A Comparative Study of Conventional and Neural Network Classification of Multispectral Data

Size: px
Start display at page:

Download "A Comparative Study of Conventional and Neural Network Classification of Multispectral Data"

Transcription

1 A Comparative Study of Conventional and Neural Network Classification of Multispectral Data B.Solaiman & M.C.Mouchot Ecole Nationale Supérieure des Télécommunications de Bretagne B.P. 832, BREST Cedex FRANCE Tel: (33) , Fax: (33) ABSTRACT In this study, the classification of remotely sensed data using several classifiers and neural networks is considered. The application was conducted using a test scene containing mainly agricultural areas. The main result obtained in this study is that the application of topological map based neural networks to classify the intensity vectors issued from agricultural classes are more suited than other neural network methods, especially the Multi Layer Perceptron (MLP) usually employed. Obtained results are very close to those of the Maximum Likelihood Classifier (MLC). INTRODUCTION The aim of remotely sensed data classification is to produce the best accuracy map of the earth surface assigning each pixel (using the corresponding feature vector) to its appropriate category of the real-world. Among all supervised non contextual classification methods (K-means, K-Nearest Neighbours,...), the Maximum Likelihood Classifier (MLC) based on Gaussian probability distribution functions for the probability estimation in the discriminate function is considered to be the best in the sense of obtaining optimal recognition rates [Schowengerdt,1983]-[Mather,1989]. Recently, the application of neural networks to the classification of multispectral sensed images is increasingly emerging. This is due to the following characteristics : 1) their ability of learning provides an interesting alternative to the MLC, 2) they make no assumptions about the probabilistic model to be made, 3) they are capable of forming highly non-linear decision boundaries in the feature space and therefore, they have the potential of outperforming a parametric Bayes classifier when a feature statistics deviate significantly from the assumed Gaussian statistics. In this study, the application of several conventional classifiers as well as several neural methods to the classification of multispectral remotely sensed data is considered. The main objectives of this work are :1) to compare the results obtained using two learning data bases, 2) to study the performances of several neural classification methods especially those based on the use of clustering approaches : the Learning Vector Quantization 2 (LVQ2) [Kohonen,1989], the Kohonen Self Organisation Feature Maps (SOFM) [Kohonen,1989] and the Hybrid Learning Vector Quantization [Solaiman,1994] networks. Obtained results using these different classifiers are discussed in terms of recognition rate as well as on their generalisation capability on the whole image. This generalisation capability is essentially evaluated by visualising the reconstructed images. LEARNING DATA BASES AND CLASSIFIERS DESCRIPTION In this work, a LANDSAT Thematic Mapper (TM) sub-scene ( 512x512 pixels ) acquired over the Canadian province of Saskatchewan is studied. The satellite data and the associated ground truth are a courtesy of Canada Centre for Remote Sensing. Among the 7 bands of the TM data only the first 5 were kept for processing through this study. Covering most of the visible and the near infra-red spectrum they tend to provide a good discrimination of the different types of land use.

2 This test area land contains mainly the agricultural category. The main goal is then to discriminate between different sorts of cultures. Two data bases are used in this study. The first one (BASE1), is issued from the ground truth analysis where 8 classes are defined. These classes are : water, humid area, wheat, flax, peas, barley, canary grass and summer fallow. The second data base (BASE2) is obtained by analysing the ground truth information and by observing the spectral intensities associated with different classes in the five spectral bands. This leads to the division of the following classes into several subclasses: class wheat (divided into 5 subclasses), class barley and the class peas (each one is divided into two subclasses). So, BASE2 is considered to represent 14 classes. Each pixel in these data bases is characterised by a vector (spectral vector) containing the five observed spectral intensities. In this study, several classification methods were tested over these two data bases. These methods are : the K-means (K-M), the K-Nearest Neighbours (K-NN), the maximum likelihood (MLC), the MLP network, the LVQ2, the Kohonen SOFM and the HLVQ classifiers. The K-means is a clustering method based on the determination of K centroïds (vector). Each centroïd is considered as a prototype vector of one class. The classification of a spectral vector is based on the Euclidean distance between this vector and the K prototype vectors. The K-Nearest Neighbour classification method of a pixel starts by determining the K nearest spectral vectors from the learning data base. The classification decision is given as the class that is mostly represented in the set of the nearest K spectral vectors. The MLC method is based on a Gaussian probability distribution function for the probability estimation in the discriminate function. Several neural classification methods are used in this study. The Multi Layer Perceptron classifier using the supervised Back-Propagation learning algorithm [Lippman,1987] is the most commonly neural network used into the classification of multispectral data. The LVQ2 network, is a competitive neural network using a supervised learning algorithm. This algorithm is described as follows: when a spectral vector is fed to the network, the two nearest (the winning and the next winning) neurons are determined. The adaptation of the synaptic weights of these two neurons is carried out only if the three following conditions are verified : 1) the class corresponding to the winning neuron is not the same as the class of the input vector, 2) the class corresponding to the next winning neuron is the same as the class of the input vector, 3) the input vector is very close to the discriminating surface between the two classes of the winning and the next winning neurons. The Kohonen SOFMs are generally used as non supervised classification methods permitting the determination of homogeneous categories in the input data space. Since they use a non supervised learning algorithm, their performances in classification problems are generally lower than the MLP classification method. The HLVQ neural network is a Kohonen SOFM using a hybrid non-supervised/supervised learning algorithm based on the combined use of the non-supervised learning algorithm of the SOFMs and the supervised LVQ2 algorithm. The main objective of this network is to obtain high recognition classification rates, while preserving the topology mapping of the SOFM. CLASSIFICATION RESULTS The first simulation was conducted over the data base : BASE2 containing the 14 classes. Each class was represented by 100 pixels. In the K-means (K-M) classifier, K=14 centroïds were used. Only one nearest neighbour (K=1) was used on the K-NN classifier. Concerning the MLP neural network, optimal results in terms of recognition rates using the test data base were obtained with one hidden layer containing 35 neurons. This network was trained using the classical back propagation algorithm. 2

