A STUDY ON CLASSIFIERS ACCURACY FOR HAND POSE RECOGNITION

Similar documents
COSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor

Tri-modal Human Body Segmentation

Classification of objects from Video Data (Group 30)

VARIATION OF INTERNAL FORCES USING ARTIFICIAL NEURONAL NETWORK

Robotics Programming Laboratory

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers

Image Processing. Image Features

Region-based Segmentation

Posture detection by kernel PCA-based manifold learning

Short Survey on Static Hand Gesture Recognition

APPLICATIONS OF MICROSOFT EXCEL - SOLVER FOR HORIZONTAL AND LEVELLING NETWORKS ADJUSTMENT

ImageCLEF 2011

Object Classification Problem

Last week. Multi-Frame Structure from Motion: Multi-View Stereo. Unknown camera viewpoints

Sketchable Histograms of Oriented Gradients for Object Detection

Robot Learning. There are generally three types of robot learning: Learning from data. Learning by demonstration. Reinforcement learning

BOOLEAN FUNCTION DECOMPOSITION BASED ON FPGA BASIC CELL STRUCTURE

The Novel Approach for 3D Face Recognition Using Simple Preprocessing Method

Investigating the Effect of Different Kernel Functions on the Performance of SVM for Recognizing Arabic Characters

Random Forest A. Fornaser

Enhancing Forestry Object Detection using Multiple Features

10-701/15-781, Fall 2006, Final

Robust PDF Table Locator

CS 229 Midterm Review

Facial Expression Classification with Random Filters Feature Extraction

CS231A Course Project Final Report Sign Language Recognition with Unsupervised Feature Learning

Tracking system. Danica Kragic. Object Recognition & Model Based Tracking

Data mining with Support Vector Machine

Face Recognition Using Vector Quantization Histogram and Support Vector Machine Classifier Rong-sheng LI, Fei-fei LEE *, Yan YAN and Qiu CHEN

Face detection and recognition. Detection Recognition Sally

Hand Gesture Extraction by Active Shape Models

Information theory methods for feature selection

Exploring Curve Fitting for Fingers in Egocentric Images

Biometrics Technology: Image Processing & Pattern Recognition (by Dr. Dickson Tong)

Probabilistic Facial Feature Extraction Using Joint Distribution of Location and Texture Information

Announcements. Recognition I. Gradient Space (p,q) What is the reflectance map?

AUTONOMOUS ROBOT NAVIGATION BASED ON FUZZY LOGIC AND REINFORCEMENT LEARNING

Hand gesture recognition with Leap Motion and Kinect devices

Fast or furious? - User analysis of SF Express Inc

Transfer Forest Based on Covariate Shift

HISTOGRAMS OF ORIENTATIO N GRADIENTS

Computer Science Faculty, Bandar Lampung University, Bandar Lampung, Indonesia

Methods for Intelligent Systems

Pattern Recognition. Kjell Elenius. Speech, Music and Hearing KTH. March 29, 2007 Speech recognition

Discriminative classifiers for image recognition

CIS 520, Machine Learning, Fall 2015: Assignment 7 Due: Mon, Nov 16, :59pm, PDF to Canvas [100 points]

Credit card Fraud Detection using Predictive Modeling: a Review

Kernel PCA of HOG features for posture detection

MIT 801. Machine Learning I. [Presented by Anna Bosman] 16 February 2018

3D Perception. CS 4495 Computer Vision K. Hawkins. CS 4495 Computer Vision. 3D Perception. Kelsey Hawkins Robotics

Classifying Images with Visual/Textual Cues. By Steven Kappes and Yan Cao

Introduction to object recognition. Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and others

Task analysis based on observing hands and objects by vision

ABOUT MANUFACTURING PROCESSES CAPABILITY ANALYSIS

CSE 158. Web Mining and Recommender Systems. Midterm recap

2. Data Preprocessing

Verification: is that a lamp? What do we mean by recognition? Recognition. Recognition

Business Club. Decision Trees

CHECKING THE HOMOGENEITY OF CONCRETE USING ARTIFICIAL NEURAL NETWORK

What do we mean by recognition?

