A novel approach for dynamic hand gesture recognition using contour-based similarity images

A novel approach is proposed for the recognition of moving hand gestures based on the representation of hand motions as contour-based similarity images (CBSIs). The CBSI was constructed by calculating the similarity between hand contours in different frames. The input CBSI was then matched with CBSIs in the database to recognize the hand gesture. The proposed continuous hand gesture recognition algorithm can simultaneously divide the continuous gestures into disjointed gestures and recognize them. No restrictive assumptions were considered for the motion of the hand between the disjointed gestures. The proposed algorithm was tested using hand gestures from American Sign Language and the results showed a recognition rate of 91.3% for disjointed gestures and 90.4% for continuous gestures. The experimental results illustrate the efficiency of the algorithm for noisy videos.     

A Novel and Fast Algorithm for Solving Permutation in Convolutive BSS,Based on Real and Imaginary Decomposition

In this paper, a new fast method for solving the permutation problem in convolutive BSS is presented. Typically, by transferring signals to the frequency domain, the convolutive BSS problem is converted to an instantaneous BSS, and deconvolution takes place in each frequency bin. However, another major problem arises which is permutation ambiguity in the frequency domain. Solving the permutation ambiguity for N sources in frequency domain needs N! comparisons between adjacent frequency bins. This drastically increases the overall computational complexity of the convolutive BSS. In our new approach, the complex-valued signals are decomposed into real and imaginary parts in each frequency bin. We show that the ideal mixing matrix has to possess a simple and symmetric structure. Accordingly, the structure can be exploited for solving the permutation ambiguity in frequency domain. Although separation in subband is accomplished by the FastICA algorithm, the proposed method requires modification of the separation algorithm, and a new structure is imposed on the mixing matrix. After that signals are separated by means of the FastICA, the permutation correction takes place only by N comparisons, decreasing the computational complexity. Comparing to five competitive methods, we experimentally demonstrate that permutation ambiguity is resolved accurately by this very fast approach while substantially decreasing the order of calculations. In terms of the separation performance and signal quality, the proposed method is superior to four of the compared methods and almost similar to the best of them.     

Composite Colloidal Gels Made of Bisphosphonate‐Functionalized Gelatin and Bioactive Glass Particles for Regeneration of Osteoporotic Bone Defects

Injectable composite colloidal gels are developed for regeneration of osteoporotic bone defects through a bottom‐up assembly from bisphosphonate‐functionalized gelatin and bioactive glass particles. Upon bisphosphonate functionalization, gelatin nanoparticles show superior adhesion toward bioactive glass particles, resulting in elastic composite gels. By tuning their composition, these composite colloidal gels combine mechanical robustness with self‐healing ability. The composite colloidal gels support cell proliferation and differentiation in vitro without requiring any osteogenic supplement. In vivo evaluation of the composite colloidal gels reveals their capacity to support the regeneration of osteoporotic bone defects. Furthermore, the bisphosphonate modification of gelatin induces a therapeutic effect on the peri‐implantation region by enhancing the bone density of the osteoporotic bone tissue. Consequently, these composite colloidal gels offer new therapeutic opportunities for treatment of osteoporotic bone defects.     

Investigation of shape effect of silver nanostructures and governing physical mechanisms on photo-activity: Zinc oxide/silver plasmonic photocatalyst

Plasmonic composites consisting of silver nanostructures and zinc oxide semiconductor have better photocatalytic performance than pure zinc oxide. To prepare the composites, nanostructures of zinc oxide particles, gold spheres, and three different silver morphology including cubes, spheres, and wires were synthesized. A detailed study of the main mechanisms governing the activity of plasmonic photocatalysts showed that the improvement of photocatalytic performance is attributed to localized surface plasmon resonance-mediated energy transfer from silver to zinc oxide. This mechanism, which is performed using non-radiative (near-field) and radiation (far-field) processes, led to an increase in the concentration of e^?/h⁺ pairs near the semiconductor. We also showed that the increase of the photocatalytic activity depends on the shape of the silver nanostructures in the composites. Our theoretical and experimental studies have shown that composites containing silver cubes have the highest increase of photocatalytic activity compared to other morphologies. The percentage of photocatalytic degradation of methylene blue solution in presence of silver cubes was about 15% higher than that of other morphologies. Therefore, by controlling the shape of noble metal nanostructures, the photocatalytic activity of a semiconductor can be maximized and adjusted.     

