Task-based annotation and retrieval for image information management

Continuing advances in digital image capture and storage are resulting in a proliferation of imagery and associated problems of information overload in image domains. In this work we present a framework that supports image management using an interactive approach that captures and reuses task-based contextual information. Our framework models the relationship between images and domain tasks they support by monitoring the interactive manipulation and annotation of task-relevant imagery. During image analysis, interactions are captured and a task context is dynamically constructed so that human expertise, proficiency and knowledge can be leveraged to support other users in carrying out similar domain tasks using case-based reasoning techniques. In this article we present our framework for capturing task context and describe how we have implemented the framework as two image retrieval applications in the geo-spatial and medical domains. We present an evaluation that tests the efficiency of our algorithms for retrieving image context information and the effectiveness of the framework for carrying out goal-directed image tasks. © 2010 Springer Science+Business Media, LLC.

Gesture based interface for image annotation

Dissertação apresentada para obtenção do Grau de Mestre em Engenharia Informática pela Universidade Nova de Lisboa, Faculdade de Ciências e Tecnologia

The life sciences Global Image Database (GID)

Although a vast amount of life sciences data is generated in the form of images, most scientists still store images on extremely diverse and often incompatible storage media, without any type of metadata structure, and thus with no standard facility with which to conduct searches or analyses. Here we present a solution to unlock the value of scientific images. The Global Image Database (GID) is a web-based (http://www.g wer.ch/qv/gid/gid.htm) structured central repository for scientific annotated images. The GID was designed to manage images from a wide spectrum of imaging domains ranging from microscopy to automated screening. The annotations in the GID define the source experiment of the images by describing who the authors of the experiment are, when the images were created, the biological origin of the experimental sample and how the sample was processed for visualization. A collection of experimental imaging protocols provides details of the sample preparation, and labeling, or visualization procedures. In addition, the entries in the GID reference these imaging protocols with the probe sequences or antibody names used in labeling experiments. The GID annotations are searchable by field or globally. The query results are first shown as image thumbnail previews, enabling quick browsing prior to original-sized annotated image retrieval. The development of the GID continues, aiming at facilitating the management and exchange of image data in the scientific community, and at creating new query tools for mining image data.

Application of Text Summarization techniques to the Geographical Information Retrieval task

Automatic Text Summarization has been shown to be useful for Natural Language Processing tasks such as Question Answering or Text Classification and other related fields of computer science such as Information Retrieval. Since Geographical Information Retrieval can be considered as an extension of the Information Retrieval field, the generation of summaries could be integrated into these systems by acting as an intermediate stage, with the purpose of reducing the document length. In this manner, the access time for information searching will be improved, while at the same time relevant documents will be also retrieved. Therefore, in this paper we propose the generation of two types of summaries (generic and geographical) applying several compression rates in order to evaluate their effectiveness in the Geographical Information Retrieval task. The evaluation has been carried out using GeoCLEF as evaluation framework and following an Information Retrieval perspective without considering the geo-reranking phase commonly used in these systems. Although single-document summarization has not performed well in general, the slight improvements obtained for some types of the proposed summaries, particularly for those based on geographical information, made us believe that the integration of Text Summarization with Geographical Information Retrieval may be beneficial, and consequently, the experimental set-up developed in this research work serves as a basis for further investigations in this field.

ICICLE: A semantic-based retrieval system for WWW images

In this paper, we present ICICLE (Image ChainNet and Incremental Clustering Engine), a prototype system that we have developed to efficiently and effectively retrieve WWW images based on image semantics. ICICLE has two distinguishing features. First, it employs a novel image representation model called Weight ChainNet to capture the semantics of the image content. A new formula, called list space model, for computing semantic similarities is also introduced. Second, to speed up retrieval, ICICLE employs an incremental clustering mechanism, ICC (Incremental Clustering on ChainNet), to cluster images with similar semantics into the same partition. Each cluster has a summary representative and all clusters' representatives are further summarized into a balanced and full binary tree structure. We conducted an extensive performance study to evaluate ICICLE. Compared with some recently proposed methods, our results show that ICICLE provides better recall and precision. Our clustering technique ICC facilitates speedy retrieval of images without sacrificing recall and precision significantly.

