Subhashree Subudhi
Indian Institutes of Information Technology
15 Papers
34 Citations
Subhashree Subudhi is an academic researcher from Indian Institutes of Information Technology. The author has contributed to research in topics: Hyperspectral imaging & Feature extraction. The author has an hindex of 4, co-authored 15 publications. Previous affiliations of Subhashree Subudhi include International Institute of Minnesota & International Institute of Information Technology.
Chat about Author
Papers
A Survey on Superpixel Segmentation as a Preprocessing Step in Hyperspectral Image Analysis
TL;DR: Superpixel segmentation is a process of segmenting the spatial image into several semantic subregions with similar characteristic features, such grouping by similarity can significantly ease the subsequent processing steps.
A Review of Unsupervised Band Selection Techniques: Land Cover Classification for Hyperspectral Earth Observation Data
TL;DR: A hyperspectral image (HSI) is a collection of several narrow-band images that span a wide spectral range, and the issue of removing redundancy is commonly called the band selection (BS) problem and refers to identifying an optimal subset of bands for further HSI processing.
46
Dictionary-based classifiers for exploiting feature sequence information and their application to hyperspectral remotely sensed data
TL;DR: Three novel dictionary-based approaches such as Sequence Classifier (SC), Sequence-dictionary-based k-Nearest Neighbours Classifiers (SDk-NN) and Combined-d dictionary- based k- NearestNeighbours classifier (CDk-nn) are proposed in this paper and found to be effective.
20
Spectral clustering and spatial Frobenius norm-based Jaya optimisation for BS of hyperspectral images
TL;DR: A novel framework for hybrid band selection (BS), which incorporates clustering (spectral) and intra-band (spatially filtered) de-correlation measure (Frobenius norm) as maximisation of two cost functions.
20
PSO-Based Synthetic Minority Oversampling Technique for Classification of Reduced Hyperspectral Image
Subhashree Subudhi,Ram Narayan Patro,Pradyut Kumar Biswal +2 more
- 01 Jan 2019
TL;DR: In this proposed approach, first principal component analysis (PCA) algorithm is applied for feature reduction, followed by application of synthetic minority oversampling technique (SMOTE) on the reduced dimensional dataset.
10