Ghazali Sulong

Recovering defective Landsat 7 Enhanced Thematic Mapper Plus images via multiple linear regression model

Since 2003, the scan line corrector (SLC) of the Landsat 7 Enhanced Thematic Mapper Plus (ETM+) sensor has failed permanently, inhibiting the retrieval or scanning of 22% of the pixels in each Landsat 7 SLC-off image. This utter failure has seriously limited the scientific applications and usability of ETM+ data. Precise and complete recovery of the missing pixels for the Landsat 7 SLC-off images is a challenging issue and developing an efficient gap-fill algorithm with improved ETM+ data usability has been ever-demanding. In this study, a new gap filling method has been introduced to reconstruct the SLC-off images via multi-temporal SLC-off auxiliary fill images. A correlation is established between the corresponding pixels in the target SLC-off image and two auxiliary fill images in parallel using the multiple linear regressions model. Both simulated and actual defective Landsat 7 images were tested to assess the performance of the proposed model by comparing with two multi-temporal data based methods, the local linear histogram matching method and Neighbourhood Similar Pixel Interpolator method. The quantitative evaluations indicate that the proposed method makes an accurate estimate of the missing values even for more temporally distant fill images.

Splicing image forgery identification based on artificial neural network approach and texture features

Splicing Image Forgery Identification controls and picture tampering with no proof being left behind has turned out to be exceptionally moderate and exceedingly utilized, because of presence of to a great degree intense altering apparatuses, for example, Adobe Photoshop. Along these lines, there has been a quick expansion of the digitally adjusted pictures on the Internet and prevailing press. The genuineness of a digital image experiences extreme dangers because of the ascent of capable digital image altering devices that effectively adjust the image substance without leaving any obvious hints of such changes. The splicing forgery should be possible by replicated a one/more area from source image and pasted into an objective picture to create a composite image called spliced image. In this manner, this sort of forgery is viewed as challenge issue difficult from tamper identification perspective. To influence the issue most exceedingly awful some to post preparing impacts, for example, blurring, JPEG compression, rotation and scaling perhaps presented in the spliced image. This study aims to perform quantification and data analysis following feature extraction using computational techniques to detect interesting textural and anatomical changes, these extracted features then can be used as a key to distinguish between different classes (Splicing Image and non-Splicing image). This paper presents a new framework to identify the spliced image by exploiting the image texture features, and to automatically identification of spliced images. To accurately identify the spliced image, the proposed solution uses different texture features to capture deferent texture related to the edge of the object and the colour features. We have combine these features to produce a good vector to describe the splice object. Two models have been proposed in this paper first combine the vectors of the three features and feed them to the ANN classifier. Second, use the majority voting of the result of three features to take the decision. This is followed by a ANN classifier; in this model we have trained the system with 30 training 20% validation 50% testing. We evaluated the effectiveness of the classification framework for identifying spliced images by compare the result with the manual label which is done by the people who have created the data sets. In this approach we have combine different features to capture different information and feed them to the neural network to identify the splicing image. The findings outcome from this study have shown an improved approach that automatically splicing image forgery identification. We have evaluated the splicing image forgery identification using the texture features. The identification accuracy in the technique used is about 98.06%., with 99.03% sensitivity and 96.07% specificity.

Classification of Arabic Writer Based on Clustering Techniques

Arabic text categorization for pattern recognitions is challenging. We propose for the first time a novel holistic method based on clustering for classifying Arabic writer. The categorization is accomplished stage-wise. Firstly, these document images are sectioned into lines, words, and characters. Secondly, their structural and statistical features are obtained from sectioned portions. Thirdly, F-Measure is used to evaluate the performance of the extracted features and their combination in different linkage methods for each distance measures and different numbers of groups. Finally, experiments are conducted on the standard KHATT dataset of Arabic handwritten text comprised of varying samples from 1000 writers. The results in the generation step are obtained from multiple runs of individual clustering methods for each distance measures. The best results are achieved when intensity, lines slope and their combination set of features are applied. It is demonstrated that different numbers of clusters having good set of features can deliver significant improvements for the handwritten structures clustering.

Recovering the large gaps in Landsat 7 SLC-off imagery using weighted multiple linear regression (WMLR)

Since 2003, the permanent failure of the scan line corrector (SLC) of the Landsat Enhanced Thematic Mapper Plus (ETM+) sensor has seriously limited the scientific applications and usability of ETM+ data. While a number of methods have been conducted to fill the regular un-scanned locations in ETM+ SLC-off images, only a few researches have been developed to recover the large gap areas in such images. In this study, an innovative gap filling method has been introduced to reconstruct the large gap locations in SLC-off images via multi-temporal auxiliary fill images. A correlation is established between the corresponding pixels in the target SLC-off image and two auxiliary fill images in parallel using the multiple linear regression (MLR) model in two successive steps. In the first step, almost half the gap locations have been recovered using the MLR model, then in the second step a weighted multiple linear regression (WMLR) algorithm is proposed to recover the remaining missing values. The simulated and actual case studies show that the proposed approach may provide a powerful tool for recovering the large gaps in SLC-off images, especially when there is a long time interval between the auxiliary fill images and the target SLC-off image.

Classification of colorectal cancer using clustering and feature selection approaches

Accurate cancer classification and responses to treatment are important in clinical cancer research since cancer acts as a family of gene-based diseases. Microarray technology has widely developed to measure gene expression level changes under normal and experimental conditions. Normally, gene expression data are high dimensional and characterized by small sample sizes. Thus, feature selection is needed to find the smallest number of informative genes and improve the classification accuracy and the biological interpretability results. Due to some feature selection methods neglect the interactions among genes, thus, clustering is used to group the similar genes together. Besides, the quality of the selected data can determine the effectiveness of the classifiers. This research proposed clustering and feature selection approaches to classify the gene expression data of colorectal cancer. Subsequently, a feature selection approach based on centroid clustering provide higher classification accuracy compared with other approaches.

K-means clustering with infinite feature selection for classification tasks in gene expression data

In the bioinformatics and clinical research areas, microarray technology has been widely used to distinguish a cancer dataset between normal and tumour samples. However, the high dimensionality of gene expression data affects the classification accuracy of an experiment. Thus, feature selection is needed to select informative genes and remove non-informative genes. Some of the feature selection methods, yet, ignore the interaction between genes. Therefore, the similar genes are clustered together and dissimilar genes are clustered in other groups. Hence, to provide a higher classification accuracy, this research proposed k-means clustering and infinite feature selection for identifying informative genes in the selected subset. This research has been applied to colorectal cancer and small round blue cell tumors datasets. Eventually, this research successfully obtained higher classification accuracy than the previous work.