Using the Amazon metric to construct an image database based on what people do, not what they say

Current image database metadata schemas require users to adopt a specific text-based vocabulary. Text-based metadata is good for searching but not for browsing. Existing image-based search facilities, on the other hand, are highly specialised and so suffer similar problems. Wexelblat's semantic dimensional spatial visualisation schemas go some way towards addressing this problem by making both searching and browsing more accessible to the user in a single interface. But the question of how and what initial metadata to enter a database remains. Different people see different things in an image and will organise a collection in equally diverse ways. However, we can find some similarity across groups of users regardless of their reasoning. For example, a search on Amazon.com returns other products also, based on an averaging of how users navigate the database. In this paper, we report on applying this concept to a set of images for which we have visualised them using traditional methods and the Amazon.com method. We report on the findings of this comparative investigation in a case study setting involving a group of randomly selected participants. We conclude with the recommendation that in combination, the traditional and averaging methods would provide an enhancement to current database visualisation, searching, and browsing facilities.

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, MAGIC AND IMAGINATION: CHALLENGES TO THE ANTHROPOLOGICAL TEXT

What different forms of engagement do image and text allow the spectator/reader? We know that text and image communicate, and that all communication depends on a relationship between those who communicate. The objective of this text is therefore to understand the new possibilities available to an anthropology of the expression of knowledge that makes use of images, such as photographs and films.

Land cover classification of Lago Grande de Curuai floodplain (Amazon, Brazil) using multi-sensor and image fusion techniques

Given the limitations of different types of remote sensing images, automated land-cover classifications of the Amazon várzea may yield poor accuracy indexes. One way to improve accuracy is through the combination of images from different sensors, by either image fusion or multi-sensor classifications. Therefore, the objective of this study was to determine which classification method is more efficient in improving land cover classification accuracies for the Amazon várzea and similar wetland environments - (a) synthetically fused optical and SAR images or (b) multi-sensor classification of paired SAR and optical images. Land cover classifications based on images from a single sensor (Landsat TM or Radarsat-2) are compared with multi-sensor and image fusion classifications. Object-based image analyses (OBIA) and the J.48 data-mining algorithm were used for automated classification, and classification accuracies were assessed using the kappa index of agreement and the recently proposed allocation and quantity disagreement measures. Overall, optical-based classifications had better accuracy than SAR-based classifications. Once both datasets were combined using the multi-sensor approach, there was a 2% decrease in allocation disagreement, as the method was able to overcome part of the limitations present in both images. Accuracy decreased when image fusion methods were used, however. We therefore concluded that the multi-sensor classification method is more appropriate for classifying land cover in the Amazon várzea.

Shape complexity based on mutual information

Shape complexity has recently received attention from different fields, such as computer vision and psychology. In this paper, integral geometry and information theory tools are applied to quantify the shape complexity from two different perspectives: from the inside of the object, we evaluate its degree of structure or correlation between its surfaces (inner complexity), and from the outside, we compute its degree of interaction with the circumscribing sphere (outer complexity). Our shape complexity measures are based on the following two facts: uniformly distributed global lines crossing an object define a continuous information channel and the continuous mutual information of this channel is independent of the object discretisation and invariant to translations, rotations, and changes of scale. The measures introduced in this paper can be potentially used as shape descriptors for object recognition, image retrieval, object localisation, tumour analysis, and protein docking, among others

Introduction of sensor spectral response into image fusion methods. Application to wavelet-based methods

Usual image fusion methods inject features from a high spatial resolution panchromatic sensor into every low spatial resolution multispectral band trying to preserve spectral signatures and improve spatial resolution to that of the panchromatic sensor. The objective is to obtain the image that would be observed by a sensor with the same spectral response (i.e., spectral sensitivity and quantum efficiency) as the multispectral sensors and the spatial resolution of the panchromatic sensor. But in these methods, features from electromagnetic spectrum regions not covered by multispectral sensors are injected into them, and physical spectral responses of the sensors are not considered during this process. This produces some undesirable effects, such as resolution overinjection images and slightly modified spectral signatures in some features. The authors present a technique which takes into account the physical electromagnetic spectrum responses of sensors during the fusion process, which produces images closer to the image obtained by the ideal sensor than those obtained by usual wavelet-based image fusion methods. This technique is used to define a new wavelet-based image fusion method.

