Recognizing emotional reactions of movie audiences to affective movie content is a challenging task in affective computing. Previous research on induced emotion recognition has mainly focused on using audio-visual movie content. Nevertheless, the relationship between the perceptions of the affective movie content (perceived emotions) and the emotions evoked in the audiences (induced emotions) is unexplored. In this work, we studied the relationship between perceived and induced emotions of movie audiences. Moreover, we investigated multimodal modelling approaches to predict movie induced emotions from movie content based features, as well as physiological and behavioral reactions of movie audiences. To carry out analysis of induced and perceived emotions, we first extended an existing database for movie affect analysis by annotating perceived emotions in a crowd-sourced manner. We find that perceived and induced emotions are not always consistent with each other. In addition, we show that perceived emotions, movie dialogues, and aesthetic highlights are discriminative for movie induced emotion recognition besides spectators' physiological and behavioral reactions. Also, our experiments revealed that induced emotion recognition could benefit from including temporal information and performing multimodal fusion. Moreover, our work deeply investigated the gap between affective content analysis and induced emotion recognition by gaining insight into the relationships between aesthetic highlights, induced emotions, and perceived emotions.

Detection of aesthetic highlights is a challenge for understanding the affective processes taking place during movie watching. In this article, we study spectators’ responses to movie aesthetic stimuli in a social context. Moreover, we look for uncovering the emotional component of aesthetic highlights in movies. Our assumption is that synchronized spectators’ physiological and behavioral reactions occur during these highlights because: ( i ) aesthetic choices of filmmakers are made to elicit specific emotional reactions (e.g., special effects, empathy, and compassion toward a character) and ( ii ) watching a movie together causes spectators’ affective reactions to be synchronized through emotional contagion. We compare different approaches to estimation of synchronization among multiple spectators’ signals, such as pairwise, group, and overall synchronization measures to detect aesthetic highlights in movies. The results show that the unsupervised architecture relying on synchronization measures is able to capture different properties of spectators’ synchronization and detect aesthetic highlights based on both spectators’ electrodermal and acceleration signals. We discover that pairwise synchronization measures perform the most accurately independently of the category of the highlights and movie genres. Moreover, we observe that electrodermal signals have more discriminative power than acceleration signals for highlight detection.

This paper studies emotion recognition in the context of collaboration. When people are interacting with each other they tend to reach a similar emotional state through mechanisms like empathy and emotion contagion. We thus investigated if participants' emotions could be determined from the affective reactions and behaviors of their partner. Two types of emotional expressions were studied: physiological reactions and speech. Results show that emotions could be recognized with similar performance when employing affective features from the self or the partner. In addition, performance was improved when combining self and partner information. The results demonstrate that in social situations an emotion recognition model should include information about partners.

Predicting the emotional response of movie audiences to affective movie content is a challenging task in affective computing. Previous work has focused on using audiovisual movie content to predict movie induced emotions. However, the relationship between the audience's perceptions of the affective movie content (perceived emotions) and the emotions evoked in the audience (induced emotions) remains unexplored. In this work, we address the relationship between perceived and induced emotions in movies, and identify features and modelling approaches effective for predicting movie induced emotions. First, we extend the LIRIS-ACCEDE database by annotating perceived emotions in a crowd-sourced manner, and find that perceived and induced emotions are not always consistent. Second, we show that dialogue events and aesthetic highlights are effective predictors of movie induced emotions. In addition to movie based features, we also study physiological and behavioural measurements of audiences. Our experiments show that induced emotion recognition can benefit from including temporal context and from including multimodal information. Our study bridges the gap between affective content analysis and induced emotion prediction.

Detection of emotional and aesthetic highlights is a challenge for the affective understanding of movies. Our assumption is that synchronized spectators' physiological and behavioral reactions occur during these highlights. We propose to employ the periodicity score to capture synchronization among groups of spectators' signals. To uncover the periodicity score's capabilities, we compare it with baseline synchronization measures, such as the nonlinear interdependence and the windowed mutual information. The results show that the periodicity score and the pairwise synchronization measures are able to capture different properties of spectators' synchronization, and they indicate the presence of some types of emotional and aesthetic highlights in a movie based on spectators' electro-dermal and acceleration signals.

