Wireless Sensor Networks (WSNs) allow the monitoring of activity or environmental conditions over a large area, from homes to industrial plants, from agriculture fields to forests and glaciers. They can support a variety of applications, from assisted living to natural disaster prevention. WSNs can, however, be challenging to setup and maintain, reducing the potential for real-world adoption. To address this limitation, this paper introduces SensorTune, a novel mobile interface to support non-expert users in iteratively setting up a WSN. SensorTune uses non-speech audio to present to its users information regarding the connectivity of the network they are setting up, allowing them to decide how to extend it. To simplify the interpretation of the data presented, the system adopts the metaphor of tuning a consumer analog radio, a very common and well known operation. A user study was conducted in which 20 subjects setup real multi-hop networks inside a large building using a limited number of wireless nodes. Subjects repeated the task with SensorTune and with a comparable mobile GUI interface. Experimental results show a statistically significant difference in the task completion time and a clear preference of users for the auditory interface.

Tangible user interfaces have been promoted and discussed in the Ubicomp and HCI communities for 15 years. In TUIs physical objects are used for the control and representation of digital information, similarly to how icons are used in graphical user interfaces for the same purpose. Most reported TUI systems have the nature of research prototypes, available in laboratories or museums. This paper reports an attempt to understand the impact of TUIs in users' everyday environments through 2 low-cost simple set-up tangible interfaces for music that can be freely downloaded from a website. The systems are based on computer vision, printed paper and audio output. A few hundreds of users downloaded them and played with them. We logged users interaction with the interfaces and analysed content posted by them on our own and other web sites to observe and evaluate how they relate to such novel systems, taking measures to protect their privacy. Both the interaction logs and the users' comments indicate that the tangible interfaces were accepted as normal: they were perceived just as interfaces to make music rather than esoteric systems. Its time to bring Ubicomp technology to the masses!

Visual markers are graphic symbols designed to be easily recognised by machines. They are traditionally used to track goods, but there is increasing interest in their application to mobile HCI. By scanning a visual marker through a camera phone users can retrieve localised information and access mobile services.

In this video demo, we present mTable, a multimedia tabletop system for browsing photo and video collections. We have developed a set of applications for visualizing and exploring photos, a board game for labeling photos, and a 3D cityscape metaphor for browsing videos. The system is suitable for use in a living room or office lounge, and can support multiple displays by visualizing the collections on the tabletop and showing full-size images and videos on another flat panel display in the room.

First developed by the architectural avante-garde in the early 20th century, the idea of the open plan was the result of a desire for greater transparency and flexibility in the design of interior environments. Essential to the functioning of the open plan in these early projects is the subtle articulation of differences between one part of the open interior and another. Later co-opted as an efficient means of achieving maximum density in office environments, the open plan as commonly practiced in the latter half of the 20th century resulted in undifferentiated, homogeneous settings that failed to realize the original intentions of this architectural idea. Embedded information technology offers an opportunity to support the differentiation and legibility of the open plan by sensing and displaying aspects of the building's environmental conditions and patterns of use. We introduce two ongoing projects as examples of building interfaces that enhance the transparency of information in the building, using surfaces embedded in the building to reveal invisible attributes of the interior that can be used by inhabitants to better understand their environment.

During grouping tasks for data exploration and sense-making, the criteria are normally not well-defined. When users are bringing together data objects thought to be similar in some way, implicit brushing continually detects for groups on the freeform workspace, analyzes the groups' text content or metadata, and draws attention to related data by displaying visual hints and animation. This provides helpful tips for further grouping, group meaning refinement and structure discovery. The sense-making process is further enhanced by retrieving relevant information from a database or network during the brushing. Closely related to implicit brushing, target snapping provides a useful means to move a data object to one of its related groups on a large display. Natural dynamics and smooth animations also help to prevent distractions and allow users to concentrate on the grouping and thinking tasks. Two different prototype applications, note grouping for brainstorming and photo browsing, demonstrate the general applicability of the technique.

Computer vision and pattern recognition systems play an important role in our lives by means of automated face detection, face and gesture recognition, and estimation of gender and age. This paper addresses the problem of gender classification using frontal facial images. We have developed gender classifiers with performance superior to existing gender classifiers. We experiment on 500 images (250 females and 250 males) randomly withdrawn from the FERET facial database. Independent component analysis (ICA) is used to represent each image as a feature vector in a low dimensional subspace. Different classifiers are studied in this lower dimensional space. Our experimental results show the superior performance of our approach to the existing gender classifiers. We get a 96% accuracy using support vector machine (SVM) in ICA space.

