scholarly journals A Visuo-Haptic Framework for Object Recognition Inspired by Human Tactile Perception

Proceedings ◽  
2019 ◽  
Vol 4 (1) ◽  
pp. 47 ◽  
Author(s):  
Ghazal Rouhafzay ◽  
Ana-Maria Cretu
Keyword(s):  
Support Vector ◽  
Self Organizing Map ◽  
Sensor Surface ◽  
Exploration Process ◽  
3D Objects ◽  
Haptic Exploration ◽  
Eye Fixations ◽  
Virtual Force ◽  
Tactile Image ◽  
Exploratory Procedure

This paper addresses the issue of robotic haptic exploration of 3D objects using an enhanced model of visual attention, where the latter is applied to obtain a sequence of eye fixations on the surface of objects guiding the haptic exploratory procedure. According to psychological studies, somatosensory data resulting as a response to surface changes sensed by human skin are used in combination with kinesthetic cues from muscles and tendons to recognize objects. Drawing inspiration from these findings, a series of five sequential tactile images are obtained by adaptively changing the size of the sensor surface according to the object geometry for each object, from various viewpoints, during an exploration process. We take advantage of the contourlet transform to extract several features from each tactile image. In addition to these somatosensory features, other kinesthetic inputs including the probing locations and the angle of the sensor surface with respect to the object in consecutive contacts are added as features. The dimensionality of the large feature vector is then reduced using a self-organizing map. Overall, 12 features from each sequence are concatenated and used for classification. The proposed framework is applied to a set of four virtual objects and a virtual force sensing resistor array (FSR) is used to capture tactile (haptic) imprints. Trained classifiers are tested to recognize data from new objects belonging to the same categories. Support vector machines yield the highest accuracy of 93.45%.

scholarly journals An Application of Deep Learning to Tactile Data for Object Recognition under Visual Guidance

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1534 ◽  
Author(s):  
Ghazal Rouhafzay ◽  
Ana-Maria Cretu
Keyword(s):  
Object Recognition ◽  
Visual Attention ◽  
Visual Information ◽  
Support Vector ◽  
Sequential Data ◽  
K Nearest Neighbors ◽  
Object A ◽  
Haptic Exploration ◽  
Virtual Force ◽  
Neuroscience Research

Drawing inspiration from haptic exploration of objects by humans, the current work proposes a novel framework for robotic tactile object recognition, where visual information in the form of a set of visually interesting points is employed to guide the process of tactile data acquisition. Neuroscience research confirms the integration of cutaneous data as a response to surface changes sensed by humans with data from joints, muscles, and bones (kinesthetic cues) for object recognition. On the other hand, psychological studies demonstrate that humans tend to follow object contours to perceive their global shape, which leads to object recognition. In compliance with these findings, a series of contours are determined around a set of 24 virtual objects from which bimodal tactile data (kinesthetic and cutaneous) are obtained sequentially and by adaptively changing the size of the sensor surface according to the object geometry for each object. A virtual Force Sensing Resistor array (FSR) is employed to capture cutaneous cues. Two different methods for sequential data classification are then implemented using Convolutional Neural Networks (CNN) and conventional classifiers, including support vector machines and k-nearest neighbors. In the case of conventional classifiers, we exploit contourlet transformation to extract features from tactile images. In the case of CNN, two networks are trained for cutaneous and kinesthetic data and a novel hybrid decision-making strategy is proposed for object recognition. The proposed framework is tested both for contours determined blindly (randomly determined contours of objects) and contours determined using a model of visual attention. Trained classifiers are tested on 4560 new sequential tactile data and the CNN trained over tactile data from object contours selected by the model of visual attention yields an accuracy of 98.97% which is the highest accuracy among other implemented approaches.

Recognition of 3D Objects from 2D Views Features

2015 ◽  
Vol 13 (2) ◽  
pp. 50-58
Author(s):  
R. Khadim ◽  
R. El Ayachi ◽  
Mohamed Fakir
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Nearest Neighbor ◽  
Color Image ◽  
Recognition Rate ◽  
Experimental Results ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
3D Objects ◽  
Color Descriptor

This paper focuses on the recognition of 3D objects using 2D attributes. In order to increase the recognition rate, the present an hybridization of three approaches to calculate the attributes of color image, this hybridization based on the combination of Zernike moments, Gist descriptors and color descriptor (statistical moments). In the classification phase, three methods are adopted: Neural Network (NN), Support Vector Machine (SVM), and k-nearest neighbor (KNN). The database COIL-100 is used in the experimental results.