We present a user-independent emotion recognition method with the goal of detecting expected emotions or affective tags for videos using electroencephalogram (EEG), pupillary response and gaze distance. We first selected 20 video clips with extrinsic emotional content from movies and online resources. Then EEG responses and eye gaze data were recorded from 24 participants while watching emotional video clips. Ground truth was defined based on the median arousal and valence scores given to clips in a preliminary study. The arousal classes were calm, medium aroused and activated and the valence classes were unpleasant, neutral and pleasant. A one-participant-out cross validation was employed to evaluate the classification performance in a user-independent approach. The best classification accuracy of 68.5% for three labels of valence and 76.4% for three labels of arousal were obtained using a modality fusion strategy and a support vector machine. The results over a population of 24 participants demonstrate that user-independent emotion recognition can outperform individual self-reports for arousal assessments and do not underperform for valence assessments.

Detection of highlights in movies is a challenge for the affective understanding and implicit tagging of films. Under the hypothesis that synchronization of the reaction of spectators indicates such highlights, we define a synchronization measure between spectators that is capable of extracting movie highlights. The intuitive idea of our approach is to define (a) a parameterization of one spectator's physiological data on a manifold; (b) the synchronization measure between spectators as the Kolmogorov-Smirnov distance between local shape distributions of the underlying manifolds. We evaluate our approach using data collected in an experiment where the electro-dermal activity of spectators was recorded during the entire projection of a movie in a cinema. We compare our methodology with baseline synchronization measures, such as correlation, Spearman's rank correlation, mutual information, Kolmogorov-Smirnov distance. Results indicate that the proposed approach allows to accurately distinguish highlight from non-highlight scenes.

Affective video indexing is the area of research that develops techniques to automatically generate descriptions of video content that encode the emotional reactions which the video content evokes in viewers. This paper provides a set of corpus development guidelines based on state-of-the-art practice intended to support researchers in this field. Affective descriptions can be used for video search and browsing systems offering users affective perspectives. The paper is motivated by the observation that affective video indexing has yet to fully profit from the standard corpora (data sets) that have benefited conventional forms of video indexing. Affective video indexing faces unique challenges, since viewer-reported affective reactions are difficult to assess. Moreover affect assessment efforts must be carefully designed in order to both cover the types of affective responses that video content evokes in viewers and also capture the stable and consistent aspects of these responses. We first present background information on affect and multimedia and related work on affective multimedia indexing, including existing corpora. Three dimensions emerge as critical for affective video corpora, and form the basis for our proposed guidelines: the context of viewer response, personal variation among viewers, and the effectiveness and efficiency of corpus creation. Finally, we present examples of three recent corpora and discuss how these corpora make progressive steps towards fulfilling the guidelines.

In this paper we propose a method to assess key collaborative processes during computer-supported group work based on physiological signals and eye-movements. Synchronous interpersonal multimodal signals from 30 dyads were recorded while collaborating remotely. Features measuring how much collaborators' eye-movements and physiology are coupled were extracted from the obtained time series and two regression models were trained to assess collaboration. Results show that the two coupling measures can be used to predict collaborative processes such as grounding and convergence. Assessing those processes is a major step toward the development of remote collaborative interfaces able to adapt to the users' social interactions.

Exploring unfamiliar environments is a challenging task in which additionally, unsighted individuals frequently fail to gain perception of obstacles and make serendipitous discoveries. This is because the mental depiction of the context is drastically lessened due to the absence of visual information. It is still not clear in neuroscience, whether stimuli elicited by visual cueing can be replicated by other senses (cross-model transfer). In the practice, however, everyone recognizes a key, whether it is felt in a pocket or seen on a table. We present a context-aware aid system for the blind that merges three levels of assistance enhancing the intelligibility of the nearby entities: an exploration module to help gain awareness of the surrounding context, an alerting method for warning the user when a stumble is likely, and, finally, a recognition engine that retrieves natural targets previously learned. Practical experiences with our system show that in the absence of visual cueing, the audio and haptic trajectory playback coupled with computer-vision methods is a promising approach to depict dynamic information of the immediate environment.

