This paper proposes a novel morphological approach for segmentation of document images in the National Institute of Standards and Technology (NIST) Database. Document Image Analysis involves transformation of any information presented on paper into an equivalent symbolic representation accessible to computer information processing. For better storage and intelligent processing, information presented on paper is now being converted into electronic form. This needs processing of documents using image analysis algorithms. The morphological approach quantitatively describes operations effective for the shape of objects in an image. The mathematical morphology describes such operations by combinations of basic set operations between an image and a small object called a structuring element. The segmentation oriented geometrical features such as size, shape, contrast, or connectivity are efficiently dealt in mathematical morphology. In this paper, morphological approach is used for segmenting the document images. The performance of the proposed method has been evaluated using many text documents. The National Institute of Standards and Technology, Technology Administration, U. S. database of document images has been used in order to carry out experimental work. The image document database used is NIST DATABASE, Federal Register Document Image Database. NIST Special Database 25 – volume 1.(NISTIR 6245). The proposed technique has been tested for various documents like multi-column, multi-article, multi-font, multi-orientation and promising results are obtained. At the end the obtained performance is also compared with other well-known page segmentation algorithms.

This study introduced the potential of microwave application in the determination of alkaloid in Dioscorea hispida rhizome. This microwave device is used to measure the coefficient permitivity of microwave level at rhizome surface using mechanical probe. With the same rhizomes, 40 grams was selected for chemical analysis at a laboratory for the programme of East Coastal Economic Regions – Kementerian Pengajan Tinggi, Universiti Sultan Zainal Abidin, Malaysia (ECER-KPT UniSZA). The sample were selected from 12 portion of 2 plants (I and B) collected from Kampung Kudat, Ajil, Terengganu, Malaysia. The result show that the correlation between microwave level and weight of alkaloid with regression, R2 is >0.8 is acceptable. Using SPSS, the ANOVA value shows significant correlation between microwave level and weight of alkaloid >0.05. This work is grouped as nondestructive method to detect the dioscorine which is one of the alkaloid components in the rhizome.

Epilepsy is a common neurological disorder that is characterized by recurrent unprovoked seizures. About 40 to 50 million people worldwide are reported to have epilepsy. In this paper the authors present clinical decision support system (DSS) for the diagnosis of epilepsy. The DSS is developed by using Multilayer Perceptron (MLP), Generalized Feed Forward Neural Network (GFF-NN) and Elman Neural Network (E-NN). The validity of neural networks to diagnose the epilepsy is checked and the most suitable neural network is recommended for the diagnosis of epilepsy. Also the different feature enhancement techniques like principal component analysis (PCA), FFT and statistical parameters are used for the input dimensionality reduction. Epilepsy diagnosis is modeled as the classification of normal EEG, interictal EEG and ictal EEG. With the different input dimensionality reduction methods performance parameters of MLP, GFF-NN and E-NN are measured and compared. For the GFF-NN, number of free parameter is reduced up to 92.22% when PCA is used for input dimensionality reduction with the overall accuracy of 98.61%.