet photo collections are now being used as a source for building such systems in a fully automatic fashion. This process typically consists of three steps: clustering large amounts of images by the objects they depict; determining object names from user-provided tags; and building a robust, compact, and efficient recognition index. To this date, however, there is little empirical information on how well current approaches for those steps perform in a large-scale open-set mining and recognition task. Furthermore, there is little empirical information on how recognition performance varies for different types of landmark objects and where there is still potential for improvement. With this paper, we intend to fill these gaps. Using a dataset of 500k images from Paris, we analyze each component of the landmark recognition pipeline in order to answer the following questions: How many and what kinds of objects can be discovered automatically? How can we best use the resulting image clusters to recognize the object in a query? How can the object be efficiently represented in memory for recognition? How reliably can semantic information be extracted? And finally: What are the limiting factors in the resulting pipeline from query to semantics? We evaluate how different choices of methods and parameters for the individual pipeline steps affect overall system performance and examine their effects for different query categories such as buildings, paintings or sculptures.