The proposed demonstration is an automatic emotion assessment installation used for game's dynamic difficulty adjustment. The goal of the system is to maintain the player of the game in a state of entertainment and engagement where his/her skills match the difficulty level of the game. The player's physiological signals are recorded while playing a Tetris game and signal processing, feature extraction and classification techniques are applied to the signals in order to detect when the player is anxious or bored. The level of the Tetris game is then adjusted according to the player's detected emotional state. The demonstration will also serve as an experimental protocol to test the player's experience through their interaction with the proposed platform.

We present a multimodal data set for the analysis of human affective states. The electroencephalogram (EEG) and peripheral physiological signals of 32 participants were recorded as each watched 40 one-minute long excerpts of music videos. Participants rated each video in terms of the levels of arousal, valence, like/dislike, dominance, and familiarity. For 22 of the 32 participants, frontal face video was also recorded. A novel method for stimuli selection is proposed using retrieval by affective tags from the last.fm website, video highlight detection, and an online assessment tool. An extensive analysis of the participants' ratings during the experiment is presented. Correlates between the EEG signal frequencies and the participants' ratings are investigated. Methods and results are presented for single-trial classification of arousal, valence, and like/dislike ratings using the modalities of EEG, peripheral physiological signals, and multimedia content analysis. Finally, decision fusion of the classification results from different modalities is performed. The data set is made publicly available and we encourage other researchers to use it for testing their own affective state estimation methods.

MAHNOB-HCI is a multimodal database recorded in response to affective stimuli with the goal of emotion recognition and implicit tagging research. A multimodal setup was arranged for synchronized recording of face videos, audio signals, eye gaze data, and peripheral/central nervous system physiological signals. Twenty-seven participants from both genders and different cultural backgrounds participated in two experiments. In the first experiment, they watched 20 emotional videos and self-reported their felt emotions using arousal, valence, dominance, and predictability as well as emotional keywords. In the second experiment, short videos and images were shown once without any tag and then with correct or incorrect tags. Agreement or disagreement with the displayed tags was assessed by the participants. The recorded videos and bodily responses were segmented and stored in a database. The database is made available to the academic community via a web-based system. The collected data were analyzed and single modality and modality fusion results for both emotion recognition and implicit tagging experiments are reported. These results show the potential uses of the recorded modalities and the significance of the emotion elicitation protocol.

This paper presents a user-independent emotion recognition method with the goal of recovering affective tags for videos using electroencephalogram (EEG), pupillary response and gaze distance. We first selected 20 video clips with extrinsic emotional content from movies and online resources. Then, EEG responses and eye gaze data were recorded from 24 participants while watching emotional video clips. Ground truth was defined based on the median arousal and valence scores given to clips in a preliminary study using an online questionnaire. Based on the participants' responses, three classes for each dimension were defined. The arousal classes were calm, medium aroused, and activated and the valence classes were unpleasant, neutral, and pleasant. One of the three affective labels of either valence or arousal was determined by classification of bodily responses. A one-participant-out cross validation was employed to investigate the classification performance in a user-independent approach. The best classification accuracies of 68.5 percent for three labels of valence and 76.4 percent for three labels of arousal were obtained using a modality fusion strategy and a support vector machine. The results over a population of 24 participants demonstrate that user-independent emotion recognition can outperform individual self-reports for arousal assessments and do not underperform for valence assessments.

Microsoft's Kinect 3-D motion sensor is a low cost 3D camera that provides color and depth information of indoor environments. In this demonstration, the functionality of this fun-only camera accompanied by an iPad's tangible interface is targeted to the benefit of the visually impaired. A computer-vision-based framework for real time objects localization and for their audio description is introduced. Firstly, objects are extracted from the scene and recognized using feature descriptors and machine-learning. Secondly, the recognized objects are labeled by instruments sounds, whereas their position in 3D space is described by virtual space sources of sound. As a result, the scene can be heard and explored while finger-triggering the sounds within the iPad, on which a top-view of the objects is mapped. This enables blindfolded users to build a mental occupancy grid of the environment. The approach presented here brings the promise of efficient assistance and could be adapted as an electronic travel aid for the visually-impaired in the near future.

