The mosaic test:benchmarking colour-based image retrieval systems using image mosaics

Evaluation and benchmarking in content-based image retrieval has always been a somewhat neglected research area, making it difficult to judge the efficacy of many presented approaches. In this paper we investigate the issue of benchmarking for colour-based image retrieval systems, which enable users to retrieve images from a database based on lowlevel colour content alone. We argue that current image retrieval evaluation methods are not suited to benchmarking colour-based image retrieval systems, due in main to not allowing users to reflect upon the suitability of retrieved images within the context of a creative project and their reliance on highly subjective ground-truths. As a solution to these issues, the research presented here introduces the Mosaic Test for evaluating colour-based image retrieval systems, in which test-users are asked to create an image mosaic of a predetermined target image, using the colour-based image retrieval system that is being evaluated. We report on our findings from a user study which suggests that the Mosaic Test overcomes the major drawbacks associated with existing image retrieval evaluation methods, by enabling users to reflect upon image selections and automatically measuring image relevance in a way that correlates with the perception of many human assessors. We therefore propose that the Mosaic Test be adopted as a standardised benchmark for evaluating and comparing colour-based image retrieval systems.

Exploring the effectiveness of similarity-based visualisations for colour-based image retrieval

In April 2009, Google Images added a filter for narrowing search results by colour. Several other systems for searching image databases by colour were also released around this time. These colour-based image retrieval systems enable users to search image databases either by selecting colours from a graphical palette (i.e., query-by-colour), by drawing a representation of the colour layout sought (i.e., query-by-sketch), or both. It was comments left by readers of online articles describing these colour-based image retrieval systems that provided us with the inspiration for this research. We were surprised to learn that the underlying query-based technology used in colour-based image retrieval systems today remains remarkably similar to that of systems developed nearly two decades ago. Discovering this ageing retrieval approach, as well as uncovering a large user demographic requiring image search by colour, made us eager to research more effective approaches for colour-based image retrieval. In this thesis, we detail two user studies designed to compare the effectiveness of systems adopting similarity-based visualisations, query-based approaches, or a combination of both, for colour-based image retrieval. In contrast to query-based approaches, similarity-based visualisations display and arrange database images so that images with similar content are located closer together on screen than images with dissimilar content. This removes the need for queries, as users can instead visually explore the database using interactive navigation tools to retrieve images from the database. As we found existing evaluation approaches to be unreliable, we describe how we assessed and compared systems adopting similarity-based visualisations, query-based approaches, or both, meaningfully and systematically using our Mosaic Test - a user-based evaluation approach in which evaluation study participants complete an image mosaic of a predetermined target image using the colour-based image retrieval system under evaluation.

The mosaic test:measuring the effectiveness of colour-based image retrieval

A variety of content-based image retrieval systems exist which enable users to perform image retrieval based on colour content - i.e., colour-based image retrieval. For the production of media for use in television and film, colour-based image retrieval is useful for retrieving specifically coloured animations, graphics or videos from large databases (by comparing user queries to the colour content of extracted key frames). It is also useful to graphic artists creating realistic computer-generated imagery (CGI). Unfortunately, current methods for evaluating colour-based image retrieval systems have 2 major drawbacks. Firstly, the relevance of images retrieved during the task cannot be measured reliably. Secondly, existing methods do not account for the creative design activity known as reflection-in-action. Consequently, the development and application of novel and potentially more effective colour-based image retrieval approaches, better supporting the large number of users creating media for use in television and film productions, is not possible as their efficacy cannot be reliably measured and compared to existing technologies. As a solution to the problem, this paper introduces the Mosaic Test. The Mosaic Test is a user-based evaluation approach in which participants complete an image mosaic of a predetermined target image, using the colour-based image retrieval system that is being evaluated. In this paper, we introduce the Mosaic Test and report on a user evaluation. The findings of the study reveal that the Mosaic Test overcomes the 2 major drawbacks associated with existing evaluation methods and does not require expert participants. © 2012 Springer Science+Business Media, LLC.

An information foraging theory based user study of an adaptive user interaction framework for content-based image retrieval

This paper presents the design and results of a task-based user study, based on Information Foraging Theory, on a novel user interaction framework - uInteract - for content-based image retrieval (CBIR). The framework includes a four-factor user interaction model and an interactive interface. The user study involves three focused evaluations, 12 simulated real life search tasks with different complexity levels, 12 comparative systems and 50 subjects. Information Foraging Theory is applied to the user study design and the quantitative data analysis. The systematic findings have not only shown how effective and easy to use the uInteract framework is, but also illustrate the value of Information Foraging Theory for interpreting user interaction with CBIR. © 2011 Springer-Verlag Berlin Heidelberg.

