<span>Hyperspectral imaging (HSI) is composed of several hundred of narrow bands (NB) with high spectral correlation and is widely used in crop classification; thus induces time and space complexity, resulting in high computational overhead and Hughes phenomenon in processing these images. Dimensional reduction technique such as band selection and feature extraction plays an important part in enhancing performance of hyperspectral image classification. However, existing method are not efficient when put forth in noisy and mixed pixel environment with dynamic illumination and climatic condition. Here the proposed Sematic Feature Representation based HSI (SFR-HSI) crop classification method first employ Image Fusion (IF) method for finding meaningful features from raw HSI spectrally. Second, to extract inherent features that keeps spatially meaningful representation of different crops by eliminating shading elements. Then, the meaningful feature set are used for training using Support vector machine (SVM). Experiment outcome shows proposed HSI crop classification model achieves much better accuracies and Kappa coefficient performance. </span>
The challenging task in the field of Document Image Analysis is automatic recognition of handwritten characters present in a scanned document. The recognition of characters in a document is achieved by Optical Character Recognition (OCR) system. In this paper, a hybrid feature extraction technique is proposed for recognizing handwritten Kannada characters. The proposed technique uses the local and global features as hybrid features. These features are extracted from each input image. 3600 samples are used as training data set to obtain consistent feature values. K-nearest neighbor classifier is used to classify the characters based on the feature values. The proposed method is tested on a dataset of 1200 samples and at present it shows an overall accuracy of 87.33%.
In India, a document may contain text lines in more than one language forms. For Optical Character Recognition (OCR) of such a multilingual document, it is necessary to identify different language forms of the input document, before feeding the documents to the OCRs of individual language. In this paper, a simple but efficient technique of language identification for Kannada, Hindi and English text lines from a printed document is presented. The proposed system is based on the characteristic features of top-profile and bottom-profile of individual text lines of the input document image. The feature extraction is achieved by finding the behavior of the characteristics of the top and bottom profiles of individual text lines. The system is trained to learn the behavior of the top and bottom profiles with a training data set of 800 text lines. Range of feature values of top and bottom profiles for all the three languages are obtained and stored in knowledge base for later use during decision-making. For a new text line, necessary features are extracted from the top and bottom profiles and the feature values obtained are compared with the stored knowledge base.A new text line is classified to the type of the language that falls within that range. The proposed system is tested on 600 text lines and an overall classification accuracy of 96.6% is achieved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.