We present the Swisshouse, a novel type of "inhabitable interface" that supports direct and indirect communication and cultural awareness of habitants in different nations. The Swisshouse allows unsophisticated users to collaborate and be aware of each other over distance. By carefully sculpting the space and choreographing interactive elements in the space, the Swisshouse allows users to instantly separate, combine, and customize environments for specific collaborative activities. By providing visual representations of remote users and places, the Swisshouse provides awareness of the culture, presence and identities of virtual participants. And by tagging physical users with RFID tags, the Swisshouse makes participants aware of the social interaction occurring in the physical space. The combination of these primitives provides a single consistent inhabitable interface that integrates architectural and user interface design thinking, hardware and software design. To illustrate the power of this convergent approach, we describe several examples of real-life applications including a remote lecture, a brainstorming session, a business meeting, and an exhibition.

Eye location is used as a test bed for developing navigation routines implemented as visual routines within the framework of adaptive behavior-based AI. The adaptive eye location approach seeks first where salient objects are, and then what their identity is. Specifically, eye location involves: 1) the derivation of the saliency attention map, and 2) the possible classification of salient locations as eve regions. The saliency ("where") map is derived using a consensus between navigation routines encoded as finite-state automata exploring the facial landscape and evolved using genetic algorithms (GAs). The classification ("what") stage is concerned with the optimal selection of features, and the derivation of decision trees, using GAs, to possibly classify salient locations as eyes. The experimental results, using facial image data, show the feasibility of our method, and suggest a novel approach for the adaptive development of task-driven active perception and navigational mechanisms.

In this paper we describe the application of mixtures of experts on gender and ethnic classification of human faces, and pose classification, and show their feasibility on the FERET database of facial images. The FERET database allows us to demonstrate performance on hundreds or thousands of images. The mixture of experts is implemented using the "divide and conquer" modularity principle with respect to the granularity and/or the locality of information. The mixture of experts consists of ensembles of radial basis functions (RBFs). Inductive decision trees (DTs) and support vector machines (SVMs) implement the "gating network" components for deciding which of the experts should be used to determine the classification output and to restrict the support of the input space. Both the ensemble of RBF's (ERBF) and SVM use the RBF kernel ("expert") for gating the inputs. Our experimental results yield an average accuracy rate of 96% on gender classification and 92% on ethnic classification using the ERBF/DT approach from frontal face images, while the SVM yield 100% on pose classification.

The eyes are important facial landmarks, both for image normalization due to their relatively constant interocular distance, and for post processing due to the anchoring on model-based schemes. This paper introduces a novel approach for the eye detection task using optimal wavelet packets for eye representation and Radial Basis Functions (RBFs) for subsequent classification ("labeling") of facial areas as eye versus non-eye regions. Entropy minimization is the driving force behind the derivation of optimal wavelet packets. It decreases the degree of data dispersion and it thus facilitates clustering ("prototyping") and capturing the most significant characteristics of the underlying (eye regions) data. Entropy minimization is thus functionally compatible with the first operational stage of the RBF classifier, that of clustering, and this explains the improved RBF performance on eye detection. Our experiments on the eye detection task prove the merit of this approach as they show that eye images compressed using optimal wavelet packets lead to improved and robust performance of the RBF classifier compared to the case where original raw images are used by the RBF classifier.

Most of the research on face recognition addresses the MATCH problem and it assumes a closed universe where there is no need for a REJECT ('false positive') option. The SURVEILLANCE problem is addressed indirectly, if at all, through the MATCH problem, where the size of the gallery rather than that of the probe set is very large. This paper addresses the proper surveillance problem where the size of the probe ('unknown image') set vs. gallery ('known image') set is 450 vs. 50 frontal images. We developed robust face ID verification ('classification') and retrieval schemes based on hybrid classifiers and showed their feasibility using the FERET face data base. The hybrid classifier architecture consists of an ensemble of connectionist networks-Radial Basis Functions (RBF) and inductive decision trees (DT). Experimental results prove the feasibility of our approach and yield 97% accuracy using the probe and gallery sets specified above.

This paper describes an approach for the problem of face pose discrimination using support vector machines (SVM). Face pose discrimination means that one can label the face image as one of several known poses. Face images are drawn from the standard FERET database. The training set consists of 150 images equally distributed among frontal, approximately 33.75/spl deg/ rotated left and right poses, respectively, and the test set consists of 450 images again equally distributed among the three different types of poses. SVM achieved perfect accuracy-100%-discriminating between the three possible face poses on unseen test data, using either polynomials of degree 3 or radial basis functions (RBF) as kernel approximation functions.