Applying Information Foraging Theory to understand user interaction with content-based image retrieval

The paper proposes an ISE (Information goal, Search strategy, Evaluation threshold) user classification model based on Information Foraging Theory for understanding user interaction with content-based image retrieval (CBIR). The proposed model is verified by a multiple linear regression analysis based on 50 users' interaction features collected from a task-based user study of interactive CBIR systems. To our best knowledge, this is the first principled user classification model in CBIR verified by a formal and systematic qualitative analysis of extensive user interaction data. Copyright 2010 ACM.

A four-factor user interaction model for content-based image retrieval

In order to bridge the “Semantic gap”, a number of relevance feedback (RF) mechanisms have been applied to content-based image retrieval (CBIR). However current RF techniques in most existing CBIR systems still lack satisfactory user interaction although some work has been done to improve the interaction as well as the search accuracy. In this paper, we propose a four-factor user interaction model and investigate its effects on CBIR by an empirical evaluation. Whilst the model was developed for our research purposes, we believe the model could be adapted to any content-based search system.

Enabling effective user interactions in content-based image retrieval

This paper presents an interactive content-based image retrieval framework—uInteract, for delivering a novel four-factor user interaction model visually. The four-factor user interaction model is an interactive relevance feedback mechanism that we proposed, aiming to improve the interaction between users and the CBIR system and in turn users overall search experience. In this paper, we present how the framework is developed to deliver the four-factor user interaction model, and how the visual interface is designed to support user interaction activities. From our preliminary user evaluation result on the ease of use and usefulness of the proposed framework, we have learnt what the users like about the framework and the aspects we could improve in future studies. Whilst the framework is developed for our research purposes, we believe the functionalities could be adapted to any content-based image search framework.

Comparing dissimilarity measures for content-based image retrieval

Dissimilarity measurement plays a crucial role in content-based image retrieval, where data objects and queries are represented as vectors in high-dimensional content feature spaces. Given the large number of dissimilarity measures that exist in many fields, a crucial research question arises: Is there a dependency, if yes, what is the dependency, of a dissimilarity measure’s retrieval performance, on different feature spaces? In this paper, we summarize fourteen core dissimilarity measures and classify them into three categories. A systematic performance comparison is carried out to test the effectiveness of these dissimilarity measures with six different feature spaces and some of their combinations on the Corel image collection. From our experimental results, we have drawn a number of observations and insights on dissimilarity measurement in content-based image retrieval, which will lay a foundation for developing more effective image search technologies.

MPEG-7 Based Image Retrieval on the World Wide Web

Due to the rapid growth of the number of digital media elements like image, video, audio, graphics on Internet, there is an increasing demand for effective search and retrieval techniques. Recently, many search engines have made image search as an option like Google, AlltheWeb, AltaVista, Freenet. In addition to this, Ditto, Picsearch, can search only the images on Internet. There are also other domain specific search engines available for graphics and clip art, audio, video, educational images, artwork, stock photos, science and nature [www.faganfinder.com/img]. These entire search engines are directory based. They crawls the entire Internet and index all the images in certain categories. They do not display the images in any particular order with respect to the time and context. With the availability of MPEG-7, a standard for describing multimedia content, it is now possible to store the images with its metadata in a structured format. This helps in searching and retrieving the images. The MPEG-7 standard uses XML to describe the content of multimedia information objects. These objects will have metadata information in the form of MPEG-7 or any other similar format associated with them. It can be used in different ways to search the objects. In this paper we propose a system, which can do content based image retrieval on the World Wide Web. It displays the result in user-defined order.

Distance Matrix Approach to Content Image Retrieval

As the volume of image data and the need of using it in various applications is growing significantly in the last days it brings a necessity of retrieval efficiency and effectiveness. Unfortunately, existing indexing methods are not applicable to a wide range of problem-oriented fields due to their operating time limitations and strong dependency on the traditional descriptors extracted from the image. To meet higher requirements, a novel distance-based indexing method for region-based image retrieval has been proposed and investigated. The method creates premises for considering embedded partitions of images to carry out the search with different refinement or roughening level and so to seek the image meaningful content.

Content-Based Image Retrieval for Computer Tomography Images Using Wavelet Descriptors

An approach to building a CBIR-system for searching computer tomography images using the methods of wavelet-analysis is presented in this work. The index vectors are constructed on the basis of the local features of the image and on their positions. The purpose of the proposed system is to extract visually similar data from the individual personal records and from analogous analysis of other patients.