Viewers' preference for multimedia selection depends highly on their emotional experience. In this paper, we present an emotion detection method for music videos using central and peripheral nervous system physiological signals as well as multimedia content analysis. A set of 40 music clips eliciting a broad range of emotions were first selected. After extracting the one minute long emotional highlight of each video, they were shown to 32 participants while their physiological responses were recorded. Participants self-reported their felt emotions after watching each clip by means of arousal, valence, dominance, and liking ratings. The physiological signals included electroencephalogram, galvanic skin response, respiration pattern, skin temperature, electromyograms and blood volume pulse using plethysmograph. Emotional features were extracted from the signals and the multimedia content. The emotional features were used to train a linear ridge regressor to detect emotions for each participant using a leave-one-out cross-validation strategy. The performance of the personalized emotion detection is shown to be significantly superior to a random regressor.

This paper proposes to maintain player's engagement by adapting game difficulty according to player's emotions assessed from physiological signals. The validity of this approach was first tested by analyzing the questionnaire responses, electroencephalogram (EEG) signals, and peripheral signals of the players playing a Tetris game at three difficulty levels. This analysis confirms that the different difficulty levels correspond to distinguishable emotions, and that, playing several times at the same difficulty level gives rise to boredom. The next step was to train several classifiers to automatically detect the three emotional classes from EEG and peripheral signals in a player-independent framework. By using either type of signals, the emotional classes were successfully recovered, with EEG having a better accuracy than peripheral signals on short periods of time. After the fusion of the two signal categories, the accuracy raised up to 63%.

In this demo, we present the detection module of the See ColOr (Seeing Colors with an Orchestra) mobility aid for visually impaired persons. This module points out areas that present either particular interest or potential threat. In order to detect object and obstacles, we propose a bottom-up approach based on visual saliency: objects that would attract the visual attention of a non-disabled individual are pointed out by the system as areas of interest for the user. The device uses a stereoscopic camera, a laptop, and standard headphones. Given the type of scene and/or scenario, specific feature maps are computed in order to indicate areas of interest in real-time. This demonstration shows that the module indicates objects and obstacles as accurately as a system using all available feature maps.

Providing the blind with substitute visual perception is a relentless challenge confronting researchers of diverse areas. The See ColOr (Seeing Color with an Orchestra) system translates aimed-at regions of a color scene into 2D-spatialized sound signals represented by musical instruments. Associating sounds with colors is achieved thanks to an efficient quantization of the regions' HSL representation (Hue, Saturation, Luminosity). See ColOr can be used both for exploring static images and as a mobility aid. In this report, we introduce its general framework for color-audio encoding of images to provide visually impaired individuals with a low-cost application for color perception substitution, using the sense of hearing instead of sight. The experimental tests using a demo implementation have shown the feasibility and usefulness of this approach.

An approach for implementing affective information as tags for multimedia content indexing and retrieval is presented. The approach can be used for implicit as well as explicit tags and is presented here using data recorded during the viewing of movie fragments containing annotations and physiological signal recordings. For retrieval based on affective queries, a representation of the query-words is defined in the arousal-valence space in the form of a Gaussian probability distribution and a retrieval method based on this representation is presented. Validation of retrieval accuracy is performed using Precision and Recall parameters. Results show that the use of arousal and valence as affective tags can improve retrieval results.

In the context of vision substitution by the auditory channel several systems have been introduced. One such system that is presented here, See ColOr, is a dedicated interface part of a mobility aid for visually impaired people. It transforms a small portion of a colored video image into spatialized instrument sounds. In this work the purpose is to verify the hypothesis that sounds from musical instruments provide an alternative way to vision for obtaining color information from the environment. We introduce an experiment in which several participants try to match pairs of colored socks by pointing a head mounted camera and by listening to the generated sounds. Our experiments demonstrated that blindfolded individuals were able to accurately match pairs of colored socks. The advantage of the See ColOr interface is that it allows the user to receive a feed-back auditory signal from the environment and its colors, promptly. Our perceptual auditory coding of pixel values opens the opportunity to achieve more complicated experiments related to vision tasks, such as perceiving the environment by interpreting its colors.