3 The last three neural networks used in this study (LVQ2, the Kohonen SOFM and the HLVQ networks) were tested using a two dimensional 8x8 map with the same initialisation values for the synaptic weights. For the LVQ2 network, the notion of the topological map makes no sense because all competitive neurones act without topological relations. So, the LVQ2 network is considered as using 64 competitive neurons. The stop-learning criteria used was the achievement of a stable synaptic weights. Results obtained in terms of mean recognition rates for the seven different classifiers using the test data base are given in TABLE 1.: TABLE 1. Mean recognition rate of different classifiers using the data base BASE2 K-M K-NN MLC MLP LVQ2 Kohonen HLVQ 77.8% 56.7% 94.5% 81% 76.1% 89.3% 94.8% These results are very general and do not give a precise description of the capability of each classifier concerning each of the 14 classes. Nevertheless, the following remarks can be given : 1) classification results in terms of mean recognition rate of the MLP network, which is a decisionsurface based classifier, are nearly 10% less than those of the MLC and the topological maps used by the Kohonen SOFM and the HLVQ networks. This means that the multi spectral data representing agricultural areas are organised in some cluster forms in the input space. In fact, using the Principal Component Analysis by making the projection of the spectral vectors into the plane formed by the first two principal components, three classes can be easily discriminated : the water, the humid area, and the "agricultural" classes. This means that if several agricultural classes are grouped together into one agricultural category then, the use of a decision-surface based classifier like the MLP network gives very good results. Other how, if the agricultural category is splitted into several classes, then the use of a clustering based classifier is well adapted. 2) classification results by the K-means, the K-nearest neighbours and and the LVQ2 networks, which are also clustering based classifiers, are nearly 12% less than the Kohonen SOFM and the HLVQ networks. The common clustering idea among the K-M, the K-NN and the LVQ2 classifiers is that each centroïd is determined independently from its "neighbouring centoïds". This confirms the interest of using the topological organisation notion applied in the Kohonen SOFM and the HLVQ networks, where the topology preserving between the centroïds is an important feature of the classifier. When testing the generalization capability of these different classification methods, the best results were obtained with the HLVQ neural network and the MLC classifiers. Obtained images are shown on figure.1 and.2. 3

4 Figure 1. HLVQ network classification results using 14 classes Figure 2. MLC classification results using 14 classes 4

5 By analysing these two images, the HLVQ and the MLC methods seem to produce the same important features contained in the original image. The second simulation conducted in this study consists in the use of only the MLC and the HLVQ neural network classifier in the classification of the data base BASE1 containing only the 8 classes. Results obtained by this experimentation are compared to those obtained by the use of the classifiers over the data base BASE2 and by grouping the decisions concerning the different subclasses into their mother classes. Obtained results in terms of mean recognition rates are resumed in TABLE 2.: TABLE 2. MLC HLVQ 8 classes 96.1% 91.5 % 14 classes grouped into after classification This confirms that the HLVQ network and the MLC are very comparable in terms of recognition rates. Concerning the generalization capability over the whole studied scene, both the MLC and the HLVQ network preserve wellthe shapes and the edges of the different image features. CONCLUSION In this study, several classification methods were compared and tested over a multispectral scene containing agricultural classes using a limited small size data bases. The best two : the MLC and the HLVQ classifiers proved to be very comparable in terms of recognition rates and generalization capacities. Nevertheless, the computation time of the HLVQ is sensibly less than the MLC. This means that this neural network architecture may be considered as a good alternative to the classical MLC method, especially when processing hyper spectral data where several hundreds of spectral bands have to be considered together. References [Kohonen,1989]T.Kohonen,"Self-Organization and associative Memory", 3d ed, 1989, Berlin :Springer-Verlag. [Lippman,1987]R.P.Lippman,"An Introduction to computing with neural nets", IEEE Acoustic, Speech and Signal Processing Magazine, 4(2), pp4-22, April1987. [Mather,1989]P.M.Mather, "Computer Processing of Remotely Sensed Images, An Introduction", Wiley, New York ( 2nd edition) [Schowengerdt,1983]R.A.Schowengerdt,"Techniques for Image Processing and Classification in Remote Sensing", Academic Press, [Solaiman,1994]B.Solaiman, M.C.Mouchot and E.Maillard, "A hybrid algorithm, HLVQ, combining unsupervised and supervised learning approaches", International Conferences on Neural Networks, ICNN94, June26-July2, Orlando, USA,

Unsupervised Change Detection in Remote-Sensing Images using Modified Self-Organizing Feature Map Neural Network

Unsupervised Change Detection in Remote-Sensing Images using Modified Self-Organizing Feature Map Neural Network Unsupervised Change Detection in Remote-Sensing Images using Modified Self-Organizing Feature Map Neural Network Swarnajyoti Patra, Susmita Ghosh Department of Computer Science and Engineering Jadavpur

More information

Data: a collection of numbers or facts that require further processing before they are meaningful

Data: a collection of numbers or facts that require further processing before they are meaningful Digital Image Classification Data vs. Information Data: a collection of numbers or facts that require further processing before they are meaningful Information: Derived knowledge from raw data. Something

More information

Application of nonparametric Bayesian classifier to remote sensing data. Institute of Parallel Processing, Bulgarian Academy of Sciences

Application of nonparametric Bayesian classifier to remote sensing data. Institute of Parallel Processing, Bulgarian Academy of Sciences Application of nonparametric Bayesian classifier to remote sensing data Nina Jeliazkova, nina@acad.bg, +359 2 979 6606 Stela Ruseva, stela@acad.bg, +359 2 979 6606 Kiril Boyanov, boyanov@acad.bg Institute

More information

Classify Multi-Spectral Data Classify Geologic Terrains on Venus Apply Multi-Variate Statistics

Classify Multi-Spectral Data Classify Geologic Terrains on Venus Apply Multi-Variate Statistics Classify Multi-Spectral Data Classify Geologic Terrains on Venus Apply Multi-Variate Statistics Operations What Do I Need? Classify Merge Combine Cross Scan Score Warp Respace Cover Subscene Rotate Translators