Decision Trees Dr. G. Bharadwaja Kumar VIT Chennai

[2008] IEEE. Reprinted, with permission, from [Yan Chen, Qiang Wu, Xiangjian He, Wenjing Jia,Tom Hintz, A Modified Mahalanobis Distance for Human

Large-Scale Traffic Sign Recognition based on Local Features and Color Segmentation

A Novel Extreme Point Selection Algorithm in SIFT

MAC LEVEL BASED QUALITY OF SERVICE MANAGEMENT IN IEEE NETWORKS

Part-based and local feature models for generic object recognition

EE 701 ROBOT VISION. Segmentation

MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION

Louis Fourrier Fabien Gaie Thomas Rolf

Model-based Visual Tracking:

CS229: Action Recognition in Tennis

Integral Channel Features with Random Forest for 3D Facial Landmark Detection

Patch-based Object Recognition. Basic Idea

Face detection and recognition. Many slides adapted from K. Grauman and D. Lowe

MODELING THE FORCE-ELONGATION CURVE OF SINGLE YARNS

Hand part classification using single depth images

Estimating normal vectors and curvatures by centroid weights

SUPPLEMENTARY FILE S1: 3D AIRWAY TUBE RECONSTRUCTION AND CELL-BASED MECHANICAL MODEL. RELATED TO FIGURE 1, FIGURE 7, AND STAR METHODS.

The SIFT (Scale Invariant Feature

3D Models and Matching

3D object recognition used by team robotto

A method for depth-based hand tracing

Beyond Bags of Features

Network Traffic Measurements and Analysis

CS 231A CA Session: Problem Set 4 Review. Kevin Chen May 13, 2016

Equation to LaTeX. Abhinav Rastogi, Sevy Harris. I. Introduction. Segmentation.

Classification/Regression Trees and Random Forests

3. Data Preprocessing. 3.1 Introduction

Facial expression recognition using shape and texture information

Face recognition based on improved BP neural network

8. Tree-based approaches

Subpixel Corner Detection Using Spatial Moment 1)

Cellular Tree Classifiers. Gérard Biau & Luc Devroye

Network Traffic Measurements and Analysis

ECE 285 Class Project Report

Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels

MULTIVARIATE TEXTURE DISCRIMINATION USING A PRINCIPAL GEODESIC CLASSIFIER

The Curse of Dimensionality

Fast Edge Detection Using Structured Forests

Face Detection and Recognition in an Image Sequence using Eigenedginess

Transcription:

BULETINUL INSTITUTULUI POLITEHNIC DIN IAŞI Publicat de Universitatea Tehnică Gheorghe Asachi din Iaşi Tomul LIX (LXIII), Fasc. 2, 2013 SecŃia AUTOMATICĂ şi CALCULATOARE A STUDY ON CLASSIFIERS ACCURACY FOR HAND POSE RECOGNITION BY CONSTANTINA RALUCA MIHALACHE and BOGDAN APOSTOL * Gheorghe Asachi Technical University of Iaşi, Faculty of Automatic Control and Computer Engineering Received: May 17, 2013 Accepted for publication: June 21, 2013 Abstract. This paper presents a comparative study between accuracy rates obtained by using different classification architectures for hand pose estimation in RGB-D data. The segmentation of a hand pose is optimized by using depth data in correlation with the grey scale image obtained from a Kinect sensor. We define an observation model composed of feature vectors obtained by calculating the histograms of oriented gradients on colour and depth data and also fingertip positions. A contour tracking algorithm is applied to track the contour of the hand and find the fingertip positions. The most relevant features from the observation model are selected and are served as input to all the classifiers. For this work we have considered Linear, Random Forest (RF), Support Vector Machine (SVM) and Decision Trees (DT) classifiers for posture classification. Experimental results show a 84.18% recognition accuracy is achieved by using the RF classifier, a 79.29% recognition accuracy is achieved using the DT classifier and a 78.27% recognition accuracy for SVM classifier. The multinomial regression is also used for classification purpose but shows a poor 44.26% recognition accuracy. Key words: hand pose recognition, RGB-D, Kinect, histogram of oriented gradients (HOG) features, decision tree, random forest, support vector machines (SVM), linear. 2010 Mathematics Subject Classification: 65D18, 68T05. * Corresponding authors; e-mail: bogdan.apostol@tuiasi.ro

