Indexing in large scale image collections: Scaling properties and benchmark

Aly, Mohamed; Munich, Mario E.; Perona, Pietro

doi:10.1109/wacv.2011.5711534

Cited by 41 publications

(42 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aside from feature descriptor, there are three main issues of concern, namely, storage, computational cost and recognition performance. It is not surprising to observe that indexing huge databases images has become an active research topic recently [3].…”

Section: Applied Mechanics and Materials Vols 182-183mentioning

confidence: 99%

Mobile Tour Planning Using Landmark Photo Matching and Intelligent Character Recognition

Huang

Liao

Chen

2012

AMM

View full text Add to dashboard Cite

Abstract. The functionalities of smart phones have extended from basic voice communication to gaming, multimedia entertainment, information retrieval and location-based services. In this paper, we attempt to design a mobile application to assist visitors to have better understandings of popular tourist destinations and related routing information while on tour. The users can obtain descriptions of a specific attraction by simply taking the picture of a landmark photo often shown in the travel booklet using their mobile devices. This is achieved by matching the landmark picture with an image database containing popular tourist spots to locate the interested destination. The location information is further confirmed using techniques in intelligent character recognition. Upon successful identification of the interested location, tourist information regarding this destination, along with the routing details will be delivered using location-based service. We anticipate the proposed mobile application to effectively assist foreign visitors by bringing comprehensive, up-to-date tourist information and promoting better travel experience.

show abstract

Section: Applied Mechanics and Materials Vols 182-183mentioning

confidence: 99%

Mobile Tour Planning Using Landmark Photo Matching and Intelligent Character Recognition

Huang

Liao

Chen

2012

AMM

View full text Add to dashboard Cite

show abstract

“…There are two major approaches for building such databases: Bag of Words (BoW) [1,2,8,16,17,18] and Full Representation (FR) [2,11]. In the first, each image is represented by a histogram of occurrences of quantized features, and search is usually done efficiently using an Inverted File (IF) structure [19].…”

Section: Introductionmentioning

confidence: 99%

“…Kd-Trees [11]). The first has the advantage of using an order of magnitude less storage, however its performance is far worse, see [2] for a benchmark. Hence, we focus on FR with Kd-Trees at its core.…”

Section: Introductionmentioning

confidence: 99%

“…Most past research on large scale image search [1,2,5,8,9,10,14,15,16,17] did not scale past a few million images on one machine because of RAM limits. However, if the goal is to scale up to billions of images, we have to think beyond one machine.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, we focus on ways to distribute the image database on an arbitrary number of machines to be able to scale up the recognition problem to hundreds of millions of images. We implement and compare two approaches for Kd-Tree parallelizations using the MapReduce paradigm [7]: Independent Kd-Trees (IKdt), which is the baseline brute force approach, and Distributed Kd-Trees (DKdt) [2], see Figure 1. We run extensive experiments to assess the different system parameters and compare the two approaches with datasets of up to 100 million images on a computer cluster with over 2000 machines.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Distributed Kd-Trees for Ultra Large Scale Object Recognition

Aly

Munich²,

Perona

2011

Procedings of the British Machine Vision Conference 2011

Self Cite

View full text Add to dashboard Cite

Distributed Kd-Trees is a method for building image retrieval systems that can handle hundreds of millions of images. It is based on dividing the Kd-Tree into a "root subtree" that resides on a root machine, and several "leaf subtrees", each residing on a leaf machine. The root machine handles incoming queries and farms out feature matching to an appropriate small subset of the leaf machines. Our implementation employs the MapReduce architecture to efficiently build and distribute the Kd-Tree for millions of images. It can run on thousands of machines, and provides orders of magnitude more throughput than the state-of-the-art, with better recognition performance. We show experiments with up to 100 million images running on 2048 machines, with run time of a fraction of a second for each query image.

show abstract

Automatic Leaf Recognition from a Big Hierarchical Image Database

Wang

Zhang

et al. 2015

Int. J. Intell. Syst.

View full text Add to dashboard Cite

Automatic plant recognition has become a research focus and received more and more attentions recently. However, existing methods usually only focused on leaf recognition from small databases that usually only contain no more than hundreds of species, and none of them reported a stable performance in either recognition accuracy or recognition speed when compared with a big image database. In this paper, we present a novel method for leaf recognition from a big hierarchical image database. Unlike the existing approaches, our method combines the textural gradient histogram with the shape context to form a more distinctive feature for leaf recognition. To achieve efficient leaf image retrieval, we divided the big database into a set of subsets based on mean‐shift clustering on the extracted features and build hierarchical k‐dimensional trees (KD‐trees) to index each cluster in parallel. Finally, the proposed parallel indexing and searching schemes are implemented with MapReduce architectures. Our method is evaluated with extensive experiments on different databases with different sizes. Comparisons to state‐of‐the‐art techniques were also conducted to validate the proposed method. Both visual results and statistical results are shown to demonstrate its effectiveness.

show abstract

Indexing in large scale image collections: Scaling properties and benchmark

Cited by 41 publications

References 20 publications

Mobile Tour Planning Using Landmark Photo Matching and Intelligent Character Recognition

Mobile Tour Planning Using Landmark Photo Matching and Intelligent Character Recognition

Distributed Kd-Trees for Ultra Large Scale Object Recognition

Automatic Leaf Recognition from a Big Hierarchical Image Database

Contact Info

Product

Resources

About