More information

The Gain setting for Landsat 7 (High or Low Gain) depends on: Sensor Calibration - Application. the surface cover types of the earth and the sun angle

The Gain setting for Landsat 7 (High or Low Gain) depends on: Sensor Calibration - Application. the surface cover types of the earth and the sun angle Sensor Calibration - Application Station Identifier ASN Scene Center atitude 34.840 (34 3'0.64"N) Day Night DAY Scene Center ongitude 33.03270 (33 0'7.72"E) WRS Path WRS Row 76 036 Corner Upper eft atitude

More information

Introduction to digital image classification

Introduction to digital image classification Introduction to digital image classification Dr. Norman Kerle, Wan Bakx MSc a.o. INTERNATIONAL INSTITUTE FOR GEO-INFORMATION SCIENCE AND EARTH OBSERVATION Purpose of lecture Main lecture topics Review

More information

Neural networks for variable star classification

Neural networks for variable star classification Neural networks for variable star classification Vasily Belokurov, IoA, Cambridge Supervised classification Multi-Layer Perceptron (MLP) Neural Networks for Pattern Recognition by C. Bishop Unsupervised

More information

Performance Analysis of Data Mining Classification Techniques

Performance Analysis of Data Mining Classification Techniques Performance Analysis of Data Mining Classification Techniques Tejas Mehta 1, Dr. Dhaval Kathiriya 2 Ph.D. Student, School of Computer Science, Dr. Babasaheb Ambedkar Open University, Gujarat, India 1 Principal

More information

Neural Network Approach for Automatic Landuse Classification of Satellite Images: One-Against-Rest and Multi-Class Classifiers

Neural Network Approach for Automatic Landuse Classification of Satellite Images: One-Against-Rest and Multi-Class Classifiers Neural Network Approach for Automatic Landuse Classification of Satellite Images: One-Against-Rest and Multi-Class Classifiers Anil Kumar Goswami DTRL, DRDO Delhi, India Heena Joshi Banasthali Vidhyapith

More information

Fuzzy Neural Network Models FOr Clustering

Fuzzy Neural Network Models FOr Clustering Fuzzy Neural Network Models FOr Clustering A. D. Kulkarui and V. K. Muniganti Computer Science Department The University of Texas at Tyler, Tyler, TX 75701 ABSTARCT Conventional clustering techniques group

More information

(Refer Slide Time: 0:51)

(Refer Slide Time: 0:51) Introduction to Remote Sensing Dr. Arun K Saraf Department of Earth Sciences Indian Institute of Technology Roorkee Lecture 16 Image Classification Techniques Hello everyone welcome to 16th lecture in

More information

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

Pattern Recognition. Kjell Elenius. Speech, Music and Hearing KTH. March 29, 2007 Speech recognition Pattern Recognition Kjell Elenius Speech, Music and Hearing KTH March 29, 2007 Speech recognition 2007 1 Ch 4. Pattern Recognition 1(3) Bayes Decision Theory Minimum-Error-Rate Decision Rules Discriminant

More information

Radial Basis Function Neural Network Classifier

Radial Basis Function Neural Network Classifier Recognition of Unconstrained Handwritten Numerals by a Radial Basis Function Neural Network Classifier Hwang, Young-Sup and Bang, Sung-Yang Department of Computer Science & Engineering Pohang University

More information

Contribution to Multicriterial Classification of Spatial Data

Contribution to Multicriterial Classification of Spatial Data Magyar Kutatók 8. Nemzetközi Szimpóziuma 8 th International Symposium of Hungarian Researchers on Computational Intelligence and Informatics Contribution to Multicriterial Classification of Spatial Data

More information

Reducing topological defects in self-organizing maps using multiple scale neighborhood functions

Reducing topological defects in self-organizing maps using multiple scale neighborhood functions Reducing topological defects in self-organizing maps using multiple scale neighborhood functions Kazushi Murakoshi,YuichiSato Department of Knowledge-based Information Engineering, Toyohashi University

More information

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University Classification Vladimir Curic Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University Outline An overview on classification Basics of classification How to choose appropriate

More information

DIGITAL IMAGE ANALYSIS. Image Classification: Object-based Classification

DIGITAL IMAGE ANALYSIS. Image Classification: Object-based Classification DIGITAL IMAGE ANALYSIS Image Classification: Object-based Classification Image classification Quantitative analysis used to automate the identification of features Spectral pattern recognition Unsupervised

More information

A novel firing rule for training Kohonen selforganising

A novel firing rule for training Kohonen selforganising A novel firing rule for training Kohonen selforganising maps D. T. Pham & A. B. Chan Manufacturing Engineering Centre, School of Engineering, University of Wales Cardiff, P.O. Box 688, Queen's Buildings,

More information

Digital Image Classification Geography 4354 Remote Sensing

Digital Image Classification Geography 4354 Remote Sensing Digital Image Classification Geography 4354 Remote Sensing Lab 11 Dr. James Campbell December 10, 2001 Group #4 Mark Dougherty Paul Bartholomew Akisha Williams Dave Trible Seth McCoy Table of Contents:

More information

Texture Classification by Combining Local Binary Pattern Features and a Self-Organizing Map

Texture Classification by Combining Local Binary Pattern Features and a Self-Organizing Map Texture Classification by Combining Local Binary Pattern Features and a Self-Organizing Map Markus Turtinen, Topi Mäenpää, and Matti Pietikäinen Machine Vision Group, P.O.Box 4500, FIN-90014 University

More information

SOME ISSUES RELATED WITH SUB-PIXEL CLASSIFICATION USING HYPERION DATA

SOME ISSUES RELATED WITH SUB-PIXEL CLASSIFICATION USING HYPERION DATA SOME ISSUES RELATED WITH SUB-PIXEL CLASSIFICATION USING HYPERION DATA A. Kumar a*, H. A. Min b, a Indian Institute of Remote Sensing, Dehradun, India. anil@iirs.gov.in b Satellite Data Processing and Digital

