The role of context in image annotation and recommendation

With the rise of smart phones, lifelogging devices (e.g. Google Glass) and popularity of image sharing websites (e.g. Flickr), users are capturing and sharing every aspect of their life online producing a wealth of visual content. Of these uploaded images, the majority are poorly annotated or exist in complete semantic isolation making the process of building retrieval systems difficult as one must firstly understand the meaning of an image in order to retrieve it. To alleviate this problem, many image sharing websites offer manual annotation tools which allow the user to “tag” their photos, however, these techniques are laborious and as a result have been poorly adopted; Sigurbjörnsson and van Zwol (2008) showed that 64% of images uploaded to Flickr are annotated with < 4 tags. Due to this, an entire body of research has focused on the automatic annotation of images (Hanbury, 2008; Smeulders et al., 2000; Zhang et al., 2012a) where one attempts to bridge the semantic gap between an image’s appearance and meaning e.g. the objects present. Despite two decades of research the semantic gap still largely exists and as a result automatic annotation models often offer unsatisfactory performance for industrial implementation. Further, these techniques can only annotate what they see, thus ignoring the “bigger picture” surrounding an image (e.g. its location, the event, the people present etc). Much work has therefore focused on building photo tag recommendation (PTR) methods which aid the user in the annotation process by suggesting tags related to those already present. These works have mainly focused on computing relationships between tags based on historical images e.g. that NY and timessquare co-exist in many images and are therefore highly correlated. However, tags are inherently noisy, sparse and ill-defined often resulting in poor PTR accuracy e.g. does NY refer to New York or New Year? This thesis proposes the exploitation of an image’s context which, unlike textual evidences, is always present, in order to alleviate this ambiguity in the tag recommendation process. Specifically we exploit the “what, who, where, when and how” of the image capture process in order to complement textual evidences in various photo tag recommendation and retrieval scenarios. In part II, we combine text, content-based (e.g. # of faces present) and contextual (e.g. day-of-the-week taken) signals for tag recommendation purposes, achieving up to a 75% improvement to precision@5 in comparison to a text-only TF-IDF baseline. We then consider external knowledge sources (i.e. Wikipedia & Twitter) as an alternative to (slower moving) Flickr in order to build recommendation models on, showing that similar accuracy could be achieved on these faster moving, yet entirely textual, datasets. In part II, we also highlight the merits of diversifying tag recommendation lists before discussing at length various problems with existing automatic image annotation and photo tag recommendation evaluation collections. In part III, we propose three new image retrieval scenarios, namely “visual event summarisation”, “image popularity prediction” and “lifelog summarisation”. In the first scenario, we attempt to produce a rank of relevant and diverse images for various news events by (i) removing irrelevant images such memes and visual duplicates (ii) before semantically clustering images based on the tweets in which they were originally posted. Using this approach, we were able to achieve over 50% precision for images in the top 5 ranks. In the second retrieval scenario, we show that by combining contextual and content-based features from images, we are able to predict if it will become “popular” (or not) with 74% accuracy, using an SVM classifier. Finally, in chapter 9 we employ blur detection and perceptual-hash clustering in order to remove noisy images from lifelogs, before combining visual and geo-temporal signals in order to capture a user’s “key moments” within their day. We believe that the results of this thesis show an important step towards building effective image retrieval models when there lacks sufficient textual content (i.e. a cold start).

Image summarisation: human action description from static images

Dissertação de Mestrado, Processamento de Linguagem Natural e Indústrias da Língua, Faculdade de Ciências Humanas e Sociais, Universidade do Algarve, 2014

Representing image captions as concept graphs using semantic information

Conceptual interpretation of languages has gathered peak interest in the world of artificial intelligence. The challenge in modeling various complications involved in a language is the main motivation behind our work. Our main focus in this work is to develop conceptual graphical representation for image captions. We have used discourse representation structure to gain semantic information which is further modeled into a graphical structure. The effectiveness of the model is evaluated by a caption based image retrieval system. The image retrieval is performed by computing subgraph based similarity measures. Best retrievals were given an average rating of . ± . out of 4 by a group of 25 human judges. The experiments were performed on a subset of the SBU Captioned Photo Dataset. This purpose of this work is to establish the cognitive sensibility of the approach to caption representations

Representing image captions as concept graphs using semantic information

Conceptual interpretation of languages has gathered peak interest in the world of artificial intelligence. The challenge in modeling various complications involved in a language is the main motivation behind our work. Our main focus in this work is to develop conceptual graphical representation for image captions. We have used discourse representation structure to gain semantic information which is further modeled into a graphical structure. The effectiveness of the model is evaluated by a caption based image retrieval system. The image retrieval is performed by computing subgraph based similarity measures. Best retrievals were given an average rating of . ± . out of 4 by a group of 25 human judges. The experiments were performed on a subset of the SBU Captioned Photo Dataset. This purpose of this work is to establish the cognitive sensibility of the approach to caption representations.