This paper advances the methodology of hybrid classification architectures for face and hand gesture recognition tasks and shows their feasibility through experimental studies using the FERET data base and gesture images. The hybrid architecture, consisting of an ensemble of connectionist networks-radial basis functions (RBF)-and inductive decision trees (DT), combines the merits of 'holistic' template matching with those of 'abstractive' matching using discrete features and subject to both positive and negative learning. The hybrid architecture, quite general as it applies to both face and hand gesture recognition, derives its robustness from (i) consensus using ensembles of RBF network;, and (ii) flexible matching using categorical classification via decision trees. The experimental results, proving the feasibility of our approach, yield (i) 93% accuracy, using cross validation, for contents-based image retrieval (CBIR) subject to correct ID matching tasks, such as 'find Joe Smith with/without glasses', on a data bate of 200 images, and (ii) 96% accuracy using cross validation, for forensic verification on a data base consisting of 102 images corresponding to 350 subjects (of whom 102 are duplicates). Cross validation results on the hand gesture recognition task yield a false negative rate of 3.6% and a false positive rate of 1.8%, using a data base of 750 images corresponding to 25 hand gestures.

The paper proposes a novel algorithm for face detection using decision trees (DT) and shows its generality and feasibility using a database consisting of 2340 face images from the FERET database (corresponding to 817 subjects and including 190 sets of duplicates) over a semi-uniform background. The approach used for face detection involves three main stages, those of location, cropping, and post-processing. The first stage finds a rough approximation for the possible location of the face box, the second stage will refine it, and the last stage decider whether a face is present in the image and if the answer is positive would normalize the face image. The algorithm does not require multiple (scale) templates and the accuracy achieved is 96%. Accuracy is based on the visual observation that the face box includes both eyes, nose, and mouth, and that the top side of the box is below the hairline. Experiments were also performed to assess the accuracy of the algorithm in rejecting images where no face is present. Using a small database of 25 images of various but complex backgrounds the algorithm failed on two images for an overall accuracy rate of 92%.

We address the problem of crafting visual routines for detection tasks. Emphasis is placed on both competition and learning to help with specific visual tasks involved in localization and identification. Crafting of visual routines presents difficult optimization problems and leads to evolutionary computation using a hybrid genetic architecture consisting of natural selection, learning, and their beneficial interactions. Base features representations and visual routines for detection represented as decision trees are evolved. The visual routine considered is that of eye detection. The experimental results reported herein prove the feasibility of our approach in terms of feature selection (data compression) and the corresponding eye detection (pattern recognition).

We describe a novel approach for fully automated face recognition and show its feasibility on a large database of facial images (FERET). Our approach, based on a hybrid architecture consisting of an ensemble of radial basis function (RBF) neural networks and inductive decision trees, combines the merits of "abstractive" features with those of "holistic" template matching. The benefits of our architecture include: 1) robust detection of facial landmarks using decision trees, and 2) robust face recognition using consensus methods over ensembles of RBF networks. Experiments carried out using k-fold cross validation on a large database consisting of 748 images corresponding to 374 subjects, among them 11 duplicates, yield on the average 87% correct match, and 99% correct surveillance ("verification").

This paper describes a hybrid methodology that integrates genetic algorithms (GAs) and decision tree learning in order to evolve useful subsets of discriminatory features for recognizing complex visual concepts. A GA is used to search the space of all possible subsets of a large set of candidate discrimination features. Candidate feature subsets are evaluated by using C4.5, a decision tree learning algorithm, to produce a decision tree based on the given features using a limited amount of training data. The classification performance of the resulting decision tree on unseen testing data is used as the fitness of the underlying feature subset. Experimental results are presented to show how increasing the amount of learning significantly improves feature set evolution for difficult visual recognition problems involving satellite and facial image data. In addition, we also report on the extent to which other more subtle aspects of the Baldwin effect are exhibited by the system.

This paper presents a multi-frame pel-recursive two-dimensional motion estimation scheme for video image interpolation. The proposed approach uses more information from the image sequences than previous approaches, and gives a closed-form solution to update motion vectors among frame pairs simultaneously. It is suitable for object motion with acceleration since it places no constraints on the motion vectors among consecutive frames.>