Morteza Daneshmand

Real-time, automatic shape-changing robot adjustment and gender classification

This paper introduces the results of novel theoretical and practical studies aimed at providing automatic and accurate real-time activation and adjustment of shape-changing robots in accord to the shape of the body of the user. The proposed method consists of scanning, classifying the instances according to gender and size, performing analysis on both the user’s body and the prospective garment, which is be virtually fitted, modelling, extracting measurements and assigning reference points on them, segmenting the 3D visual data imported from the shape-changing robot, and finally, superimposing, adopting and depicting the resulting garment model on the user’s body. The estimation process of the positions of the moving actuators for adjusting the shape-changing robots tries to determine which input values could result in the closest representation of the desired sizes and distances through devising the mathematical description of a map relating them to each other. In order to classify the data obtained by the 3D scanner, first maximum likelihood function is used for selecting one of the shape-changing robots, according to the presumed gender and size, to be activated, and subsequently, support vector machine is utilized so as to find out which shape template from the dictionary best matches the scanning instance being considered. As a use case, the proposed method is applied to the visual data obtained by scanning Fits.me’s shape-changing robots using 3D laser scanner. The methods currently used are manual, whereas the proposed method is automatic and the experimental results show that it is the accurate and reliable.

Size-Dictionary Interpolation for Robot’s Adjustment

This paper describes the classification and size-dictionary interpolation of the three-dimensional data obtained by a laser scanner to be used in a realistic virtual fitting room, where automatic activation of the chosen mannequin robot, while several mannequin robots of different genders and sizes are simultaneously connected to the same computer, is also considered to make it mimic the body shapes and sizes instantly. The classification process consists of two layers, dealing, respectively, with gender and size. The interpolation procedure tries to find out which set of the positions of the biologically inspired actuators for activation of the mannequin robots could lead to the closest possible resemblance of the shape of the body of the person having been scanned, through linearly mapping the distances between the subsequent size-templates and the corresponding position set of the bioengineered actuators, and subsequently, calculating the control measures that could maintain the same distance proportions, where minimizing the Euclidean distance between the size-dictionary template vectors and that of the desired body sizes determines the mathematical description. In this research work, the experimental results of the implementation of the proposed method on Fits.me’s mannequin robots are visually illustrated, and explanation of the remaining steps toward completion of the whole realistic online fitting package is provided.

Medical robots with potential applications in participatory and opportunistic remote sensing: A review

Abstract Among numerous applications of medical robotics, this paper concentrates on the design, optimal use and maintenance of the related technologies in the context of healthcare, rehabilitation and assistive robotics, and provides a comprehensive review of the latest advancements in the foregoing field of science and technology, while extensively dealing with the possible applications of participatory and opportunistic mobile sensing in the aforementioned domains. The main motivation for the latter choice is the variety of such applications in the settings having partial contributions to functionalities such as artery, radiosurgery, neurosurgery and vascular intervention. From a broad perspective, the aforementioned applications can be realized via various strategies and devices benefiting from detachable drives, intelligent robots, human-centric sensing and computing, miniature and micro-robots. Throughout the paper tens of subjects, including sensor-fusion, kinematic, dynamic and 3D tissue models are discussed based on the existing literature on the state-of-the-art technologies. In addition, from a managerial perspective, topics such as safety monitoring, security, privacy and evolutionary optimization of the operational efficiency are reviewed.

Real-time, automatic digi-tailor mannequin robot adjustment based on human body classification through supervised learning

Although mannequin robots have been in use in the context of fit advising, most of the modules involved in the process of online try-on still demand manual calculations, operations and adjustments. This article overcomes the latter deficiency, alleviates the time consumption and brings about significant enhancements to the efficiency and reliability of the foregoing service through coming up with a fully automatic solution. Notions and practices aimed at the classification of 3D scanning instances of human body using a laser scanner are explained, along with the subsequent automatic activation of the mannequin robots, upon presentation of the experimental results. The proposed methodology consists in scanning, classifying according to gender and size and performing analysis on the user’s body, modelling and extracting measurements from the 3D visual data imported from the mannequins, and finally, photoshooting the garment being put on the user’s body. In order to classify the data obtained by the 3D scanner, first, maximum likelihood function is used for selecting one of the digi-tailor mannequin robots, according to the presumed gender and size, to be activated, and then support vector machine is utilized so as to find out which shape template from the dictionary best matches the scanning instance being considered. The proposed automatic methodology is also compared with the currently used manual method, and the experimental results easily approve its accuracy and reliability.

Medical image illumination enhancement and sharpening by using stationary wavelet transform

Medical images captured by various devices have different illumination states based on chemicals used by patient prior to scanning. Consider a MRI image which has low contrast or is too bright, hence the experts cannot analysis that image due to poor representation of data in the image. In this paper we are proposing new medical image illumination enhancement and sharpening technique based on stationary wavelet transform which is addressing the aforementioned problem. The technique decomposes the input medical image into the four frequency subbands by using stationary wavelet transformation and enhances the illumination of the low-low subband image, and then it enhanced edges of image by adding the high frequency subbands to the image. The technique is compared with the conventional and state-of-art image illumination enhancement techniques such as histogram equalisation, local histogram equalisation, singular value equalisation, and discrete wavelet transform followed by singular value decomposition contrast enhancement techniques. The experimental results are showing the superiority of the proposed method over the conventional and the state-of-art techniques.