In this paper, we propose an approach for affective representation of movie scenes based on the emotions that are actually felt by spectators. Such a representation can be used for characterizing the emotional content of video clips for e.g. affective video indexing and retrieval, neuromarketing studies, etc. A dataset of 64 different scenes from eight movies was shown to eight participants. While watching these clips, their physiological responses were recorded. The participants were also asked to self-assess their felt emotional arousal and valence for each scene. In addition, content-based audio- and video-based features were extracted from the movie scenes in order to characterize each one. Degrees of arousal and valence were estimated by a linear combination of features from physiological signals, as well as by a linear combination of content-based features. We showed that a significant correlation exists between arousal/valence provided by the spectator's self-assessments, and affective grades obtained automatically from either physiological responses or from audio-video features. This demonstrates the ability of using multimedia features and physiological responses to predict the expected affect of the user in response to the emotional video content.

Performance limits of multimodal detection systems are analyzed in this paper. Two main setups are considered, i.e., based on fusion of dependent and independent modalities, respectively. The analysis is performed in terms of attainable probability of detection errors characterized by the corresponding error exponents. It is demonstrated that an expected performance gain from fusion of dependent modalities is superior than in the case when one fuses independent signals. In order to quantify the efficiency of dependent modality fusion versus the independent case, the problem analysis is performed in the Gaussian formulation.

In this paper we consider the problem of robust perceptual hashing as composite hypothesis testing. First, we formulate this problem as multiple hypothesis testing under prior ambiguity about source statistics and channel parameters representing a family of restricted geometric attacks. We introduce an efficient universal test that achieves the performance of informed decision rules for the specified class of source and geometric channel models. Finally, we consider the practical hash construction, which compromises computational complexity, robustness to geometrical transformations, lack of priors about source statistics and security requirements. The proposed hash is based on a binary hypothesis testing for randomly or semantically selected blocks or regions in sequences or images. We present the results of experimental validation of the developed concept that justifies the practical efficiency of the elaborated framework.

The work presented in this paper aims at assessing human emotions using peripheral as well as electroencephalographic (EEG) physiological signals. Three specific areas of the valence-arousal emotional space are defined, corresponding to negatively excited, positively excited, and calm-neutral states. An acquisition protocol based on the recall of past emotional events has been designed to acquire data from both peripheral and EEG signals. Pattern classification is used to distinguish between the three areas of the valence-arousal space. The performance of two classifiers has been evaluated on different features sets: peripheral data, EEG data, and EEG data with prior feature selection. Comparison of results obtained using either peripheral or EEG signals confirms the interest of using EEG’s to assess valence and arousal in emotion recall conditions.

In this paper, we address the analysis of the Costa setup under channel uncertainty. Since the Costa setup was entirely considered under the Gaussian assumptions about host and channel statistics, we assume that the channel is an additive white Gaussian noise (AWGN) with unknown variance defined on some interval. First, we solve the problem of average achievable rate optimization assuming that the distribution of noise variances is known. Then, we withdraw the previous assumption and consider that the variance distribution is unknown. The corresponding criteria are formulated and the performance of the Costa under these criteria is demonstrated

In this paper, we consider the problem of optimal self-embedding Laplacian data hiding for the state-dependent channels. In particular, we propose to decompose the Laplacian data using the paradigm of parallel source splitting. Experimental validation confirms the efficiency of the proposed approach

In this paper, we deal with the design of high-rate multilevel 2-D bar codes for the print-and-scan channel. First, we introduce a framework for evaluating the performance limits of these codes by studying an intersymbol-interference (ISI)-free, synchronous, and noiseless print-and-scan channel, where the input and output alphabets are finite and the printer device uses halftoning to simulate multiple gray levels. Second, we present a new model for the print-and-scan channel specifically adapted to the problem of communications via multilevel 2-D bar codes. This model, inspired by our experimental work, assumes perfect synchronization and absence of ISI, but independence between the channel input and the noise is not assumed. We adapt the theory of multilevel coding with multistage decoding (MLC/MSD) to the print-and-scan channel. Finally, we present experimental results confirming the utility of our channel model, and showing that multilevel 2-D bar codes using MLC/MSD can reliably achieve the high-capacity storage requirements of many multimedia security and management applications

Spread spectrum (SS) or known-host-statistics technique has shown the best performance in terms of both rate of reliable communications and bit error probability at the low watermark-to-noise ratio (WNR) regime. These results were obtained assuming that the host data follows an independent and identically distributed (i.i.d.) Gaussian distribution. However, in some widely used in practical data-hiding transform domains (like wavelet or discrete cosine transform domains) the host statistics have strong non-Gaussian character. Motivated by this stochastic modeling mismatch between the used assumption and the real case, a new set-up of the SS-based data-hiding with Laplacian host is presented for performance enhancement in terms of both bit error probability and achievable rates in additive white Gaussian noise (AWGN) channels based on the parallel splitting of Laplacian source.