70 Constantina Raluca Mihalache and Bogdan Apostol 1. Introduction The last few years witnessed an increasing interest in the field of Human Computer Interaction (HCI). Between the wide varieties of hand posture recognition techniques, marker less visual based recognition has brought to us non-restrictive systems for HCI (Rautaray & Agrawal, 2012). With the release of the Kinect sensor in 2010 the capturing of scene colour and depth data has become affordable. The device opens whole new opportunities for applications in the domain of computer vision and pattern recognition. These techniques have applications in sign language recognition, gestural communication and device automatic controlling. Classification of hand gestures is the problem of taking a given hand observation model for an instance whose category is unknown and finding a category that the model is closest to. Based on features extracted from the current model and the data learned from the training set a prediction is done for the current instance. The classification process is the last operation that a recognition system performs. Before classification we need to make an initial segmentation to extract the region of interest, correlate depth and colour data, extract hand features from the selected region and decide which features are the most relevant to the recognition process. In this paper we compare the classification accuracy of four different classifiers applied for the same dataset. The dataset contains features extracted for four different hand poses and a wide variety of camera angles. a b c d Fig. 1 Four hand poses classes contained by the training dataset: a open hand, b peace sign, c ok pose, d like sign. The considered hand gestures are: open hand pose, peace pose, like pose and ok pose, as it is shown in Fig. 1. Decision Trees, Random Forests, Support Vector Machines and Multinomial Regression machine learning approaches are used for comparison purposes. The reminder of this paper is as follows: Section II explains the details of calculating and selecting the most important feature vectors obtained through fingertip recognition and calculating the histogram of gradients (HOG) on both colour and depth data; Section III reviews the four hand pose classification

Bul. Inst. Polit. Iaşi, t. LIX (LXIII), f. 2, 2013 71 techniques that we have chosen for our study; Section IV describes the setup for each classifier and compares the accuracy rates obtained through experiments run on the same feature dataset and Section V concludes with a summary and discussion. 2. Feature Extraction from RGB-D Data The input of the classification algorithm is represented by a set of the most important features extracted from the raw video data. The RGB-D format of the stream input captured by a Microsoft Windows Kinect sensor combines visual (RGB colours) and geometric information (depth) in a synchronized format that provides us with the possibility of extracting features from both. Segmentation is an important first step in the process of feature extraction, as it eliminates the background and keeps just the tracked object. In this paper we do a segmentation based only on the depth data and create a validity mask that can be applied on both depth and colour data to extract the hand region. From the segmented data we extract fingertip positions and features that characterize the local appearance of the hand. We track the contour of the hand in the valid depth data by classifying the pixels correspondent to the validity mask in either interior pixels or contour pixels. Contour tracking of objects in binary images is a well-known subject and solutions such as in (Ren et al., 2002; Chang et al., 2004; Yan & Min, 2011) scan the images pixel by pixel in different directions to find the pixels in the contours and have different starting points. In this paper we start bottom up and scan each line of the image for a valid contour point. A valid contour point is a point that has at least another point that is not in the validity mask and thus is an exterior point. After finding the first contour point we use a 3 3 neighbourhood to look for the next pixel of the contour. Once this is found we add it to an ordered list and keep the search direction of the last valid contour point. A k curvature algorithm similar to the one in (Ryan, 2012) is used to find the curves along the tracked contour of the hand. For each point P i that is a valid contour point the algorithm chooses to points P i k and P i+k and calculates the angle ω between them. We consider that P i is a valid curve point if ω is smaller than an empirically chosen value. In this paper we have used a k value of 20 and a ω value of 0.87 radians. The curvature points found are not all fingertip positions and these points can also correspond to valleys in the contour of the hand. We decide if a point is a fingertip by calculating the bisect between the P i P i k and P i P i+k, and choosing the ones for which the bisect points to the interior of the hand, see Fig. 2. Methods like Harris-Corner detection, Scale Invariant Feature Transform (SIFT), and Histograms of oriented gradients (HOG) successfully extract features from visual data by aggregating gradients. These methods split the grayscale images into equal regions and apply masks to calculate gradients orientations.