Fusion on Citrus Image Data from Cold Mirror Acquisition System

2012 ◽  
Vol 2 (4) ◽  
pp. 11-24 ◽  
Author(s):  
Peilin Li ◽  
Sang-Heon Lee ◽  
Hung-Yao Hsu
Keyword(s):  
Near Infrared ◽  
Color Image ◽  
Infrared Image ◽  
Image Data ◽  
Acquisition System ◽  
Support Vector ◽  
Self Organizing Map ◽  
Visible Image ◽  
Low Pass ◽  
Low Dimensional

In this paper, an image fusion is presented to improve the citrus identification by filtering the incoming data from two cameras. The citrus image data has been photographed by using a portable bi-camera cold mirror acquisition system. The prototype of the customized fixture has been manufactured to position and align a classical cold mirror with two CCD cameras in relative kinematic position. The algorithmic registration on the pairwise images has been bypassed by both the spatial alignment of two cameras with recourse of software calibration and the triggering synchronization in temporal during the photographing. The pairwise frames have been fused by using the Daubechies wavelets decomposition filters. The pixel level fusion index rule is proposed to combine the low pass coefficients of the visible image and the low pass coefficients of the near-infrared image convoluted by the complementary of entropy filter from the visible low pass coefficients. In the study, the fused artifact color image and the non-fused color image have been processed and compared by some classification methods such as low dimensional projection, self-organizing map and the support vector machine.

scholarly journals MULTIVARIATE TECHNIQUES FOR IDENTIFYING DIFFRACTIVE INTERACTIONS AT THE LHC

2010 ◽  
Vol 25 (08) ◽  
pp. 1615-1647 ◽  
Author(s):  
MIKAEL KUUSELA ◽  
JERRY W. LÄMSÄ ◽  
ERIC MALMI ◽  
PETTERI MEHTÄLÄ ◽  
RISTO ORAVA
Keyword(s):  
Cross Sections ◽  
Transverse Energy ◽  
Gene Expression Programming ◽  
Relative Rate ◽  
Support Vector ◽  
Forward Physics ◽  
Simple Extension ◽  
Multivariate Techniques ◽  
Self Organizing Map ◽  
Proton Proton

Close to one half of the LHC events are expected to be due to elastic or inelastic diffractive scattering. Still, predictions based on extrapolations of experimental data at lower energies differ by large factors in estimating the relative rate of diffractive event categories at the LHC energies. By identifying diffractive events, detailed studies on proton structure can be carried out.The combined forward physics objects: rapidity gaps, forward multiplicity and transverse energy flows can be used to efficiently classify proton–proton collisions. Data samples recorded by the forward detectors, with a simple extension, will allow first estimates of the single diffractive (SD), double diffractive (DD), central diffractive (CD), and nondiffractive (ND) cross-sections. The approach, which uses the measurement of inelastic activity in forward and central detector systems, is complementary to the detection and measurement of leading beam-like protons.In this investigation, three different multivariate analysis approaches are assessed in classifying forward physics processes at the LHC. It is shown that with gene expression programming, neural networks and support vector machines, diffraction can be efficiently identified within a large sample of simulated proton–proton scattering events. The event characteristics are visualized by using the self-organizing map algorithm.

KERNEL METHODS FOR CLUSTERING: COMPETITIVE LEARNING AND c-MEANS

2006 ◽  
Vol 14 (04) ◽  
pp. 481-493 ◽  
Author(s):  
RYO INOKUCHI ◽  
SADAAKI MIYAMOTO
Keyword(s):  
Computational Complexity ◽  
Kernel Methods ◽  
Clustering Algorithms ◽  
Competitive Learning ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Alternative Formulation ◽  
Self Organizing Map ◽  
Data Set ◽  
High Computational Complexity

Recently kernel methods in support vector machines have widely been used in machine learning algorithms to obtain nonlinear models. Clustering is an unsupervised learning method which divides whole data set into subgroups, and popular clustering algorithms such as c-means are employing kernel methods. Other kernel-based clustering algorithms have been inspired from kernel c-means. However, the formulation of kernel c-means has a high computational complexity. This paper gives an alternative formulation of kernel-based clustering algorithms derived from competitive learning clustering. This new formulation obviously uses sequential updating or on-line learning to avoid high computational complexity. We apply kernel methods to related algorithms: learning vector quantization and self-organizing map. We moreover consider kernel methods for sequential c-means and its fuzzy version by the proposed formulation.

EXPLORING FEATURES AND CLASSIFIERS TO CLASSIFY GENE EXPRESSION PROFILES OF ACUTE LEUKEMIA

2002 ◽  
Vol 16 (07) ◽  
pp. 831-844 ◽  
Author(s):  
SUNG-BAE CHO
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Expression Profiles ◽  
Lymphoblastic Leukemia ◽  
Recognition Rate ◽  
Correlation Coefficients ◽  
Support Vector ◽  
Self Organizing Map ◽  
Backpropagation Neural Network ◽  
Self Organizing

Bioinformatics has recently drawn a lot of attention to efficiently analyze biological genomic information with information technology, especially pattern recognition. In this paper, we attempt to explore extensive features and classifiers through a comparative study of the most promising feature selection methods and machine learning classifiers. The gene information from a patient's marrow expressed by DNA microarray, which is either the acute myeloid leukemia or acute lymphoblastic leukemia, is used to predict the cancer class. Pearson's and Spearman's correlation coefficients, Euclidean distance, cosine coefficient, information gain, mutual information and signal to noise ratio have been used for feature selection. Backpropagation neural network, self-organizing map, structure adaptive self-organizing map, support vector machine, inductive decision tree and k-nearest neighbor have been used for classification. Experimental results indicate that backpropagation neural network with Pearson's correlation coefficients produces the best result, 97.1% of recognition rate on the test data.

Sign in / Sign up

Export Citation Format

Share Document