No abstract

No abstract

Vegetation mapping is an active research area in the domain of remote sensing. This study proposes a methodology for the mapping of vegetation by integrating several vegetation indices along with original spectral bands. The Land Use Land Cover classification was performed by two powerful Machine Learning techniques, namely Random Forest and AdaBoost. The Random Forest algorithm works on the concept of building multiple decision trees for the final prediction. The other Machine Learning technique selected for the classification is AdaBoost (adaptive boosting), converts a set of weak learners into strong learners. Here, multispectral satellite data of Dehradun, India, was utilised. The results demonstrate an increase of 3.87% and 4.32% after inclusion of selected vegetation indices by Random Forest and AdaBoost respectively. An Overall Accuracy (OA) of 91.23% (kappa value of 0.89) and 88.59% (kappa value of 0.86) was obtained by means of the Random Forest and AdaBoost classifiers respectively. Although Random Forest achieved greater OA as compared to AdaBoost, interestingly AdaBoost provided better class-specific accuracy for the Shrubland class compared to Random Forest. Furthermore, this study also evaluated the importance of each individual feature used in the classification. Results demonstrated that the NDRE, GNDVI, and RTVIcore vegetation indices, and spectral bands (NIR, and Red-Edge), obtained higher importance scores.

This paper proposes a novel method to address the problem of segmentation, for uneven lighting images. Though there are many segmentation methods, but most of them are based on either the fixed window method or window merging technique. Limitation of such methods is that, initial size of window is selected manually and segmentation accuracy greatly depends upon the proper choice of initial window size. In the proposed work, problem of uneven illumination condition has been addressed using dynamic window growing approach. The proposed algorithm is based on an incremental window growing approach using entropy based selection criteria. The window thus fixed by the selection criteria are considered as sub-images and each sub-images has been segmented by using minimum standard deviation difference based thresholding to improve the segmentation result. The result of the experiments show that the proposed method can deal with higher number of segmentation problem and improve the overall performance for uneven lighting image segmentation. General TermsThresholding, window size, image binarization, entropy, standard deviation.

Image binarization is still a relevant research area due to its wide range of applications in the field of document analysis and recognition. Accuracy of binarization methods affected by many factors such as shadows non-uniform illumination, low contrast, large signal-dependent noise etc. This paper provides a comprehensive survey of major binarization techniques. We also emphasis on the problems being encountered and the related issues in the research area of document image binarization. In addition, some important issues affecting the performance of image binarization methods are also discussed. This literature review suggests that designing a suitable document image binarization method is a prerequisite for a successful document image analysis and recognition. General TermsImage Processing, Document image analysis.