High-level concept annotation using ontology and probabilistic inference

Image annotation is a significant step towards semantic based image retrieval. Ontology is a popular approach for semantic representation and has been intensively studied for multimedia analysis. However, relations among concepts are seldom used to extract higher-level semantics. Moreover, the ontology inference is often crisp. This paper aims to enable sophisticated semantic querying of images, and thus contributes to 1) an ontology framework to contain both visual and contextual knowledge, and 2) a probabilistic inference approach to reason the high-level concepts based on different sources of information. The experiment on a natural scene database from LabelMe database shows encouraging results.

A neural network based CBIR system using STI features and relevance feedback

Multimedia mining primarily involves, information analysis and retrieval based on implicit knowledge. The ever increasing digital image databases on the Internet has created a need for using multimedia mining on these databases for effective and efficient retrieval of images. Contents of an image can be expressed in different features such as Shape, Texture and Intensity-distribution(STI). Content Based Image Retrieval(CBIR) is an efficient retrieval of relevant images from large databases based on features extracted from the image. Most of the existing systems either concentrate on a single representation of all features or linear combination of these features. The paper proposes a CBIR System named STIRF (Shape, Texture, Intensity-distribution with Relevance Feedback) that uses a neural network for nonlinear combination of the heterogenous STI features. Further the system is self-adaptable to different applications and users based upon relevance feedback. Prior to retrieval of relevant images, each feature is first clustered independent of the other in its own space and this helps in matching of similar images. Testing the system on a database of images with varied contents and intensive backgrounds showed good results with most relevant images being retrieved for a image query. The system showed better and more robust performance compared to existing CBIR systems

Contributions to the analysis and segmentation of remote sensing hyperspectral images

142 p.

Incremental Linear Discriminant Analysis Using Sufficient Spanning Sets and Its Applications

This paper presents an incremental learning solution for Linear Discriminant Analysis (LDA) and its applications to object recognition problems. We apply the sufficient spanning set approximation in three steps i.e. update for the total scatter matrix, between-class scatter matrix and the projected data matrix, which leads an online solution which closely agrees with the batch solution in accuracy while significantly reducing the computational complexity. The algorithm yields an efficient solution to incremental LDA even when the number of classes as well as the set size is large. The incremental LDA method has been also shown useful for semi-supervised online learning. Label propagation is done by integrating the incremental LDA into an EM framework. The method has been demonstrated in the task of merging large datasets which were collected during MPEG standardization for face image retrieval, face authentication using the BANCA dataset, and object categorisation using the Caltech101 dataset. © 2010 Springer Science+Business Media, LLC.

Coarse-level object recognition using interlevel products of complex wavelets

This paper introduces the Interlevel Product (ILP) which is a transform based upon the Dual-Tree Complex Wavelet. Coefficients of the ILP have complex values whose magnitudes indicate the amplitude of multilevel features, and whose phases indicate the nature of these features (e.g. ridges vs. edges). In particular, the phases of ILP coefficients are approximately invariant to small shifts in the original images. We accordingly introduce this transform as a solution to coarse scale template matching, where alignment concerns between decimation of a target and decimation of a larger search image can be mitigated, and computational efficiency can be maintained. Furthermore, template matching with ILP coefficients can provide several intuitive "near-matches" that may be of interest in image retrieval applications. © 2005 IEEE.

Shape Recognition of Linear Construction Entities from Construction Site Images

The capability to automatically identify shapes, objects and materials from the image content through direct and indirect methodologies has enabled the development of several civil engineering related applications that assist in the design, construction and maintenance of construction projects. This capability is a product of the technological breakthroughs in the area of Image Processing that has allowed for the development of a large number of digital imaging applications in all industries. In this paper, an automated and content based shape recognition model is presented. This model was devised to enhance the recognition capabilities of our existing material based image retrieval model. The shape recognition model is based on clustering techniques, and specifically those related with material and object segmentation. The model detects the borders of each previously detected material depicted in the image, examines its linearity (length/width ratio) and detects its orientation (horizontal/vertical). The results emonstrate the suitability of this model for construction site image retrieval purposes and reveal the capability of existing clustering technologies to accurately identify the shape of a wealth of materials from construction site images.

基于海底资源丰度的图像检索

提出了一种基于丰度的图像检索方法 ,在小波变换的基础上定义了边缘平均重复度来描述丰度 ,由此构成相似性度量的特征空间 .依据这一研究结果 ,可快速对海底资源图像库进行丰度意义下的检索并形成资源分布图 .最后 ,给出了对海底资源图像库进行检索的实验结果

Fast Contour Matching Using Approximate Earth Mover's Distance

Weighted graph matching is a good way to align a pair of shapes represented by a set of descriptive local features; the set of correspondences produced by the minimum cost of matching features from one shape to the features of the other often reveals how similar the two shapes are. However, due to the complexity of computing the exact minimum cost matching, previous algorithms could only run efficiently when using a limited number of features per shape, and could not scale to perform retrievals from large databases. We present a contour matching algorithm that quickly computes the minimum weight matching between sets of descriptive local features using a recently introduced low-distortion embedding of the Earth Mover's Distance (EMD) into a normed space. Given a novel embedded contour, the nearest neighbors in a database of embedded contours are retrieved in sublinear time via approximate nearest neighbors search. We demonstrate our shape matching method on databases of 10,000 images of human figures and 60,000 images of handwritten digits.

