Hand gesture recognition for human computer interaction : a comparative study of different image features

Hand gesture recognition for human computer interaction, being a natural way of human computer interaction, is an area of active research in computer vision and machine learning. This is an area with many different possible applications, giving users a simpler and more natural way to communicate with robots/systems interfaces, without the need for extra devices. So, the primary goal of gesture recognition research is to create systems, which can identify specific human gestures and use them to convey information or for device control. For that, vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition in real time. In this study we try to identify hand features that, isolated, respond better in various situations in human-computer interaction. The extracted features are used to train a set of classifiers with the help of RapidMiner in order to find the best learner. A dataset with our own gesture vocabulary consisted of 10 gestures, recorded from 20 users was created for later processing. Experimental results show that the radial signature and the centroid distance are the features that when used separately obtain better results, with an accuracy of 91% and 90,1% respectively obtained with a Neural Network classifier. These to methods have also the advantage of being simple in terms of computational complexity, which make them good candidates for real-time hand gesture recognition.

Hand gesture recognition system based in computer vision and machine learning

"Lecture notes in computational vision and biomechanics series, ISSN 2212-9391, vol. 19"

Generic system for human-computer gesture interaction: applications on sign language recognition and robotic soccer refereeing

Hand gestures are a powerful way for human communication, with lots of potential applications in the area of human computer interaction. Vision-based hand gesture recognition techniques have many proven advantages compared with traditional devices, giving users a simpler and more natural way to communicate with electronic devices. This work proposes a generic system architecture based in computer vision and machine learning, able to be used with any interface for human-computer interaction. The proposed solution is mainly composed of three modules: a pre-processing and hand segmentation module, a static gesture interface module and a dynamic gesture interface module. The experiments showed that the core of visionbased interaction systems could be the same for all applications and thus facilitate the implementation. For hand posture recognition, a SVM (Support Vector Machine) model was trained and used, able to achieve a final accuracy of 99.4%. For dynamic gestures, an HMM (Hidden Markov Model) model was trained for each gesture that the system could recognize with a final average accuracy of 93.7%. The proposed solution as the advantage of being generic enough with the trained models able to work in real-time, allowing its application in a wide range of human-machine applications. To validate the proposed framework two applications were implemented. The first one is a real-time system able to interpret the Portuguese Sign Language. The second one is an online system able to help a robotic soccer game referee judge a game in real time.

Vision-based portuguese sign language recognition system

Vision-based hand gesture recognition is an area of active current research in computer vision and machine learning. Being a natural way of human interaction, it is an area where many researchers are working on, with the goal of making human computer interaction (HCI) easier and natural, without the need for any extra devices. So, the primary goal of gesture recognition research is to create systems, which can identify specific human gestures and use them, for example, to convey information. For that, vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition in real time. Hand gestures are a powerful human communication modality with lots of potential applications and in this context we have sign language recognition, the communication method of deaf people. Sign lan- guages are not standard and universal and the grammars differ from country to coun- try. In this paper, a real-time system able to interpret the Portuguese Sign Language is presented and described. Experiments showed that the system was able to reliably recognize the vowels in real-time, with an accuracy of 99.4% with one dataset of fea- tures and an accuracy of 99.6% with a second dataset of features. Although the im- plemented solution was only trained to recognize the vowels, it is easily extended to recognize the rest of the alphabet, being a solid foundation for the development of any vision-based sign language recognition user interface system.

An integrated system for human action recognition from video using hidden Markov model

In this paper, we present an integrated system for real-time automatic detection of human actions from video. The proposed approach uses the boundary of humans as the main feature for recognizing actions. Background subtraction is performed using Gaussian mixture model. Then, features are extracted from silhouettes and Vector Quantization is used to map features into symbols (bag of words approach). Finally, actions are detected using the Hidden Markov Model. The proposed system was validated using a newly collected real- world dataset. The obtained results show that the system is capable of achieving robust human detection, in both indoor and outdoor environments. Moreover, promising classification results were achieved when detecting two basic human actions: walking and sitting.

