Image Retrieval

This software can find images in an image database based on the content of the images. This means, the first step is to index a collection of images. Subsequently, using a query image, the image collection can be searched retrieving images which show similar objects or scenes.* Build your own image database * Query your database for similar images in a matter of seconds * No internet access needed, your images remain on your computer

1. The databases should be used only for comparing algorithms, which can be considered as ‘fair use’ of the images and our metadata. You should not redistribute the images. You should reference to
   • Jia Li, James Z. Wang, “Automatic linguistic indexing of pictures by a statistical modeling approach,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 9, pp. 1075-1088, 2003. (download)
   • James Z. Wang, Jia Li, Gio Wiederhold, “SIMPLIcity: Semantics-sensitive Integrated Matching for Picture LIbraries,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol 23, no.9, pp. 947-963, 2001. (download)
2. Download SIMPLIcity Software Package:
   If you are a government agency, an education institution, or a non-profit organization, we may offer you a FREE license of the SIMPLIcity system to run on LINUX or Solaris. Please contact Prof. James Wang by email to discuss details. At the moment, the C source code is not ready for public download. If you are commercial and would like to use SIMPLIcity, let us know and we will try to arrange to let you use.

   The GRire library is a light-weight but complete framework for implementing CBIR (Content Based Image Retrieval) methods. Currently, the main objective of the project is the implementation of BOVW (Bag of Visual Words) methods so, apart from the image analysis tools, it offers methods from the field of IR (Information Retrieval), e.g. weighting models such as SMART and Okapi, adjusted to meet the Image Retrieval perspective.

   The purpose of the project is to help developers create and distribute their methods and test the performance of their BOVW systems in actual databases with minimum effort and without having to deal with every aspect of the model.

   Please cite:
   Lazaros T. Tsochatzidis, Chryssanthi Iakovidou, Savvas A. Chatzichristofis, and Yiannis S. Boutalis. 2013. Golden retriever: a Java based open source image retrieval engine. In Proceedings of the 21st ACM International Conference on Multimedia (MM ’13).

   Features

   • Variety of feature extractors, clustering algorithms and weighting schemes.
   • Easy-to-use Indexing and Querying procedures
   • Very easily extensible with plugin system
   • Fast and efficient disk database
   • Frontent GUI using JavaFX

   Content-Based Image Retrieval (CBIR) systems have recently emerged as one of the most promising and best image retrieval paradigms. To pacify the semantic gap associated with CBIR systems, the Bag of Visual Words (BoVW) techniques are now increasingly used. However, existing BoVW techniques fail to capture the location information of visual words effectively. This paper proposes an unsupervised Content-Based Medical Image Retrieval (CBMIR) framework based on the spatial matching of the visual words. The proposed method efficiently computes the spatial similarity of visual words using a novel similarity measure called the Skip Similarity Index. Experiments on three large medical datasets reveal promising results. The location-based correlation of visual words assists in more accurate and efficient retrieval of anatomically diverse and multimodal medical images than the state-of-the-art CBMIR systems.

   LIRe (Lucene Image Retrieval) is a light weight open source Java library for content based image retrieval. It provides common and state of the art global image features and offers means for indexing and retrieval. Due to the fact that it is based on a light weight embedded text search engine, it can be integrated easily in applications without relying on a database server.

   In this tutorial, you will learn how to use convolutional autoencoders to create a Content-based Image Retrieval system (i.e., image search engine) using Keras and TensorFlow.

   The COREL Database for Content based Image Retrieval

   We manually divided 10,800 images from the Corel Photo Gallery [6] into 80 concept groups, e.g., autumn, aviation, bonsai, castle, cloud, dog, elephant, iceberg, primates, ship, stalactite, steam-engine, tiger, train, and waterfall. Figure 6 shows some example images. We reorganised the Corel Photo Gallery, because 1) many images with similar concepts were not in the same group and 2) some images with different semantic contents were in the same group in the original database. In the reorganised database, each group includes more than 100 images and the images in the group are category-homogeneous. These concept groups were used in the evaluation of the results of our algorithms [1-5].img(Rummager) brings into effect a number of new as well as state of the art descriptors. The application can execute an image search based on a query image, either from XML-based index files, or directly from a folder containing image files, extracting the comparison features in real time. In addition the img(Rummager) application can execute a hybrid search of images from the application server, combining keyword information and visual similarity. img(Rummager) supports easy retrieval evaluation based on the normalized modified retrieval rank (NMRR), Mean Normalized Retrieval Order and average precision (AP). You can also save the retrieval results in trec_eval format. The Img(Rummager) application is programmed in C# and requires a Windows XP+ Operating System with a 3.5 .NET Framework. This is a portable application that does not require installation. The index files it creates can be stored in any part of the user’s hard disk, or even on a local network. They are normal XML files where documents consisting of fields each have a name and a value. Img(Rummager) is developed in the Automatic Control Systems & Robotics Laboratory at the Democritus University of Thrace-Greece.