Text documents, in electronic and hardcopy forms, are and will probably remain the most widely used kind of content in our digital age. The goal of this paper is to overview protocols for text data-hiding based "smart documents", achieving document self-authentication, self-recovery, self-annotation and automatic processing. We argue that document security, recovery and embedded annotation are the most promising data-hiding based frameworks.

In the scope of quantization-based watermarking techniques and additive attacks, there exists a common belief that the worst case attack (WCA) is given by additive white Gaussian noise (AWGN). Nevertheless, it has not been proved that the AWGN is indeed the WCA within the class of additive attacks against quantization-based watermarking. In this paper, the analysis of the WCA is theoretically developed with probability of error as a cost function. The adopted approach includes the possibility of masking the attack by a target probability density function (PDF) in order to trick smart decoding. The developed attack upper bounds the probability of error for quantization-based embedding schemes within the class of additive attacks.

In this paper we consider the problem of joint capacity-security analysis of data hiding technologies from the communications point of view. First, we formulate data hiding as an optimal encoding problem for different operational regimes, that include both robust digital watermarking and steganography. This provides the corresponding estimation of the hidden data statistics, as well as of the rates approaching embedding capacity. Secondly, we formulate the problem of blind stochastic hidden data detection based on the developed watermark statistics. Finally, we estimate the error of watermark detection and the variance of the watermark estimation that determine the system security.

This paper presents an efficient method for the estimation and recovering from nonlinear or local geometrical distortions, such as the random bending attack and restricted projective transforms. The distortions are modeled as a set of local affine transforms, the watermark being repeatedly allocated into small blocks in order to ensure its locality. The estimation of the affine transform parameters is formulated as a robust penalized maximum likelihood (ML) problem, which is suitable for the local level as well as for global distortions. Results with the Stirmark benchmark confirm the high robustness of the proposed method and show its state-of-the-art performance.

Abstract In this article we address the problem of benchmarking image browsers. Image browsers are systems that help the user in finding an image from scratch, as opposed to query by example (QBE), where an example image is needed. The existence of different search paradigms for image browsers makes it difficult to compare image browsers. Currently, the only admissible way of evaluation is by conducting large‐scale user studies. This makes it difficult to use such an evaluation as a tool for improving browsing systems. As a solution, we propose an automatic image browser benchmark that uses structured text annotation of the image collection for the simulation of the user's needs. We apply such a benchmark on an example system.

We describe effective channel coding strategies which can be used in conjunction with linear programming optimization techniques for the embedding of robust perceptually adaptive DCT domain watermarks. The main contributions lie in the proposal of a coding strategy based on the magnitude of a DCT coefficient, the use of turbo codes for effective error correction, and finally the incorporation of JPEG quantization tables at embedding.

Relevance feedback has been shown to be a very effective tool for enhancing retrieval results in text retrieval. It has also been increasingly used in content-based image retrieval and very good results have been obtained. However, too much negative feedback may destroy a query as good features get negative weightings. This paper compares a variety of strategies for positive and negative feedback. The performance evaluation of feedback algorithms is a hard problem. To solve this, we obtain judgments from several users and employ an automated feedback scheme. We then evaluate different techniques using the same judgements. Using automated feedback, the ability of a system to adapt to the user's needs can be measured very effectively. Our study highlights the utility of negative feedback, especially over several feedback steps.

Digital watermarks have been proposed as a method for discouraging illicit copying and distribution of copyrighted material. This paper describes a method for the secure and robust copyright protection of digital images. We present an approach for embedding a digital watermark into an image using the Fourier transform. To this watermark is added a template in the Fourier transform domain to render the method robust against general linear transformations. We detail a new algorithm based on polar maps for the accurate and efficient recovery of the template in an image which has undergone a general affine transformation. We also present results which demonstrate the robustness of the method against some common image processing operations such as compression, rotation, scaling, and aspect ratio changes.