Application of near surface mounted (NSM) strengthening technique to traditional timber frame walls

Timber frame buildings are well known as an efficient seismic resistant structure popular all over the world not only due to their seismic performance, but also to their low cost and the strength they offer. These constructions still exist today and it is important to be able to preserve them, so a better knowledge on their behaviour is sought. Furthermore, historic technologies could be used even in modern constructions to build seismic resistant buildings using more natural materials with lesser costs. A great rehabilitation effort is being carried out on this type of buildings, as their neglect has led to decay or their change in use and alterations to the structure has led to the need to retrofit such buildings; only recently studies on their behaviour have become available and only a few of them address the issue of possible strengthening techniques for this kind of walls. In this scope, an innovative retrofitting technique (near surface mounted steel flat bars) is proposed and validated on traditional timber frame walls based on an extensive experimental program. The results of the static cyclic tests on distinct wall typologies retrofitted with the NSM technique are herein presented and discussed in detail. The main features on deformation, lateral stiffness, lateral resistance and seismic performance indexes are analysed

Deploying public surface transit to forward messages in DTN

Delay Tolerant Network (DTN) is a communication architecture enabling connectivity in a topology with unregular end-to-end network connection. DTN enables communication in environments with cross-connectivity, large delays and delivery time variations, and a high error rate. DTN can be used in vehicular networks where public transport get involved. This research aims to analyze the role of public transit as a DTN routing infrastructure. The impact of using public transit as a relay router is investigated by referencing the network performance, defined by its delivery ratio, average delay and overhead. The results show that public transit can be used as a backbone for DTN in an urban scenario using existing protocols. This opens insights for future researches on routing algorithm and protocol design.

Enrollment time as a requirement for biometric hand recognition systems

Biometric systems are increasingly being used as a means for authentication to provide system security in modern technologies. The performance of a biometric system depends on the accuracy, the processing speed, the template size, and the time necessary for enrollment. While much research has focused on the first three factors, enrollment time has not received as much attention. In this work, we present the findings of our research focused upon studying user’s behavior when enrolling in a biometric system. Specifically, we collected information about the user’s availability for enrollment in respect to the hand recognition systems (e.g., hand geometry, palm geometry or any other requiring positioning the hand on an optical scanner). A sample of 19 participants, chosen randomly apart their age, gender, profession and nationality, were used as test subjects in an experiment to study the patience of users enrolling in a biometric hand recognition system.

Evolution of the surface plasmon resonance of Au:TiO2 nanocomposite thin films with annealing temperature

This paper reports on the changes in the structural and morphological features occurring in a particular type of nanocomposite thin-film system, composed of Au nanoparticles (NPs) dispersed in a host TiO2 dielectric matrix. The structural and morphological changes, promoted by in-vacuum annealing experiments of the as-deposited thin films at different temperatures (ranging from 200 to 800 C), resulted in a well-known localized surface plasmon resonance (LSPR) phenomenon, which gave rise to a set of different optical responses that can be tailored for a wide number of applications, including those for optical-based sensors. The results show that the annealing experiments enabled a gradual increase of the mean grain size of the Au NPs (from 2 to 23 nm), and changes in their distributions and separations within the dielectric matrix. For higher annealing temperatures of the as-deposited films, a broad size distribution of Au NPs was found (sizes up to 100 nm). The structural conditions necessary to produce LSPR activity were found to occur for annealing experiments above 300 C, which corresponded to the crystallization of the gold NPs, with an average size strongly dependent on the annealing temperature itself. The main factor for the promotion of LSPR was the growth of gold NPs and their redistribution throughout the host matrix. On the other hand, the host matrix started to crystallize at an annealing temperature of about 500 C, which is an important parameter to explain the shift of the LSPR peak position to longer wavelengths, i.e. a red-shift.

A cost study of common surface finish systems for steel structures

This paper presents part of a study aimed at finding a suitable, yet cost-effective, surface finish for a steel structure subject to the car washing environment and corrosive chemicals. The initial, life cycle and average equivalent annual (AEAC) costs for surface finishing methods were calculated for a steel structure using the LCCC algorithm developed by American Galvanizers Association (AGA). The cost study consisted of 45 common surface finish systems including: hot-dip galvanization (HDG), metallization, acrylic, alkyd and epoxy as well as duplex coatings such as epoxy zinc and inorganic zinc (IOZ). The results show that initial, life cycle and AEAC costs for hot dip galvanization are the lowest among all the other methods, followed by coal tar epoxy painting. The annual average cost of HDG for this structure was estimated about €0.22/m2, while the other cost-effective alternatives were: IOZ, polyurea, epoxy waterborne and IOZ/epoxy duplex coating.