More information

Nonlinear data separation and fusion for multispectral image classification

Nonlinear data separation and fusion for multispectral image classification Nonlinear data separation and fusion for multispectral image classification Hela Elmannai #*1, Mohamed Anis Loghmari #2, Mohamed Saber Naceur #3 # Laboratoire de Teledetection et Systeme d informations

More information

Image Classification. RS Image Classification. Present by: Dr.Weerakaset Suanpaga

Image Classification. RS Image Classification. Present by: Dr.Weerakaset Suanpaga Image Classification Present by: Dr.Weerakaset Suanpaga D.Eng(RS&GIS) 6.1 Concept of Classification Objectives of Classification Advantages of Multi-Spectral data for Classification Variation of Multi-Spectra

More information

AN INTEGRATED APPROACH TO AGRICULTURAL CROP CLASSIFICATION USING SPOT5 HRV IMAGES

AN INTEGRATED APPROACH TO AGRICULTURAL CROP CLASSIFICATION USING SPOT5 HRV IMAGES AN INTEGRATED APPROACH TO AGRICULTURAL CROP CLASSIFICATION USING SPOT5 HRV IMAGES Chang Yi 1 1,2,*, Yaozhong Pan 1, 2, Jinshui Zhang 1, 2 College of Resources Science and Technology, Beijing Normal University,

More information

Remote Sensing Introduction to the course

Remote Sensing Introduction to the course Remote Sensing Introduction to the course Remote Sensing (Prof. L. Biagi) Exploitation of remotely assessed data for information retrieval Data: Digital images of the Earth, obtained by sensors recording

More information

CHAPTER 6 COUNTER PROPAGATION NEURAL NETWORK IN GAIT RECOGNITION

CHAPTER 6 COUNTER PROPAGATION NEURAL NETWORK IN GAIT RECOGNITION 75 CHAPTER 6 COUNTER PROPAGATION NEURAL NETWORK IN GAIT RECOGNITION 6.1 INTRODUCTION Counter propagation network (CPN) was developed by Robert Hecht-Nielsen as a means to combine an unsupervised Kohonen

More information

A Vector Agent-Based Unsupervised Image Classification for High Spatial Resolution Satellite Imagery

A Vector Agent-Based Unsupervised Image Classification for High Spatial Resolution Satellite Imagery A Vector Agent-Based Unsupervised Image Classification for High Spatial Resolution Satellite Imagery K. Borna 1, A. B. Moore 2, P. Sirguey 3 School of Surveying University of Otago PO Box 56, Dunedin,

More information

Lecture 11: Classification

Lecture 11: Classification Lecture 11: Classification 1 2009-04-28 Patrik Malm Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University 2 Reading instructions Chapters for this lecture 12.1 12.2 in

More information

COMBINED METHOD TO VISUALISE AND REDUCE DIMENSIONALITY OF THE FINANCIAL DATA SETS

COMBINED METHOD TO VISUALISE AND REDUCE DIMENSIONALITY OF THE FINANCIAL DATA SETS COMBINED METHOD TO VISUALISE AND REDUCE DIMENSIONALITY OF THE FINANCIAL DATA SETS Toomas Kirt Supervisor: Leo Võhandu Tallinn Technical University Toomas.Kirt@mail.ee Abstract: Key words: For the visualisation

More information

Estimating the Natural Number of Classes on Hierarchically Clustered Multi-spectral Images

Estimating the Natural Number of Classes on Hierarchically Clustered Multi-spectral Images Estimating the Natural Number of Classes on Hierarchically Clustered Multi-spectral Images André R.S. Marçal and Janete S. Borges Faculdade de Ciências, Universidade do Porto, DMA, Rua do Campo Alegre,

More information

Performance analysis of a MLP weight initialization algorithm

Performance analysis of a MLP weight initialization algorithm Performance analysis of a MLP weight initialization algorithm Mohamed Karouia (1,2), Régis Lengellé (1) and Thierry Denœux (1) (1) Université de Compiègne U.R.A. CNRS 817 Heudiasyc BP 49 - F-2 Compiègne

More information

ECG782: Multidimensional Digital Signal Processing

ECG782: Multidimensional Digital Signal Processing ECG782: Multidimensional Digital Signal Processing Object Recognition http://www.ee.unlv.edu/~b1morris/ecg782/ 2 Outline Knowledge Representation Statistical Pattern Recognition Neural Networks Boosting

More information

Image Classification. Introduction to Photogrammetry and Remote Sensing (SGHG 1473) Dr. Muhammad Zulkarnain Abdul Rahman

Image Classification. Introduction to Photogrammetry and Remote Sensing (SGHG 1473) Dr. Muhammad Zulkarnain Abdul Rahman Image Classification Introduction to Photogrammetry and Remote Sensing (SGHG 1473) Dr. Muhammad Zulkarnain Abdul Rahman Classification Multispectral classification may be performed using a variety of methods,

More information

FAST IMAGE ANALYSIS USING KOHONEN MAPS

FAST IMAGE ANALYSIS USING KOHONEN MAPS FAST IMAGE ANALYSIS USING KOHONEN MAPS D.Willett, C. Busch, F. Seibert, Visual Computing Group Darmstadt Computer Graphics Center Wilhelminenstraße 7, D 64283 Darmstadt Tel: +49 6151 155 255, Fax: +49

More information

Image Classification Using Wavelet Coefficients in Low-pass Bands

Image Classification Using Wavelet Coefficients in Low-pass Bands Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, August -7, 007 Image Classification Using Wavelet Coefficients in Low-pass Bands Weibao Zou, Member, IEEE, and Yan

More information

Unsupervised Learning

Unsupervised Learning Networks for Pattern Recognition, 2014 Networks for Single Linkage K-Means Soft DBSCAN PCA Networks for Kohonen Maps Linear Vector Quantization Networks for Problems/Approaches in Machine Learning Supervised

More information

Geomatics 89 (National Conference & Exhibition) May 2010

Geomatics 89 (National Conference & Exhibition) May 2010 Evaluation of the Pixel Based and Object Based Classification Methods For Monitoring Of Agricultural Land Cover Case study: Biddinghuizen - The Netherlands Hossein Vahidi MSc Student of Geoinformatics

More information

Unsupervised Change Detection in Optical Satellite Images using Binary Descriptor

Unsupervised Change Detection in Optical Satellite Images using Binary Descriptor Unsupervised Change Detection in Optical Satellite Images using Binary Descriptor Neha Gupta, Gargi V. Pillai, Samit Ari Department of Electronics and Communication Engineering, National Institute of Technology,

More information

Function approximation using RBF network. 10 basis functions and 25 data points.