A digital watermark is an invisible mark embedded in a digital image which may be used for copyright protection. This paper proposes that Fourier-Mellin transform-based invariants can be used for digital image watermarking. The embedded marks may be designed to be unaffected by any combination of rotation, scale and translation transformations. The original image is not required for extracting the embedded mark.

This paper describes a two-stage statistical approach supporting content-based search in image databases. The first stage performs correspondence analysis, a factor analysis method transforming image attributes into a reduced-size, uncorrelated factor space. The second stage performs ascendant hierarchical classification, an iterative clustering method which constructs a hierarchical index structure for the images of the database. Experimental results supporting the applicability of both techniques to data sets of heterogeneous images are reported.

This project concerns the management of a multimedia database (text and image) of historical papers representing ancient watermarks. The current database contains roughly 3000 images of such watermarks; the system allows archival and retrieval by means of textual or morphological criteria. During the archival phase, textual description are stored, as well as descriptive primitives extracted together with the watermark itself by image analysis methods. For the retrieval phase, several types of queries are supported; they allow textual search on the basis of the accompanying descriptions, morphological search according to global characteristics, and shape based search on the basis of the watermark shape.

Active and selective perception seeks regions of interest in an image in order to reduce the computational complexity associated with time-consuming processes such as object recognition. We describe in this paper a visual attention system that extracts regions of interest by integrating multiple image cues. Bottom-up cues are detected by decomposing the image into a number: of feature and conspicuity maps, while a-priori knowledge (i.e. models) about objects is used to generate top-down attention cues. Bottom-up and top-down information is combined through a non-linear relaxation process using energy minimization-like procedures. The functionality of the attention system is expanded by the introduction of an alerting (motion-based) system able to explore and avoid obstacles. Experimental results are reported, using cluttered and noisy scenes.>

The potato operation is a project belonging to the domain of agricultural robotics, or agrotics. It aims to automate pulp sampling of potatoes in order to detect viral diseases. The difficulty of this problem lies in the high variability (shape, texture, colour) of natural objects. Three approaches have been studied, based on contour classification, on thermometry and on active vision and image analysis. Cooperation between robotics, active 3D computer vision and robust image analysis leads to a performant solution.>

In manufacturing automation, the current focus is on integration at enterprise level. This however has not reduced the need for automation on the shopfloor. On the contrary, the latter has become more pressing. On the shopfloor, major manufacturing costs are related to handling and assembly operations. Difficulties in automating those operations are twofold. First, there is usually a line beyond which manual operation remains the most economical solution today. And then for each application, the proper level ofsophistication in terms of automation technology should be adopted. The paper concentrates on the second difficulty. Most often, products and processes can be designed so as to require fairly simple automated systems for their manufacturing (on/off devices, programmable logic controllers, independent actuators, etc.). But when the applicationfeatures significant position and/or orientation uncertainties (mathematical space of dimension 3 or more), some kind of perception is required to cope with them, and this usually results in adaptive workpiece or tool trajectories. Robotics provide unmatched solutions for such multi-dimensional, coordinated motions. General guidelines are introduced in order t o select the appropriate type of component for automation. Then, two case studies follow. In both cases, the application is complex, in terms of parameter variability. Many examples are given of correspondence between given guidelines and concrete, low-level details. In particular, while in the first case automated solutions can be devised with traditional, multiple independent servoed motions and general-purpose computers, in the second one, industrial robotics with dedicated controllers provide the right answer.

Numerous images are produced daily in biomedical research. In order to extract relevant and useful results, various processing and analysis steps are mandatory. The present paper describes a new, powerful and user-friendly image analysis system: LaboImage. In addition to standard image processing modules. LaboImage also contains various specialized tools. These multiple processing modules and tools are first introduced. A one-dimensional gel analysis method is then described. The new concept of 'normalized virtual one-dimensional gel' is introduced, making comparisons between gels particularly easy. This normalized gel is obtained by compensating for the bending of the lanes automatically; no information loss is incurred in the process. Finally, the model of interaction in a multi-window environment is discussed. LaboImage is designed to run in two ways: interactively, using menus and panels; and in batch mode by means of user-defined macros. Examples are given to illustrate the potentialities of the software.