Vol 1, 2013

1 A HYBRID ALGORITHM USING GEOMETRIC WAVELETS FOR LOW BIT RATE IMAGE CODING

Rehna. V. J, Dr. M. K. Jeya Kumar
Noorul Islam University, INDIA
rehna_vj@yahoo.co.in
jeyakumarmk@yahoo.com

Abstract: Image compression systems based on hybrid image coding techniques that combine the advantages of various classical methods have been developed over the years. Segmentation-based coding methods provide high compression ratios compared to traditional coding approaches such as transform and sub band coding, especially for low bit-rate compression applications. In this paper, a hybrid algorithm using segmentation based binary space partition scheme and geometric wavelets, well suited for low bit rate image coding is discussed. The present study improves the geometric wavelet image compression method by using the slope intercept depiction of the straight line in the binary space partition scheme. The scheme takes advantage of the underlying geometry of the edge singularities in an image. This method is compared with other state-of-the-art wavelet based techniques as well as other recent segmentation based methods and shown that this method outperforms all of them at low bit rates. The results show a gain of 0.79 dB over the EZW algorithm at a bit rate of 0.03125.  [Download PDF]

Keywords: image coding, segmentation, binary space partition, edge singularity, bit rate.

2 CRUDE OIL FORECASTING WITH AN IMPROVED MODEL BASED ON WAVELET TRANSFORM AND SUPPORT VECTOR MACHINES

Ruhaidah Samsudin,
Department of Software Engineering, Faculty of Computing,
Universiti Teknologi Malaysia, 81310, Johor, Malaysia
ruhaidah@utm.my

Ani Shabri
Mathematic Department, Faculty of Science,
Universiti Teknologi Malaysia, 81310, Johor, Malaysia
ani@utm.my

Abstract: This paper presents a hybrid wavelet support vector machines (WSVM) model that combines both wavelet technique and the SVM model for crude oil forecasting. Based on the purpose, the main time series was decomposed to some multi-frequently time series by wavelet theory and these time series were imposed as input data to the SVM for forecasting of crude oil series. To assess the effectiveness of this model, daily crude oil market-West Texas Intermediate (WTI) has been used as the case study. Time series prediction capability performance of the WSVM model is compared with the single SVM model using various statistics measures. As seen in comparison, WSVM yielded more accurate than of any individual model and offered a practical solution to the problem in crude oil forecasting. [Download PDF]

 3 THERMAL IMAGING ANALYSIS OF POTENTIALLY HARMFUL SUBJECT FOR NIGHT VISION SYSTEM
Noor Amira Syuhada Mahamad Salleh, Kamarul Hawari Ghazali
Faculty of Electrical and Electronics Engineering
Universiti Malaysia Pahang
26600, Pekan, Pahang
Malaysia
nooramirasyuhada@gmail.com

Abstract: Thermal imaging is now widely used in important and high risk field. With the good performance to detect the object in poor lighting condition, thermal imaging is used as the advanced technology in the critical surveillance activity. Surveillance system become a critical issue when it comes to a critical area cover by the responsible party such as military , police and others security organization .Besides, the computing technology contributes the easiness of implementing digital image processing in many applications. This can greatly improve the effectiveness of the surveillance activity done at the critical surveillance area. Hence, this present paper proposed few techniques on image processing to enhance the surveillance efficiency based on the thermal image dataset. The selection of the correct technique is followed the specification, process and output from this thermal surveillance system. The method of frame difference is used since the detection is on the moving subject. Image processing is fully used to fulfil the identification of the subject. By using the edge characteristic of the subject, the identification and image analysis use the boundary information .The feature of subject detected is analysed to improve the identification of the existence of the potentially harmful subject. The algorithm developed able to identify the subject come across the critical surveillance area. Analysis of the study is using a dataset of night surveillance activities which include the possibilities of harmful and harmless subject. Finally , the system will automatically differentiate and identify the subject and indicate the exist subject is harmful or harmless subject . The experimental results show the detection with better accuracy.

Keywords: surveillance , thermal imaging, detection, potentially harmful subject.  [Download PDF]

4 SUPERVISED ANN CLASSIFICATION FOR ENGINEERING MACHINED TEXTURES BASED ON ENHANCED FEATURES EXTRACTION AND REDUCTION SCHEME


Mohammed W. Ashour, Fatimah Khalid

Faculty of Computer Science and Information Technology,
University Putra Malaysia, Selangor
eng.m.ashour@gmail.com
fatimahk@upm.edu.my

M. M. Abdulrazzaq
Faculty of Information Science and Technology,
University Kebangsaan Malaysia, Selangor
eng.alobaydee81@gmail.com

Abstract: Image classification involves the act of classifying images according to their extracted and selected features. Some of the main problems of image classification are the poor features that do not precisely represent an image, and the large dimensionality of data input passed to classifiers. To overcome these problems, an efficient feature extraction and selection technique is required which extracts and reduces the number of selected features and thus improves the classification accuracy. In this paper, feature extractions scheme followed by features dimensionality reduction technique is presented for image classification. The proposed methodology focuses mainly on three main stages for an input image, firstly extracting features by commonly used features extraction methods such as edge detection, and histogram. Secondly reducing the numbers of extracted features vector using the concept of Principal Component Analysis (PCA) for features selection and vectors dimensionality reduction. Finally, the feature vectors selected by the proposed technique are then input to a supervised Artificial Neural Network (ANN) classifier. Experiments are conducted on a dataset of 72 multi-class engineering surface textures produced by six different machining processes. The classification accuracy rate is calculated after testing 36 samples from our dataset. The experimental results show that the proposed algorithm is superior to some recent algorithms presented in the literature in many respects.  [Download PDF]

 5 AN EFFECTIVE APPROACH FOR FEATURE BASED CLOUD IMAGE SEGMENTATION

 

Achintya K. Mandal,
Deputy Registrar, Assam University, Silchar, INDIA
achintya99@hotmail.com

Abhoy Chand Mondal
Associate Professor, Department of Computer Sciences,
The University of Burdwan, INDIA

Abstract: In this article we have proposed an effective approach for cloud image segmentation for finding candidate tracer clouds from infrared and water vapor satellite imageries. Since cloud images are highly textures, the feature based segmentation techniques are expected to work well for such cases. First, we have extracted a number of features for each image pixel considering its 8-neighborhood and 24-neighborhood pixels information. Then the clouds are segmented using k-means clustering algorithm. Next considering the coldest cloud segment, candidate regions for tracer clouds are identified. Finally, with a set of features computed for each segment, quantitative characterization for the regions was determined. The overall method has been tested in several image sequences and in each case it is found to do an excellent job. [Download PDF]

Keywords: Cloud Image Segmentation, k-means clustering, Satellite Images, Tracer Cloud Patches

 

 

Advertisements

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s