Ramon E. Vasquez

SCALED AND ROTATED TEXTURE CLASSIFICATION USING A CLASS OF BASIS FUNCTIONS

Abstract Three classes of basis functions are considered for classifying scaled and rotated textured images. The first is the orthonormal, compactly supported Daubechies and the discrete Haar bases, the second is the biorthogonal basis and the third is the non orthogonal Gabor basis. Textures are scaled and rotated and the basis functions are used to expand them. Features are computed on a combination of inter-resolution coefficients. Experimental results show that the Daubechies orthonormal basis perform well in recognizing transformed textures, followed by the Haar basis. The concept of multiresolution representation and orthogonality are shown to be useful for invariant texture classificaiton.

Texture classification using logical operators

In this paper, a new algorithm for texture classification based on logical operators is presented. Operators constructed from logical building blocks are convolved with texture images. An optimal set of six operators are selected based on their texture discrimination ability. The responses are then converted to standard deviation matrices computed over a sliding window. Zonal sampling features are computed from these matrices. A feature selection process is applied and the new set of features are used for texture classification. Classification of several natural and synthetic texture images are presented demonstrating the excellent performance of the logical operator method. The computational superiority and classification accuracy of the algorithm is demonstrated by comparison with other popular methods. Experiments with different classifiers and feature normalization are also presented. The Euclidean distance classifier is found to perform best with this algorithm. The algorithm involves only convolutions and simple arithmetic in the various stages which allows faster implementations. The algorithm is applicable to different types of classification problems which is demonstrated by segmentation of remote sensing images, compressed and reconstructed images and industrial images.

Urban heat islands developing in coastal tropical cities

Beautiful and breezy cities on small tropical islands, it turns out, may not be exempt from the same local climate change effects and urban heat island effects seen in large continental cities such as Los Angeles or Mexico City. A surprising, recent discovery indicates that this is the case for San Juan, Puerto Rico, a relatively affluent coastal tropical city of about two million inhabitants that is spreading rapidly into the once-rural areas around it. A recent climatological analysis of the surface temperature of the city has revealed that the local temperature has been increasing over the neighboring vegetated areas at a rate of 0.06°C per year for the past 30 years. This is a trend that may be comparable to climate changes induced by global warming.

Comparison of Daubechies, Coiflet, and Symlet for edge detection

The ability of wavelets to extract the high frequency component of an image has made them useful for edge detection. The high frequency details are analyzed and processed to obtain the edges. This work is primarily concerned with the comparison of Daubechies, Coiflet, and Symlet wavelets for the purpose of edge detection. Discrete wavelet frame has been sued to detect edges in this work. Different wavelet filters of varied lengths have been used to find out the best wavelet for edge detection. The criterion chosen for comparison is the same threshold selection. The results of the experimentation suggest that the Haar wavelet, which is the simplest of the Daubechies wavelets, is the best wavelet with the methodology followed in this paper. The results are also indicative of the fact that with increase in filter length the performance of the wavelet deteriorates.

Approaches to color- and texture-based image classification

A Gabor filtering method for texture-based classification of color images is presented. The algorithm is robust and can be used with different color representations. It involves a filter selection process based on texture smoothness. Unichannel and interchannel correlation features are computed. Two types of color representations have been considered: computing chromaticity values from xyY, HIS, and RGB spaces; and using the three channels of the perceptually uniform color spaces L*a*b* and HSV. The RGB space universally used in image processing can be used for color-texture-based classification by computing the rgb chromaticity values, which yield higher classification accuracies than the direct use of R, G, and B values. The wavelet transform methods have been extended to perform color image classifications with additional features. The two approaches, Gabor filtering and wavelet transform methods, are compared in terms of classification accuracy and efficiency. The pyramid wavelet transform (PWT) performs well with all color spaces. The tree-structured wavelet transform (TWT) is more suitable for smaller classification problems. The best color spaces for higher class problems with wavelet methods are L*a*b* and HSV spaces. The HSV space is found to be the best for application of both of these texture-based approaches. Computationally the Gabor method followed by PWT is fast and efficient.

An algorithm to estimate soil moisture over vegetated areas based on in situ and remote sensing information

An algorithm is proposed for estimating soil moisture over vegetated areas. The algorithm uses in situ and remote sensing information and statistical tools to estimate soil moisture at 1 km spatial resolution and at 20 cm depth over Puerto Rico. Soil moisture within the study region is characterized by spatial and temporal variability. The temporal variability for a given area exhibits long- and short-term variations that can be expressed by two empirical models. The average monthly soil moisture exhibits the long-term variability and is modelled by an artificial neural network (ANN), whereas the short-term variability is determined by hourly variation and is represented by a nonlinear stochastic transfer function model. Monthly vegetation index, land surface temperature, accumulated rainfall and soil texture are the major drivers of the ANN to estimate the monthly soil moisture. Radar, satellite and in situ observations are the major sources of information of the soil moisture empirical models. A self-organized ANN was also used to identify spatial variability to be able to determine a similar transfer function that best resembles the properties of a particular grid point and estimate the hourly soil moisture across the island. Validation techniques reveal an average absolute error of 3.34% of volumetric water content and this result shows that the proposed algorithm is a potential tool for estimating soil moisture over vegetated areas.

Classifier performance for SAR image classification

Classifier robustness is important for classification of remote sensing images. This paper investigates the use of the supervised maximum likelihood (ML) classifier and the unsupervised K-means algorithm. Classifier adaptability to other data sets is considered. Also, a method is presented to fuse classifiers for better performance with application to SAR images. The performance of neural network classifier such as the learning vector quantization (LVQ) technique is also studied and is used in the classifier integration algorithm. The paper presents results with SAR images.

A spatial data retrieval and image processing expert system for the World Wide Web

The integration of a data warehouse, an image processing engine and an expert system provides a complete solution to researchers from different fields that make use of spatial data in their investigations. Also, by adding image processing capabilities and making the system available to the World Wide Web, it is possible to provide remote access and processing of the data. This paper presents the fundamental concepts on designing the system.

A computational framework for analyzing textured image classification

A computational framework for analyzing textured image classification is presented. Parallel and distributed processing is the major element of this framework. The framework is developed by introducing computational constraints namely image representation, algorithms and strategies for texture feature extraction and classification, and fault tolerant behavior of the classifier. An illustration of an application of this framework for analyzing a textured image classification system is presented. Parallel distributed representations in hypercube multicomputer networks are discussed and a method for analyzing its performance is presented. The transputer computational structures in hypercube configurations are used for feature extraction. The networks are analyzed and a performance evaluation is done. The discriminatory power of a neural network is used for classification. It is shown that this framework is useful in analyzing and simplifying computationally intensive and complex image classification procedures. Efficient and optimal classification systems for real-time applications can be designed with this framework.

On teaching AI and expert systems courses

The experiences of faculty members from departments of engineering, mathematics, and computer science throughout the United States and Puerto Rico who came together for three weeks to discuss effective ways to teach artificial intelligence to undergraduates are outlined. The paper describes the rationale for the development of three main topic areas: artificial intelligence, expert systems, and symbolic and logic programming, and it includes syllabi for these topics. Also included is a discussion of the results obtained after a year of using the materials and techniques gathered during the original meeting. >