72 Constantina Raluca Mihalache and Bogdan Apostol Fig. 2 Choosing fingertips by calculating bisect orientation of curvature points. We calculate two sets of features corresponding to both visual and geometric data. From the colour image we obtain a grayscale image on which we compute HOG feature vectors. In order to obtain a well-defined grayscale image on which to apply HOG feature extraction we have to apply a transformation on the depth data. A Cumulative Distribution Function (CDF) is used to make a normal distribution of the depth values and represent them in a grayscale image. For the tests in this paper we split the grayscale images obtained from both colour and depth source into 6 6 pixel cells, organized in blocks composed of 3 3 cells and quantize all the gradient directions in the image into 9 valid directions (Mihalache & Apostol, 2013). We reduce the dimensionality of the HOG features extracted from RGB-D data and remove redundant features by using a Kernel Principal Component Analysis (KPCA) method. This method performs better than linear PCA as it ignores noise from input features and removes noise from test features by projecting the data onto the manifold (Cheng et al., 2009). For the experiments conducted in this paper we used a Gaussian Radial Basis Function (RBF) with a value for σ of 0.223. Similar to (Oikonomidis et al., 2011) we define the observation model that feeds the rest of the algorithm composed of two arrays containing the selection of the most important HOG features from the segmented image of the hand and the corresponding valid depth map, and an array of fingertip positions. 3. Hand Pose Recognition Classifiers From last few years, the task of hand pose recognition are extensively studied and rapid progress seems in this area, including the machine learning approaches such as Decision Trees, Random Forests, Support Vector Machines, and Liniar Multinomial Regression.

Bul. Inst. Polit. Iaşi, t. LIX (LXIII), f. 2, 2013 73 In this section we will detail the proposed method of handpose estimation using above mentioned classifiers and clearly present the training and testing steps. The training phase consists of three steps: (1) get RGB images and their associated depth information for different m hand poses from Kinect sensor, (2) reducing obtained HOG features of both colour and depth images using KPCA, (3) building input patterns and train the classifier. Training patterns are presented according our observation model where we define the set of p training patterns over m hand poses as I train = {O ij }, j= 1, m, i= 1, p. As we apply a supervised learning method for each used classifier we split this training set into m classes corresponding to the number of considered hand poses (Fig. 1). A training pattern that is considered an input in the trained classifier is a vector that results by applying KPCA on the HOG. We choose the set of l rgb (l rgb < n rgb ) and the set of l d (l d < n d ) eigenvectors which have the l rgb and l d largest eigenvalues (l rgb and n rgb, l d and n d are the number l of the largest eigenvalues and thedimension of the covariance matrix for the colour and depth HOG features, respective). Proposed pattern representation includes the first l rgb and l d principal components of HOG data applied on i th colour and depth image, respective. The last element in our training pattern is represented by the positions of identified fingers. The trained model is tested on q testing patterns (I test = {O ij }, j= 1, m, i= 1, q, q >> p) over the same m hand poses. Testing is made offline and for each received image from Kinect sensor an observation model is created in order to estimate its hand position. 3.1. Decision Trees Decision trees traditional algorithm is based on the recursive partitioning greedy algorithm which builds a decision tree in a top-down manner. The algorithm starts with the original set X as the root node, iterates through each unused attribute of the set X and computes the information gain IG, where IG(Y X) = H(Y) H(Y X). The information gain is obtained by deducting conditional entropy H(Y X) of the given attribute with the total entropy H(X): m n p( yi, x j ) H( Y X) = p( yi, x j ) log i= 1 j= 1 p( x j ) (1) n H X = p x p x (2) ( ) ( ) log ( ( )) i= 1 i i