A Copy detection Method for Malayalam Text Documents using N-grams Model

In this paper a method of copy detection in short Malayalam text passages is proposed. Given two passages one as the source text and another as the copied text it is determined whether the second passage is plagiarized version of the source text. An algorithm for plagiarism detection using the n-gram model for word retrieval is developed and found tri-grams as the best model for comparing the Malayalam text. Based on the probability and the resemblance measures calculated from the n-gram comparison , the text is categorized on a threshold. Texts are compared by variable length n-gram(n={2,3,4}) comparisons. The experiments show that trigram model gives the average acceptable performance with affordable cost in terms of complexity

Shape complexity based on mutual information

Shape complexity has recently received attention from different fields, such as computer vision and psychology. In this paper, integral geometry and information theory tools are applied to quantify the shape complexity from two different perspectives: from the inside of the object, we evaluate its degree of structure or correlation between its surfaces (inner complexity), and from the outside, we compute its degree of interaction with the circumscribing sphere (outer complexity). Our shape complexity measures are based on the following two facts: uniformly distributed global lines crossing an object define a continuous information channel and the continuous mutual information of this channel is independent of the object discretisation and invariant to translations, rotations, and changes of scale. The measures introduced in this paper can be potentially used as shape descriptors for object recognition, image retrieval, object localisation, tumour analysis, and protein docking, among others

Reading hybrid texts : remarks on text/image transitions

The reading of printed materials implies the visual processing of information originated in two distinct semiotic systems. The rapid identification of redundancy, complementation or contradiction rhetoric strategies between the two information types may be crucial for an adequate interpretation of bimodal materials. Hybrid texts (verbal and visual) are particular instances of bimodal materials, where the redundant information is often neglected while the complementary and the contradictory ones are essential.Studies using the 504 ASL eye-tracking system while reading either additive or exhibiting captions (Baptista, 2009) revealed fixations on the verbal material and transitions between the written and the pictorial in a much higher number and duration than the initially foreseen as necessary to read the verbal text. We therefore hypothesized that confirmation strategies of the written information are taking place, by using information available in the other semiotic system.Such eye-gaze patterns obtained from denotative texts and pictures seem to contradict some of the scarce existing data on visual processing of texts and images, namely cartoons (Carroll, Young and Guertain, 1992), descriptive captions (Hegarty, 1992 a and b), and advertising images with descriptive and explanatory texts (cf. Rayner and Rotello, 2001, who refer to a previous reading of the whole text before looking at the image, or even Rayner, Miller and Rotello, 2008 who refer to an earlier and longer look at the picture) and seem to consolidate findings of Radach et al. (2003) on systematic transitions between text and image.By framing interest areas in the printed pictorial material of non redundant hybrid texts, we have identified the specific areas where transitions take place after fixations in the verbal text. The way those transitions are processed brings a new interest to further research.

Semantic-level Visual Content Descriptor combining visual and textual cues as collaterals

In this paper, we introduce a novel high-level visual content descriptor which is devised for performing semantic-based image classification and retrieval. The work can be treated as an attempt to bridge the so called “semantic gap”. The proposed image feature vector model is fundamentally underpinned by the image labelling framework, called Collaterally Confirmed Labelling (CCL), which incorporates the collateral knowledge extracted from the collateral texts of the images with the state-of-the-art low-level image processing and visual feature extraction techniques for automatically assigning linguistic keywords to image regions. Two different high-level image feature vector models are developed based on the CCL labelling of results for the purposes of image data clustering and retrieval respectively. A subset of the Corel image collection has been used for evaluating our proposed method. The experimental results to-date already indicates that our proposed semantic-based visual content descriptors outperform both traditional visual and textual image feature models.