A novel forensic image analysis tool for discovering double JPEG compression clues

This paper presents a novel technique to discover double JPEG compression traces. Existing detectors only operate in a scenario that the image under investigation is explicitly available in JPEG format. Consequently, if quantization information of JPEG files is unknown, their performance dramatically degrades. Our method addresses both forensic scenarios which results in a fresh perceptual detection pipeline. We suggest a dimensionality reduction algorithm to visualize behaviors of a big database including various single and double compressed images. Based on intuitions of visualization, three bottom-up, top-down and combined top-down/bottom-up learning strategies are proposed. Our tool discriminates single compressed images from double counterparts, estimates the first quantization in double compression, and localizes tampered regions in a forgery examination. Extensive experiments on three databases demonstrate results are robust among different quality levels. F ₁-measure improvement to the best state-of-the-art approach reaches up to 26.32 %. An implementation of algorithms is available upon request to fellows.     

A HIL Testbed for Initial Controller Gain Tuning of a Small Unmanned Helicopter

A Hardware-In-The-Loop (HIL) testbed design for small unmanned helicopters which provides a safe and low-cost platform to implement control algorithms and tune the control gains in a controlled environment is described. Specifically, it allows for testing the robustness of the controller to external disturbances by emulating the hover condition. A 6-DOF nonlinear mathematical model of the helicopter has been validated in real flight tests. This model is implemented in real-time to estimate the states of the helicopter which are then used to determine the actual control signals on the testbed. Experiments of the longitudinal, lateral and heading control tests are performed. To minimize the structural stress on the fuselage in case of controller failure or a subsystem malfunction, a damping system with a negligible parasitic effect on the dynamics of the helicopter around hover is incorporated. The HIL testbed is capable of testing the helicopter in hover, as well as on any smooth trajectories such as cruise flight, figure-8, etc. Experimentally tuning the controller on the HIL testbed is described and results in a controller which is robust to the external disturbances, and achieves an accuracy of ±2.5 cm in the position control on the longitudinal and lateral trajectory tracking, and ±5 deg accuracy around the yaw axis on the heading trajectory tracking.     

The control point concept for nonlinear trajectory-tracking control of autonomous helicopters with fly-bar

An alternative approach for automatic trajectory-tracking control of small unmanned helicopters with fly-bar is proposed. This approach uses the spatial three-dimensional coordinates of a point on the helicopter's local coordinate frame other than its centre of gravity, called the control point, and the helicopter's yaw angle as four control outputs. The helicopter is assumed to have four independent control inputs. With this choice of control outputs, the helicopter's input–output model becomes a square control system, which opens the possibility of implementation of many robust nonlinear control methods that are suitable for such systems. The helicopter, which has six rigid body degrees of freedom (DOFs), has two underactuated DOFs (UA-DOFs). It is proved that the zero-dynamics of the UA-DOFs are inherently stable, leading to a stable control system. A sliding mode controller is designed for trajectory-tracking of the outputs. It is verified via simulations that the response of the control outputs and UA-DOFs are in fact stable.     

A clustering based feature selection method in spectro-temporal domain for speech recognition

Spectro-temporal representation of speech has become one of the leading signal representation approaches in speech recognition systems in recent years. This representation suffers from high dimensionality of the features space which makes this domain unsuitable for practical speech recognition systems. In this paper, a new clustering based method is proposed for secondary feature selection/extraction in the spectro-temporal domain. In the proposed representation, Gaussian mixture models (GMM) and weighted K-means (WKM) clustering techniques are applied to spectro-temporal domain to reduce the dimensions of the features space. The elements of centroid vectors and covariance matrices of clusters are considered as attributes of the secondary feature vector of each frame. To evaluate the efficiency of the proposed approach, the tests were conducted for new feature vectors on classification of phonemes in main categories of phonemes in TIMIT database. It was shown that by employing the proposed secondary feature vector, a significant improvement was revealed in classification rate of different sets of phonemes comparing with MFCC features. The average achieved improvements in classification rates of voiced plosives comparing to MFCC features is 5.9% using WKM clustering and 6.4% using GMM clustering. The greatest improvement is about 7.4% which is obtained by using WKM clustering in classification of front vowels comparing to MFCC features.