Automatic garment retexturing based on infrared information

This paper introduces a new automatic technique for garment retexturing using a single static image along with the depth and infrared information obtained using the Microsoft Kinect II as the RGB-D acquisition device. First, the garment is segmented out from the image using either the Breadth-First Search algorithm or the semi-automatic procedure provided by the GrabCut method. Then texture domain coordinates are computed for each pixel belonging to the garment using normalised 3D information. Afterwards, shading is applied to the new colours from the texture image. As the main contribution of the proposed method, the latter information is obtained based on extracting a linear map transforming the colour present on the infrared image to that of the RGB colour channels. One of the most important impacts of this strategy is that the resulting retexturing algorithm is colour-, pattern- and lighting-invariant. The experimental results show that it can be used to produce realistic representations, which is substantiated through implementing it under various experimentation scenarios, involving varying lighting intensities and directions. Successful results are accomplished also on video sequences, as well as on images of subjects taking different poses. Based on the Mean Opinion Score analysis conducted on many randomly chosen users, it has been shown to produce more realistic-looking results compared to the existing state-of-the-art methods suggested in the literature. From a wide perspective, the proposed method can be used for retexturing all sorts of segmented surfaces, although the focus of this study is on garment retexturing, and the investigation of the configurations is steered accordingly, since the experiments target an application in the context of virtual fitting rooms. Graphical abstractDisplay Omitted HighlightsDespite state-of-the-art methods, ours does not depend on the brightness of surface.Our method works for garments that already have texture on them.We propose a completely color- and texture-invariant shading system.The manual contribution from the user is minimized by our method.Except for the minimal segmentation interaction, the proposed solution is automatic.

Robust grayscale watermarking technique based on face detection

Due to increase of usage of digital media distributed over the Internet, concerns about security and piracy have emerged. The amount of digital media reproduction has brought a need for content watermarking. In this paper robust grayscale watermarking technique based on face detection is proposed. Face detection algorithm is used to find a face on host image and this part of image is transformed into frequency domain using Discrete Wavelet Transform. Chirp z-transform is applied on low-frequency subband from previous step and LU decomposition is used on the outcome. Diagonal matrix from LU decomposition is further decomposed using Singular Value Decomposition and watermark is embedded into singular values. Numerous experiments are run on that algorithm and results are compared with novel and state-of-the-art techniques. The results show that proposed method has good imperceptibility and robustness characteristics.

Block based image compression technique using rank reduction and wavelet difference reduction

In this paper a new block based lossy image compression technique which is using rank reduction of the image and wavelet difference reduction (WDR) technique, is proposed. Rank reduction is obtained by applying singular value decomposition (SVD). The input image is divided into blocks of equal sizes after which quantization by SVD is carried out on each block followed by WDR technique. Reconstruction is carried out by decompressing each blocks bit streams and then merging all of them to obtain the decompressed image. The visual and quantitative experimental results of the proposed image compression technique are shown and also compared with those of the WDR technique and JPEG2000. From the results of the comparison, the proposed image compression technique outperforms the WDR and JPEG2000 techniques.

Classification of Alzheimer’s Disease and Prediction of Mild Cognitive Impairment Conversion Using Histogram-Based Analysis of Patient-Specific Anatomical Brain Connectivity Networks

In this study, we investigated the early detection of Alzheimers disease (AD) and mild cognitive impairment (MCI) conversion to AD through individual structural connectivity networks using structural magnetic resonance imaging (sMRI) data. In the proposed method, the cortical morphometry of individual gray matter images were used to construct structural connectivity networks. A statistical feature generation approach based on histogram-based feature generation procedure was proposed to represent a statistical-pattern of connectivity networks from a high-dimensional space into low-dimensional feature vectors. The proposed method was evaluated on numerous samples including 61 healthy controls (HC), 42 stable-MCI (sMCI), 45 progressive-MCI (pMCI), and 83 AD subjects at the baseline from the J-ADNI data-set using support vector machine classifier. The proposed method yielded a classification accuracy of 84.17%, 70.38%, and 61.05% in identifying AD/HC, MCIs/HCs, and sMCI/pMCI, respectively. The experimental results show that the proposed method performed in a comparable way to alternative methods using MRI data.

Iterative closest point based 3D object reconstruction using RGB-D acquisition devices

This paper introduces, and verifies the applicability of, a practical algorithm for creating 3D points clouds resembling objects, based on multiple RGB-D frames having been taken from different viewpoints, by the Kinect 2 camera. The experimental set-up is described, along with a certain variant of the process referred to as iterative closest point, being utilized for the latter purpose. Moreover, in order to achieve reliable and realistic representations of the objects, the noise involved in the initial result of the reconstruction procedure is removed through employing a high-pass filter mask, being aimed at detecting and excluding the outliers. The proposed method, based on the experiments whose results are reported in the paper, is computationally less costly than the relevant alternatives suggested in the literature heretofore, which is one of its fundamental contributions when dealing with real-time scenarios. The strengths and weaknesses of the proposed algorithm are discussed according to the results, where objects of various sorts, i.e. with different colors and types of materials and surface, are taken into account and investigated as case-studies.