Function approximation using RBF network. 10 basis functions and 25 data points. 1 Function approximation using RBF network F (x j ) = m 1 w i ϕ( x j t i ) i=1 j = 1... N, m 1 = 10, N = 25 10 basis functions and 25 data points. Basis function centers are plotted with circles and data

More information

Contextual priming for artificial visual perception

Contextual priming for artificial visual perception Contextual priming for artificial visual perception Hervé Guillaume 1, Nathalie Denquive 1, Philippe Tarroux 1,2 1 LIMSI-CNRS BP 133 F-91403 Orsay cedex France 2 ENS 45 rue d Ulm F-75230 Paris cedex 05

More information

DEEP LEARNING TO DIVERSIFY BELIEF NETWORKS FOR REMOTE SENSING IMAGE CLASSIFICATION

DEEP LEARNING TO DIVERSIFY BELIEF NETWORKS FOR REMOTE SENSING IMAGE CLASSIFICATION DEEP LEARNING TO DIVERSIFY BELIEF NETWORKS FOR REMOTE SENSING IMAGE CLASSIFICATION S.Dhanalakshmi #1 #PG Scholar, Department of Computer Science, Dr.Sivanthi Aditanar college of Engineering, Tiruchendur

More information

A Neural Network Based Technique for Data Compression

A Neural Network Based Technique for Data Compression A Neural Network Based Technique for Data Compression Author Verma, Brijesh, Blumenstein, Michael, Kulkarni, Siddhivinayak Published 1997 Conference Title IASTED International Conference on Modelling,

More information

PUTTING KNOWLEDGE ON THE MAP PROBA-V CLOUD ROUND ROBIN. Béatrice Berthelot 01/03/ /03/2017 HYPOS-PPT-37-MAGv1.0

PUTTING KNOWLEDGE ON THE MAP PROBA-V CLOUD ROUND ROBIN. Béatrice Berthelot 01/03/ /03/2017 HYPOS-PPT-37-MAGv1.0 HYPOS-PPT-37-MAGv1.0 PUTTING KNOWLEDGE ON THE MAP PROBA-V CLOUD ROUND ROBIN Béatrice Berthelot 1 Objectives The objective was to capitalize on former activities related to cloud detection to propose a

More information

Object-Based Classification & ecognition. Zutao Ouyang 11/17/2015

Object-Based Classification & ecognition. Zutao Ouyang 11/17/2015 Object-Based Classification & ecognition Zutao Ouyang 11/17/2015 What is Object-Based Classification The object based image analysis approach delineates segments of homogeneous image areas (i.e., objects)

More information

Clustering and Visualisation of Data

Clustering and Visualisation of Data Clustering and Visualisation of Data Hiroshi Shimodaira January-March 28 Cluster analysis aims to partition a data set into meaningful or useful groups, based on distances between data points. In some

More information

II. ARTIFICIAL NEURAL NETWORK

II. ARTIFICIAL NEURAL NETWORK Applications of Artificial Neural Networks in Power Systems: A Review Harsh Sareen 1, Palak Grover 2 1, 2 HMR Institute of Technology and Management Hamidpur New Delhi, India Abstract: A standout amongst

More information

Glasses Detection for Face Recognition Using Bayes Rules

Glasses Detection for Face Recognition Using Bayes Rules Glasses Detection for Face Recognition Using Bayes Rules Zhong Jing, Roberto ariani, Jiankang Wu RWCP ulti-modal Functions KRDL Lab Heng ui Keng Terrace, Kent Ridge Singapore 963 Email: jzhong, rmariani,

More information

Controlling the spread of dynamic self-organising maps

Controlling the spread of dynamic self-organising maps Neural Comput & Applic (2004) 13: 168 174 DOI 10.1007/s00521-004-0419-y ORIGINAL ARTICLE L. D. Alahakoon Controlling the spread of dynamic self-organising maps Received: 7 April 2004 / Accepted: 20 April

More information

Figure 1: Workflow of object-based classification

Figure 1: Workflow of object-based classification Technical Specifications Object Analyst Object Analyst is an add-on package for Geomatica that provides tools for segmentation, classification, and feature extraction. Object Analyst includes an all-in-one

More information

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani

Neural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani Neural Networks CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Biological and artificial neural networks Feed-forward neural networks Single layer

More information

CLASSIFICATION OF HYPERSPECTRAL DATA OF SEMINATURAL ECOSYSTEMS

CLASSIFICATION OF HYPERSPECTRAL DATA OF SEMINATURAL ECOSYSTEMS CLASSIFICATION OF HYPERSPECTRAL DATA OF SEMINATURAL ECOSYSTEMS B. Zagajewski, D. Olesiuk Dept. of Geoinformatics and Remote Sensing, Faculty of Geography and Regional Studies, University of Warsaw, Krakowskie

More information

Supervised vs.unsupervised Learning

Supervised vs.unsupervised Learning Supervised vs.unsupervised Learning In supervised learning we train algorithms with predefined concepts and functions based on labeled data D = { ( x, y ) x X, y {yes,no}. In unsupervised learning we are

More information

11/14/2010 Intelligent Systems and Soft Computing 1

11/14/2010 Intelligent Systems and Soft Computing 1 Lecture 8 Artificial neural networks: Unsupervised learning Introduction Hebbian learning Generalised Hebbian learning algorithm Competitive learning Self-organising computational map: Kohonen network