Color Region Grouping and Shape Recognition with Deformable Models

A new deformable shape-based method for color region segmentation is described. The method includes two stages: over-segmentation using a traditional color region segmentation algorithm, followed by deformable model-based region merging via grouping and hypothesis selection. During the second stage, region merging and object identification are executed simultaneously. A statistical shape model is used to estimate the likelihood of region groupings and model hypotheses. The prior distribution on deformation parameters is precomputed using principal component analysis over a training set of region groupings. Once trained, the system autonomously segments deformed shapes from the background, while not merging them with similarly colored adjacent objects. Furthermore, the recovered parametric shape model can be used directly in object recognition and comparison. Experiments in segmentation and image retrieval are reported.

Étude sur l’influence du vocabulaire utilisé pour l’indexation des images en contexte de repérage multilingue

Depuis quelques années, Internet est devenu un média incontournable pour la diffusion de ressources multilingues. Cependant, les différences linguistiques constituent souvent un obstacle majeur aux échanges de documents scientifiques, culturels, pédagogiques et commerciaux. En plus de cette diversité linguistique, on constate le développement croissant de bases de données et de collections composées de différents types de documents textuels ou multimédias, ce qui complexifie également le processus de repérage documentaire. En général, on considère l’image comme « libre » au point de vue linguistique. Toutefois, l’indexation en vocabulaire contrôlé ou libre (non contrôlé) confère à l’image un statut linguistique au même titre que tout document textuel, ce qui peut avoir une incidence sur le repérage. Le but de notre recherche est de vérifier l’existence de différences entre les caractéristiques de deux approches d’indexation pour les images ordinaires représentant des objets de la vie quotidienne, en vocabulaire contrôlé et en vocabulaire libre, et entre les résultats obtenus au moment de leur repérage. Cette étude suppose que les deux approches d’indexation présentent des caractéristiques communes, mais également des différences pouvant influencer le repérage de l’image. Cette recherche permet de vérifier si l’une ou l’autre de ces approches d’indexation surclasse l’autre, en termes d’efficacité, d’efficience et de satisfaction du chercheur d’images, en contexte de repérage multilingue. Afin d’atteindre le but fixé par cette recherche, deux objectifs spécifiques sont définis : identifier les caractéristiques de chacune des deux approches d’indexation de l’image ordinaire représentant des objets de la vie quotidienne pouvant influencer le repérage, en contexte multilingue et exposer les différences sur le plan de l’efficacité, de l’efficience et de la satisfaction du chercheur d’images à repérer des images ordinaires représentant des objets de la vie quotidienne indexées à l’aide d’approches offrant des caractéristiques variées, en contexte multilingue. Trois modes de collecte des données sont employés : l’analyse des termes utilisés pour l’indexation des images, la simulation du repérage d’un ensemble d’images indexées selon chacune des formes d’indexation à l’étude réalisée auprès de soixante répondants, et le questionnaire administré aux participants pendant et après la simulation du repérage. Quatre mesures sont définies pour cette recherche : l’efficacité du repérage d’images, mesurée par le taux de succès du repérage calculé à l’aide du nombre d’images repérées; l’efficience temporelle, mesurée par le temps, en secondes, utilisé par image repérée; l’efficience humaine, mesurée par l’effort humain, en nombre de requêtes formulées par image repérée et la satisfaction du chercheur d’images, mesurée par son autoévaluation suite à chaque tâche de repérage effectuée. Cette recherche montre que sur le plan de l’indexation de l’image ordinaire représentant des objets de la vie quotidienne, les approches d’indexation étudiées diffèrent fondamentalement l’une de l’autre, sur le plan terminologique, perceptuel et structurel. En outre, l’analyse des caractéristiques des deux approches d’indexation révèle que si la langue d’indexation est modifiée, les caractéristiques varient peu au sein d’une même approche d’indexation. Finalement, cette recherche souligne que les deux approches d’indexation à l’étude offrent une performance de repérage des images ordinaires représentant des objets de la vie quotidienne différente sur le plan de l’efficacité, de l’efficience et de la satisfaction du chercheur d’images, selon l’approche et la langue utilisées pour l’indexation.

Grey Level Co-Occurrence Matrices: Generalisation And Some New Features

Grey Level Co-occurrence Matrices (GLCM) are one of the earliest techniques used for image texture analysis. In this paper we defined a new feature called trace extracted from the GLCM and its implications in texture analysis are discussed in the context of Content Based Image Retrieval (CBIR). The theoretical extension of GLCM to n-dimensional gray scale images are also discussed. The results indicate that trace features outperform Haralick features when applied to CBIR.