Image retrieval on the Honeycomb Image Browser

Efficient and effective approaches of dealing with the vast amount of visual information available nowadays are highly sought after. This is particularly the case for image collections, both personal and commercial. Due to the magnitude of these ever expanding image repositories, annotation of all images images is infeasible, and search in such an image collection therefore becomes inherently difficult. Although content-based image retrieval techniques have shown much potential, such approaches also suffer from various problems making it difficult to adopt them in practice. In this paper, we follow a different approach, namely that of browsing image databases for image retrieval. In our Honeycomb Image Browser, large image databases are visualised on a hexagonal lattice with image thumbnails occupying hexagons. Arranged in a space filling manner, visually similar images are located close together enabling large image datasets to be navigated in a hierarchical manner. Various browsing tools are incorporated to allow for interactive exploration of the database. Experimental results confirm that our approach affords efficient image retrieval. © 2010 IEEE.

Leveraging Multiple Features for Image Retrieval and Matching

The goal of image retrieval and matching is to find and locate object instances in images from a large-scale image database. While visual features are abundant, how to combine them to improve performance by individual features remains a challenging task. In this work, we focus on leveraging multiple features for accurate and efficient image retrieval and matching. We first propose two graph-based approaches to rerank initially retrieved images for generic image retrieval. In the graph, vertices are images while edges are similarities between image pairs. Our first approach employs a mixture Markov model based on a random walk model on multiple graphs to fuse graphs. We introduce a probabilistic model to compute the importance of each feature for graph fusion under a naive Bayesian formulation, which requires statistics of similarities from a manually labeled dataset containing irrelevant images. To reduce human labeling, we further propose a fully unsupervised reranking algorithm based on a submodular objective function that can be efficiently optimized by greedy algorithm. By maximizing an information gain term over the graph, our submodular function favors a subset of database images that are similar to query images and resemble each other. The function also exploits the rank relationships of images from multiple ranked lists obtained by different features. We then study a more well-defined application, person re-identification, where the database contains labeled images of human bodies captured by multiple cameras. Re-identifications from multiple cameras are regarded as related tasks to exploit shared information. We apply a novel multi-task learning algorithm using both low level features and attributes. A low rank attribute embedding is joint learned within the multi-task learning formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered. To locate objects in images, we design an object detector based on object proposals and deep convolutional neural networks (CNN) in view of the emergence of deep networks. We improve a Fast RCNN framework and investigate two new strategies to detect objects accurately and efficiently: scale-dependent pooling (SDP) and cascaded rejection classifiers (CRC). The SDP improves detection accuracy by exploiting appropriate convolutional features depending on the scale of input object proposals. The CRC effectively utilizes convolutional features and greatly eliminates negative proposals in a cascaded manner, while maintaining a high recall for true objects. The two strategies together improve the detection accuracy and reduce the computational cost.

Learning Binary Code Representations for Effective and Efficient Image Retrieval

The size of online image datasets is constantly increasing. Considering an image dataset with millions of images, image retrieval becomes a seemingly intractable problem for exhaustive similarity search algorithms. Hashing methods, which encodes high-dimensional descriptors into compact binary strings, have become very popular because of their high efficiency in search and storage capacity. In the first part, we propose a multimodal retrieval method based on latent feature models. The procedure consists of a nonparametric Bayesian framework for learning underlying semantically meaningful abstract features in a multimodal dataset, a probabilistic retrieval model that allows cross-modal queries and an extension model for relevance feedback. In the second part, we focus on supervised hashing with kernels. We describe a flexible hashing procedure that treats binary codes and pairwise semantic similarity as latent and observed variables, respectively, in a probabilistic model based on Gaussian processes for binary classification. We present a scalable inference algorithm with the sparse pseudo-input Gaussian process (SPGP) model and distributed computing. In the last part, we define an incremental hashing strategy for dynamic databases where new images are added to the databases frequently. The method is based on a two-stage classification framework using binary and multi-class SVMs. The proposed method also enforces balance in binary codes by an imbalance penalty to obtain higher quality binary codes. We learn hash functions by an efficient algorithm where the NP-hard problem of finding optimal binary codes is solved via cyclic coordinate descent and SVMs are trained in a parallelized incremental manner. For modifications like adding images from an unseen class, we propose an incremental procedure for effective and efficient updates to the previous hash functions. Experiments on three large-scale image datasets demonstrate that the incremental strategy is capable of efficiently updating hash functions to the same retrieval performance as hashing from scratch.