More information

EVALUATION OF THE THEMATIC INFORMATION CONTENT OF THE ASTER-VNIR IMAGERY IN URBAN AREAS BY CLASSIFICATION TECHNIQUES

EVALUATION OF THE THEMATIC INFORMATION CONTENT OF THE ASTER-VNIR IMAGERY IN URBAN AREAS BY CLASSIFICATION TECHNIQUES EVALUATION OF THE THEMATIC INFORMATION CONTENT OF THE ASTER-VNIR IMAGERY IN URBAN AREAS BY CLASSIFICATION TECHNIQUES T. G. Panagou a *, G. Ch. Miliaresis a a TEI, Dpt. of Topography, 3 P.Drakou Str., Thiva,

More information

Artificial neural networks are the paradigm of connectionist systems (connectionism vs. symbolism)

Artificial neural networks are the paradigm of connectionist systems (connectionism vs. symbolism) Artificial Neural Networks Analogy to biological neural systems, the most robust learning systems we know. Attempt to: Understand natural biological systems through computational modeling. Model intelligent

More information

Remote Sensing & Photogrammetry W4. Beata Hejmanowska Building C4, room 212, phone:

Remote Sensing & Photogrammetry W4. Beata Hejmanowska Building C4, room 212, phone: Remote Sensing & Photogrammetry W4 Beata Hejmanowska Building C4, room 212, phone: +4812 617 22 72 605 061 510 galia@agh.edu.pl 1 General procedures in image classification Conventional multispectral classification

More information

International Journal of Scientific Research & Engineering Trends Volume 4, Issue 6, Nov-Dec-2018, ISSN (Online): X

International Journal of Scientific Research & Engineering Trends Volume 4, Issue 6, Nov-Dec-2018, ISSN (Online): X Analysis about Classification Techniques on Categorical Data in Data Mining Assistant Professor P. Meena Department of Computer Science Adhiyaman Arts and Science College for Women Uthangarai, Krishnagiri,

More information

MURDOCH RESEARCH REPOSITORY

MURDOCH RESEARCH REPOSITORY MURDOCH RESEARCH REPOSITORY http://dx.doi.org/10.1109/19.668276 Fung, C.C., Wong, K.W. and Eren, H. (1997) Modular artificial neural network for prediction of petrophysical properties from well log data.

More information

3D Visualization and Spatial Data Mining for Analysis of LULC Images

3D Visualization and Spatial Data Mining for Analysis of LULC Images 3D Visualization and Spatial Data Mining for Analysis of LULC Images Kodge B. G. Department of Computer Science, Swami Vivekanand Mahavidyalaya, Udgir, Latur, India kodgebg@hotmail.com Abstract: The present

More information

Raster Classification with ArcGIS Desktop. Rebecca Richman Andy Shoemaker

Raster Classification with ArcGIS Desktop. Rebecca Richman Andy Shoemaker Raster Classification with ArcGIS Desktop Rebecca Richman Andy Shoemaker Raster Classification What is it? - Classifying imagery into different land use/ land cover classes based on the pixel values of

More information

In this assignment, we investigated the use of neural networks for supervised classification

In this assignment, we investigated the use of neural networks for supervised classification Paul Couchman Fabien Imbault Ronan Tigreat Gorka Urchegui Tellechea Classification assignment (group 6) Image processing MSc Embedded Systems March 2003 Classification includes a broad range of decision-theoric

More information

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University

Classification. Vladimir Curic. Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University Classification Vladimir Curic Centre for Image Analysis Swedish University of Agricultural Sciences Uppsala University Outline An overview on classification Basics of classification How to choose appropriate

More information

A USER-FRIENDLY AUTOMATIC TOOL FOR IMAGE CLASSIFICATION BASED ON NEURAL NETWORKS

A USER-FRIENDLY AUTOMATIC TOOL FOR IMAGE CLASSIFICATION BASED ON NEURAL NETWORKS A USER-FRIENDLY AUTOMATIC TOOL FOR IMAGE CLASSIFICATION BASED ON NEURAL NETWORKS B. Buttarazzi, F. Del Frate*, C. Solimini Università Tor Vergata, Ingegneria DISP, Via del Politecnico 1, I-00133 Rome,

More information

MS1b Statistical Data Mining Part 3: Supervised Learning Nonparametric Methods

MS1b Statistical Data Mining Part 3: Supervised Learning Nonparametric Methods MS1b Statistical Data Mining Part 3: Supervised Learning Nonparametric Methods Yee Whye Teh Department of Statistics Oxford http://www.stats.ox.ac.uk/~teh/datamining.html Outline Supervised Learning: Nonparametric

More information

MultiSpec Tutorial. January 11, Program Concept and Introduction Notes by David Landgrebe and Larry Biehl. MultiSpec Programming by Larry Biehl

MultiSpec Tutorial. January 11, Program Concept and Introduction Notes by David Landgrebe and Larry Biehl. MultiSpec Programming by Larry Biehl MultiSpec Tutorial January 11, 2001 Program Concept and Introduction Notes by David Landgrebe and Larry Biehl MultiSpec Programming by Larry Biehl School of Electrical and Computer Engineering Purdue University

More information

Exploratory Data Analysis using Self-Organizing Maps. Madhumanti Ray

Exploratory Data Analysis using Self-Organizing Maps. Madhumanti Ray Exploratory Data Analysis using Self-Organizing Maps Madhumanti Ray Content Introduction Data Analysis methods Self-Organizing Maps Conclusion Visualization of high-dimensional data items Exploratory data

More information

Lab 9. Julia Janicki. Introduction

Lab 9. Julia Janicki. Introduction Lab 9 Julia Janicki Introduction My goal for this project is to map a general land cover in the area of Alexandria in Egypt using supervised classification, specifically the Maximum Likelihood and Support

More information

PATTERN RECOGNITION USING NEURAL NETWORKS

PATTERN RECOGNITION USING NEURAL NETWORKS PATTERN RECOGNITION USING NEURAL NETWORKS Santaji Ghorpade 1, Jayshree Ghorpade 2 and Shamla Mantri 3 1 Department of Information Technology Engineering, Pune University, India santaji_11jan@yahoo.co.in,