74 Constantina Raluca Mihalache and Bogdan Apostol The method used for attribute selection is minimizing the value of entropy and maximizing the information gain. The process of decision tree generation by repeatedly splitting on attributes is equivalent to partitioning the initial training set into smaller training set, until the entropy of each of these subsets is zero. At any stage of this process, splitting on any attribute has the property that the average entropy of the resulting subsets will be less than that of the previous training set. Gain ratio (GR) heuristics (uncertainty coefficient) can also be used for choosing best feature and is calculated by dividing its information gain IG with its information value IV. n IV Y X = p( y, x ) log p( y, x ) (3) ( ) j ( j ) j= 1 ( Y X) GR ( X) ( X) = IG Y IV Y (4) 3.2. Random Forests Random forests are an ensemble learning method for classification that operate by building a collection of decision trees at training time and outputting the class that is the mode of the classes output by individual trees. Let n pairs of random variables (X, Y), (X 1, Z 1 ),, (X n, Z n ), where X d is a feature vector that takes its values in R and Y (the label) is a binary {0; 1}- valued random variable. We define a random forest (Biau et al., 2008), with m trees a classifier consisting of a set of randomized base tree classifiers g n (x, Z 1 ),, g n (x, Z m ) which are identically distributed random vectors, independent conditionally on X, Y and D n, where D n is a training dataset and is the collection (X 1, Z 1 ),, (X n, Z n ). The randomizing variable shows how the successive cuts are performed when building the tree such as selection of the node and the coordinate to split, as well as the position of the split. The random forest classifier takes a majority vote among the random tree classifiers. If m is large, the random forest classifier is well approximated by the averaged classifier. A random tree classifier g n (x, Z) is constructed as follows. All nodes of the tree are associated with rectangular cells such that at each step of the construction of the tree, the collection of cells associated with the leaves of the forms a partition of [0,1] d. The root of the random tree is [0,1] d itself. At each step of the construction of the tree, a leaf is chosen uniformly at random. The split variable J is then selected uniformly at random from the d candidates x (1),, x (d). Finally, the selected cell is split along the randomly chosen variable at a random location, chosen according to a uniform random variable on the length of the chosen side of the selected cell. The procedure is repeated k times, where k 1 is a deterministic parameter, fixed before hand by the user, and

Bul. Inst. Polit. Iaşi, t. LIX (LXIII), f. 2, 2013 75 possibly depending on n. The randomized classifier g n (x, Z) takes a majority vote among all Y i for which the corresponding feature vector X i falls in the same cell of the random partition as x. 3.3. Support Vector Machines Support vector machines are supervised learning models with associated learning algorithms that analyze data and recognize patterns, used for classification analysis (Cheng et al., 2009). n Given a set of training patterns (x 1, y 1 ),, (x n, y n ) in R R, according to undefined probability distribution P(x, y), and an error function V(y, f(x)) where f(x) is the predicted output instead of ideal output y for the input x our problem consists in finding the function f that minimizes the error: n V( y, f ( x) ) P( x, y) dxd y (5) 1 Having non-linear separable training patterns we map them using a Ф(x) kernel function into a higher dimension space in order to make them linearly separable. The goal of SVM is to find a hyper plane w x b = 0, which separates the two different samples accurately by maximizing the bilateral blank area 1 2 1 2 w maximum. Thus, our problem resumes to, min Φ ( w) = w = w w where yi ( w xi b) 1, i= 1, n. 2 2 3.4. Multinomial Regression The generalized linear modeling technique of multinomial logistic regression can be used to model unordered categorical response variables. Multinomial Regression is useful for situations in which is desired to classify subjects based on values of a set of predictor variables. This type of regression is similar to logistic regression, but it is more general because the dependent variable is not restricted to two categories. Parameter estimation is performed through an iterative maximum-likelihood algorithm. Let the response variable Y have r categories, and X 1,, X k be explanatory variables, y i = (y i1,, y ir ) be the response values in i th subgroup having multinomial distribution M n = (n i, ρ i1,, ρ ir ), β j = (β 0j, β 1j,, β kj )' be regression coefficients for the j th response category with respect to the j* th (reference) one, and x i = (x i1,, x ik )' be actual values of explanatory variables for the i th subgroup, then general multinomial regression model is:

76 Constantina Raluca Mihalache and Bogdan Apostol p log p ij ij * = xi β j, * j j (6) and log-likelihood function is: l( β ) = log + y log( p ), β = β, j= 1,..., r, j j n n r y i! r i 1 y! = i 1 j 1 j 1 ij = = = ij ij j * ( ) (7) 4. Experimental Results This section will present some experimental hand pose estimation results that are obtained by applying the classifiers described in the previous sections. We compare the accuracy rates of four different classification algorithms which are: Decision Trees, Random Forests, Support Vector Machines and Linear (Multinomial Regression). The performance of the classification algorithms is affected by the quality of data source. Features that are redundant or are irrelevant to hand pose estimation are already taken out through a previous KPCA filtration. The same definite set of filtered features is fed to each of the classification algorithms. In this paper we used features obtained from 1000 RGB-D images for building the training set and an additional set of 300 RGB-D images for the testing data. Images contain four different valid postures of the hand (open hand, peace sign, ok pose, like sign) and also images that show no hand object. Experimental results were obtained by using the Rattle library from R (Zhao, 2012). The Rattle package provides a graphical user interface for data mining that uses the R language. The optimal parameters were chosen empirically and are: a) 20 min splits, 10 min buckets, 30 max depth and a complexity of 0.01 for Decision Trees classifier; b) 400 trees, a number of 10 variables tried at each split for Random Forests classifier; c) Gaussian Radial Basis kernel function, a value of 0.06 for sigma and a cost=1 for Support Vector Machine classifier; d) 1000 max iterations for Linear classifier; We can see the performance of these four algorithms by looking at the confusion matrixes shown in Tables 1 4 for the tests conducted for each of the classifiers on the test dataset.

Bul. Inst. Polit. Iaşi, t. LIX (LXIII), f. 2, 2013 77 Actual Actual Actual Actual Table 1 Confusion Matrix for Decision Trees Classifier Predicted Open Peace Like OK pose pose pose pose Accuracy Open pose 28 0 0 0 100% Peace pose 0 22 3 0 88% Like pose 0 2 22 0 91.67% OK pose 3 9 3 9 37.5% Average 79.29% Table 2 Confusion Matrix for Random Forest Classifier Predicted Open Peace Like OK pose pose pose pose Accuracy Open pose 28 0 0 0 100% Peace pose 0 25 0 0 100% Like pose 0 3 16 3 72.73% OK pose 0 6 3 16 64% Average 84.18% Table 3 Confusion Matrix for Support Vector Machines Classifier Predicted Open Peace Like OK pose pose pose pose Accuracy Open pose 28 0 0 0 100% Peace pose 0 25 0 0 100% Like pose 0 10 11 0 52.38% OK pose 0 8 3 17 60.71% Average 78.27% Table 4 Confusion Matrix for Linear (Multinomial Regression) Classifier Predicted Open Peace Like OK pose pose pose pose Accuracy Open pose 28 0 0 0 100% Peace pose 0 9 0 16 36% Like pose 0 9 6 6 28.57% OK pose 6 12 3 3 12.5% Average 44.26%

78 Constantina Raluca Mihalache and Bogdan Apostol We can see in Fig. 3 a comparative representation of accuracy detection rates for all classifiers and each hand pose. One can easily see that all classifiers obtain 100% accuracy rates for open hand pose. Both peace hand pose and ok pose are best detected by SVM and RF classifiers, while like pose is best detected by DT and RF classifiers. Fig. 3 Accuracy detection rates for each hand pose. Fig. 4 shows the average accuracy rates of the compared classifiers. As figures shows the Random Forest classifier obtains the best average recognition rate. Fig. 4 Comparison of classifiers average accuracy rates.