Surface plasmon resonance-coupled photoluminescence and resistive switching behavior of pulsed laser-deposited Ag:SiC nanocermet thin films

In this study, Ag:SiC nanocermets were prepared via rapid thermal annealing (RTA) of pulsed laser-deposited SiC/Ag/SiC trilayers grown on Si substrate. Atomic force microscope images show that silver nanoparticles (Ag NPs) are formed after RTA, and the size of NPs increases with increasing Ag deposition time (t Ag). Sharp dip observed in the reflectance spectra confirmed the existence of Ag surface plasmons (SPs). The infrared transmission spectra showed an intense and broad absorption band around 780–800 cm−1 that can be assigned to Si-C stretching vibration mode. Influence of t Ag on the spectral characteristics of SP-enhanced photoluminescence (PL) and electrical properties of silicon carbide (SiC) films has been investigated. The maximum PL enhancement by 5.5 times for Ag:SiC nanocermets is achieved when t Ag ≈ 50 s. This enhancement is due to the strong resonant coupling between SiC and the SP oscillations of the Ag NPs. Presence of Ag NPs in SiC also induces a forming-free resistive switching with switching ratio of 2 × 10−2. The analysis of I–V curves demonstrates that the trap-controlled space-charge-limited conduction with filamentary model is the governing mechanism for the resistive switching in nanocerment thin films.

Design de superfície biomimética para aplicação em atividades desportivas

Tese de Doutoramento Engenharia Têxtil.

Biochemical and physical surface functionalization of polycaprolactone as a key mediator of osteogenic differentiation and vascularized tissue morphogenesis

Tese de Doutoramento em Engenharia de Tecidos, Medicina Regenerativa e Células Estaminais.

Aspergilli and Penicillia related to the surface of ripening italian grana type cheese and its ripening environment

Information available on the mycoflora associated to ripening Italian “grana type” cheese is very poor. Recently, ochratoxin A (OTA) was detected in samples of packed grated cheese [1]; therefore, the need of information to perform a risk management was highlighted. Moreover, sterigmatocystin (STC) has been reported in cheese and it is considered an emerging problem. Despite the fact that both of them are mycotoxins included in group 2B by IARC [2,3], no European regulation exists. So, the main goal of this work is to give for the first time a general overview about Penicillia and Aspergilli growing on the surface of ripening “grana type” cheese, with particular attention on mycotoxigenic species. To perform this, in 2013 and 2014 crust samples were scratched from ripening grana cheese wheels and also Potato Dextrose Agar plates were exposed to monitor ripening house air. Then, 140 fungal isolates were randomly chosen, purified and monosporic colonies were obtained for their identification at specie level. A polyphasic approach is followed, based on morphological characterisation, toxic extrolites profiling and gene sequencing. The identification is still in progress, but the first results based on the morphological approach showed the presence of mycotoxigenic Aspergilli (Aspergillus flavus and A. versicolor) and various Penicillium species; among them Penicillium chrysogenum, P. implicatum and P. solitum were identified. Only P. chrysogenum was reported to produce the mycotoxins cyclopiazonic acid (CPA) and roquefortine-C (ROQ-C) [4]. These results will be presented and discussed. [1] A. Biancardi, R. Piro, G. Galaverna, C. Dall’Asta, "A simple and reliable liquid chromatography–tandem mass spectrometry method for determination of ochratoxin A in hard cheese" International Journal of Food Sciences and Nutrition 64 (5), 2013, 632 – 640. [2] International Agency for Research on Cancer (IARC) “IARC Monographs on the Evaluation of Carcinogenic Risks to Humans” 31, 1983, 191 – 199. [3] International Agency for Research on Cancer (IARC) “IARC Monographs on the Evaluation of carcinogenic Risks to Humans”, suppl. 7, 1987, 72. [4] J. I. Pitt, D. A. Hocking, “Fungi and Food Spoilage” 1997, 291.