More information

Data Mining Chapter 9: Descriptive Modeling Fall 2011 Ming Li Department of Computer Science and Technology Nanjing University

Data Mining Chapter 9: Descriptive Modeling Fall 2011 Ming Li Department of Computer Science and Technology Nanjing University Data Mining Chapter 9: Descriptive Modeling Fall 2011 Ming Li Department of Computer Science and Technology Nanjing University Descriptive model A descriptive model presents the main features of the data

More information

Time Series Prediction as a Problem of Missing Values: Application to ESTSP2007 and NN3 Competition Benchmarks

Time Series Prediction as a Problem of Missing Values: Application to ESTSP2007 and NN3 Competition Benchmarks Series Prediction as a Problem of Missing Values: Application to ESTSP7 and NN3 Competition Benchmarks Antti Sorjamaa and Amaury Lendasse Abstract In this paper, time series prediction is considered as

More information

CS6716 Pattern Recognition

CS6716 Pattern Recognition CS6716 Pattern Recognition Prototype Methods Aaron Bobick School of Interactive Computing Administrivia Problem 2b was extended to March 25. Done? PS3 will be out this real soon (tonight) due April 10.

More information

Neural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /10/2017

Neural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /10/2017 3/0/207 Neural Networks Emily Fox University of Washington March 0, 207 Slides adapted from Ali Farhadi (via Carlos Guestrin and Luke Zettlemoyer) Single-layer neural network 3/0/207 Perceptron as a neural

More information

Saliency Detection in Aerial Imagery

Saliency Detection in Aerial Imagery Saliency Detection in Aerial Imagery using Multi-scale SLIC Segmentation Samir Sahli 1, Daniel A. Lavigne 2 and Yunlong Sheng 1 1- COPL, Image Science group, Laval University, Quebec, Canada 2- Defence

More information

Self-Organizing Feature Map. Kazuhiro MINAMIMOTO Kazushi IKEDA Kenji NAKAYAMA

Self-Organizing Feature Map. Kazuhiro MINAMIMOTO Kazushi IKEDA Kenji NAKAYAMA Topology Analysis of Data Space Using Self-Organizing Feature Map Kazuhiro MINAMIMOTO Kazushi IKEDA Kenji NAKAYAMA Department of Electrical and Computer Eng., Faculty of Eng., Kanazawa Univ. 2-4-2, Kodatsuno,

More information

Temporal Modeling and Missing Data Estimation for MODIS Vegetation data

Temporal Modeling and Missing Data Estimation for MODIS Vegetation data Temporal Modeling and Missing Data Estimation for MODIS Vegetation data Rie Honda 1 Introduction The Moderate Resolution Imaging Spectroradiometer (MODIS) is the primary instrument on board NASA s Earth

More information

Machine Learning. Unsupervised Learning. Manfred Huber

Machine Learning. Unsupervised Learning. Manfred Huber Machine Learning Unsupervised Learning Manfred Huber 2015 1 Unsupervised Learning In supervised learning the training data provides desired target output for learning In unsupervised learning the training

More information

Machine Learning. Nonparametric methods for Classification. Eric Xing , Fall Lecture 2, September 12, 2016

Machine Learning. Nonparametric methods for Classification. Eric Xing , Fall Lecture 2, September 12, 2016 Machine Learning 10-701, Fall 2016 Nonparametric methods for Classification Eric Xing Lecture 2, September 12, 2016 Reading: 1 Classification Representing data: Hypothesis (classifier) 2 Clustering 3 Supervised

More information

CHAPTER 5 OBJECT ORIENTED IMAGE ANALYSIS

CHAPTER 5 OBJECT ORIENTED IMAGE ANALYSIS 85 CHAPTER 5 OBJECT ORIENTED IMAGE ANALYSIS 5.1 GENERAL Urban feature mapping is one of the important component for the planning, managing and monitoring the rapid urbanized growth. The present conventional

More information

Effect of Grouping in Vector Recognition System Based on SOM

Effect of Grouping in Vector Recognition System Based on SOM Effect of Grouping in Vector Recognition System Based on SOM Masayoshi Ohta Graduate School of Science and Engineering Kansai University Osaka, Japan Email: k287636@kansai-u.ac.jp Yuto Kurosaki Department

More information

Spectral Classification

Spectral Classification Spectral Classification Spectral Classification Supervised versus Unsupervised Classification n Unsupervised Classes are determined by the computer. Also referred to as clustering n Supervised Classes

More information

CANCER PREDICTION USING PATTERN CLASSIFICATION OF MICROARRAY DATA. By: Sudhir Madhav Rao &Vinod Jayakumar Instructor: Dr.

CANCER PREDICTION USING PATTERN CLASSIFICATION OF MICROARRAY DATA. By: Sudhir Madhav Rao &Vinod Jayakumar Instructor: Dr. CANCER PREDICTION USING PATTERN CLASSIFICATION OF MICROARRAY DATA By: Sudhir Madhav Rao &Vinod Jayakumar Instructor: Dr. Michael Nechyba 1. Abstract The objective of this project is to apply well known

More information

Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications

Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications Anil K Goswami 1, Swati Sharma 2, Praveen Kumar 3 1 DRDO, New Delhi, India 2 PDM College of Engineering for

More information

A Self Organizing Map for dissimilarity data 0

A Self Organizing Map for dissimilarity data 0 A Self Organizing Map for dissimilarity data Aïcha El Golli,2, Brieuc Conan-Guez,2, and Fabrice Rossi,2,3 Projet AXIS, INRIA-Rocquencourt Domaine De Voluceau, BP 5 Bâtiment 8 7853 Le Chesnay Cedex, France

More information

TEXTURE CLASSIFICATION METHODS: A REVIEW

TEXTURE CLASSIFICATION METHODS: A REVIEW TEXTURE CLASSIFICATION METHODS: A REVIEW Ms. Sonal B. Bhandare Prof. Dr. S. M. Kamalapur M.E. Student Associate Professor Deparment of Computer Engineering, Deparment of Computer Engineering, K. K. Wagh