Bul. Inst. Polit. Iaşi, t. LIX (LXIII), f. 2, 2013 79 3. Conclusions In this paper we presented a comparative study on four well known classifiers for pattern recognition. We applied these algorithms on the same dataset with application in the domain of hand gesture recognition. As we previously detailed we used four hand gesture classes and compared the accuracy rates for each pose recognition and the overall accuracy rates. In the process of creating the dataset we used RGB-D data from a Kinect sensor and extracted features from both hand shape and aspect. By applying KPCA algorithm we chose the most relevant features from the multitude of extracted HOG features from both colour and depth images. Experimental results show a 84.18% recognition accuracy is achieved by using the RF classifier, a 79.29% recognition accuracy is achieved using the DT classifier and a 78.27% recognition accuracy for SVM classifier. The multinomial regression is also used for classification purpose but shows a poor 44.26% recognition accuracy. It is shown that random forest classifier outperforms the other three algorithms. REFERENCES Biau G., Devroye L., Lugosi G., Consistency of Random Forests and Other Averaging Classifier. The Journal of Machine Learning Research, 9, 2015 2033, 6/1/2008. Chang F., Chen C., Lu C., A Linear-Time Component-Labelling Algorithm Using Contour Tracing Technique. Computer Vision and Image Understanding, 206 220, 2004. Cheng P., Li W., Ogunbona P., Kernel PCA of HOG Features for Posture Detection. International Conference: Image and Vision Computing New Zealand, 415 420, 2009. Mihalache C.R., Apostol B., Hand Pose Estimation Using HOG Features From RGB-D Data. In System Theory, Control and Computing (ICSTCC), 2013 17th International Conference on, 2013. Oikonomidis I., Kyriazis N., Argyros A., Efficient Model-Based 3D Tracking of Hand Articulations Using Kinect. Proceedings of the British Machine Vision Conference, 1-11, 2011. Rautaray S.S., Agrawal A., Vision Based Hand Gesture Recognition for Human Computer Interaction: a Survey. Artificial Intelligence Review, 1 54, 2012. Ren M., Yang J., Sun H., Tracing Boundary Contours in a Binary Image. Image and Vision Computing. 125 131, 2002. Ryan D.J., Finger and Gesture Recognition with Microsoft Kinect. Master s Thesis in Computer Science (TN-IDE), 2012. Yan L., Min Z., A New Contour Tracing Automaton in Binary Image. 2011 IEEE International Conference on Computer Scienceand Automation Engineering (CSAE), 577 581, 2011.

80 Constantina Raluca Mihalache and Bogdan Apostol Zhao Y., R and Data Mining: Examples and Case Studies. Published by Elsevier in December 2012. STUDIU PRIVIND PRECIZIA CLASIFICATORILOR PENTRU RECUNOAŞTEREA POSTURII MÂINII (Rezumat) În ultimii ani interacńiunea om-calculator (HCI) a devenit un domeniu de interes tot mai studiat. Captarea secvenńelor video precum şi corelarea acestora cu informańiile de adâncime (RGB-D) au devenit accesibile odată cu lansarea în 2010 a senzorului Kinect. Această lucrare prezintă un studiu comparativ între preciziile obńinute la testare prin aplicarea mai multor tehnici de clasificare folosind date ce reprezintă caracterisiticile extrase din informańii de tip RGB-D. Se defineşte un model de observare format din vectori de caracteristici obńinuńi prin calculul histogramelor orientărilor gradienńilor (HOG) atât pe datele de culoare cât şi pe datele de adâncime. Tot în acest model se introduc şi informańii despre numărul şi pozińia degetelor. Sunt selectate cele mai importante caracteristici ale modelului de observare şi utilizate ca date de intrare pentru fiecare dintre clasificatorii considerańi. În această lucrare s-au considerat următorii clasificatori pentru recunoaşterea posturii mâinii: Linear, Random Forests (RF), Support Vector Machines (SVM) şi Decision Trees (DT). Rezultatele experimentale arată o precizie de recunoaştere de 84,18% prin utilizarea clasificatorului RF, o precizie de recunoaştere de 79,29% pentru clasificatorul DT şi o precizie de recunoaştere 78,27% pentru clasificatorul SVM. Se utilizează, de asemenea, un clasificator liniar care obńine o precizie de recunoaştere de doar 44,26%.