More information

Land Cover Classification Techniques

Land Cover Classification Techniques Land Cover Classification Techniques supervised classification and random forests Developed by remote sensing specialists at the USFS Geospatial Technology and Applications Center (GTAC), located in Salt

More information

NEURAL NETWORK-BASED SEGMENTATION OF TEXTURES USING GABOR FEATURES

NEURAL NETWORK-BASED SEGMENTATION OF TEXTURES USING GABOR FEATURES NEURAL NETWORK-BASED SEGMENTATION OF TEXTURES USING GABOR FEATURES A. G. Ramakrishnan, S. Kumar Raja, and H. V. Raghu Ram Dept. of Electrical Engg., Indian Institute of Science Bangalore - 560 012, India

More information

More Learning. Ensembles Bayes Rule Neural Nets K-means Clustering EM Clustering WEKA

More Learning. Ensembles Bayes Rule Neural Nets K-means Clustering EM Clustering WEKA More Learning Ensembles Bayes Rule Neural Nets K-means Clustering EM Clustering WEKA 1 Ensembles An ensemble is a set of classifiers whose combined results give the final decision. test feature vector

More information

Gray-Level Reduction Using Local Spatial Features

Gray-Level Reduction Using Local Spatial Features Computer Vision and Image Understanding 78, 336 350 (2000) doi:10.1006/cviu.2000.0838, available online at http://www.idealibrary.com on Gray-Level Reduction Using Local Spatial Features Nikos Papamarkos

More information

Fundamentals of Digital Image Processing

Fundamentals of Digital Image Processing \L\.6 Gw.i Fundamentals of Digital Image Processing A Practical Approach with Examples in Matlab Chris Solomon School of Physical Sciences, University of Kent, Canterbury, UK Toby Breckon School of Engineering,

More information

Day 3 Lecture 1. Unsupervised Learning

Day 3 Lecture 1. Unsupervised Learning Day 3 Lecture 1 Unsupervised Learning Semi-supervised and transfer learning Myth: you can t do deep learning unless you have a million labelled examples for your problem. Reality You can learn useful representations

More information

An Introduction to Pattern Recognition

An Introduction to Pattern Recognition An Introduction to Pattern Recognition Speaker : Wei lun Chao Advisor : Prof. Jian-jiun Ding DISP Lab Graduate Institute of Communication Engineering 1 Abstract Not a new research field Wide range included

More information

An Autoassociator for Automatic Texture Feature Extraction

An Autoassociator for Automatic Texture Feature Extraction An Autoassociator for Automatic Texture Feature Extraction Author Kulkarni, Siddhivinayak, Verma, Brijesh Published 200 Conference Title Conference Proceedings-ICCIMA'0 DOI https://doi.org/0.09/iccima.200.9088

More information

CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS

CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CHAPTER 4 CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS 4.1 Introduction Optical character recognition is one of

More information

Establishing Virtual Private Network Bandwidth Requirement at the University of Wisconsin Foundation

Establishing Virtual Private Network Bandwidth Requirement at the University of Wisconsin Foundation Establishing Virtual Private Network Bandwidth Requirement at the University of Wisconsin Foundation by Joe Madden In conjunction with ECE 39 Introduction to Artificial Neural Networks and Fuzzy Systems

More information

A MAXIMUM NOISE FRACTION TRANSFORM BASED ON A SENSOR NOISE MODEL FOR HYPERSPECTRAL DATA. Naoto Yokoya 1 and Akira Iwasaki 2

A MAXIMUM NOISE FRACTION TRANSFORM BASED ON A SENSOR NOISE MODEL FOR HYPERSPECTRAL DATA. Naoto Yokoya 1 and Akira Iwasaki 2 A MAXIMUM NOISE FRACTION TRANSFORM BASED ON A SENSOR NOISE MODEL FOR HYPERSPECTRAL DATA Naoto Yokoya 1 and Akira Iwasaki 1 Graduate Student, Department of Aeronautics and Astronautics, The University of

More information

A NEW ALGORITHM FOR OPTIMIZING THE SELF- ORGANIZING MAP

A NEW ALGORITHM FOR OPTIMIZING THE SELF- ORGANIZING MAP A NEW ALGORITHM FOR OPTIMIZING THE SELF- ORGANIZING MAP BEN-HDECH Adil, GHANOU Youssef, EL QADI Abderrahim Team TIM, High School of Technology, Moulay Ismail University, Meknes, Morocco E-mail: adilbenhdech@gmail.com,

More information

Outlier detection using autoencoders

Outlier detection using autoencoders Outlier detection using autoencoders August 19, 2016 Author: Olga Lyudchik Supervisors: Dr. Jean-Roch Vlimant Dr. Maurizio Pierini CERN Non Member State Summer Student Report 2016 Abstract Outlier detection

More information

Case-Based Reasoning. CS 188: Artificial Intelligence Fall Nearest-Neighbor Classification. Parametric / Non-parametric.

Case-Based Reasoning. CS 188: Artificial Intelligence Fall Nearest-Neighbor Classification. Parametric / Non-parametric. CS 188: Artificial Intelligence Fall 2008 Lecture 25: Kernels and Clustering 12/2/2008 Dan Klein UC Berkeley Case-Based Reasoning Similarity for classification Case-based reasoning Predict an instance

More information

CS 188: Artificial Intelligence Fall 2008

CS 188: Artificial Intelligence Fall 2008 CS 188: Artificial Intelligence Fall 2008 Lecture 25: Kernels and Clustering 12/2/2008 Dan Klein UC Berkeley 1 1 Case-Based Reasoning Similarity for classification Case-based reasoning Predict an instance

More information

Self-Organizing Maps for cyclic and unbounded graphs

Self-Organizing Maps for cyclic and unbounded graphs Self-Organizing Maps for cyclic and unbounded graphs M. Hagenbuchner 1, A. Sperduti 2, A.C. Tsoi 3 1- University of Wollongong, Wollongong, Australia. 2- University of Padova, Padova, Italy. 3- Hong Kong

More information