eprintid: 11449
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/14/49
datestamp: 2023-11-10 03:25:57
lastmod: 2023-11-10 03:25:57
status_changed: 2023-11-10 01:15:18
type: article
metadata_visibility: show
creators_name: Qayyum, A.
creators_name: Saeed Malik, A.
creators_name: Saad, N.M.
creators_name: Iqbal, M.
creators_name: Abdullah, M.F.
creators_name: Rasheed, W.
creators_name: Abdullah, T.A.B.R.
creators_name: Bin Jafaar, M.Y.
title: Image classification based on sparse-coded features using sparse coding technique for aerial imagery: a hybrid dictionary approach
ispublished: pub
keywords: Aerial photography; Aircraft detection; Antennas; Codes (symbols); Discrete cosine transforms; Discrete wavelet transforms; Glossaries; Image classification; Image coding; Image enhancement; Learning algorithms; Learning systems; Object recognition; Remote sensing; Satellite imagery; Satellites; Unmanned aerial vehicles (UAV), Discrete tchebichef transforms; Discriminative features; Finite Ridgelet Transform; Histogram of oriented gradients; Image processing and computer vision; Scale invariant feature transforms; SIFT; Sparse coding, Classification (of information)
note: cited By 8
abstract: This work offers an approach to aerial image classification for use in remote sensing object recognition, image processing and computer vision. Sparse coding (SC) is used to classify unmanned-aerial-vehicle (UAV) and satellite images because SC representation can generalize a large dataset and improve the detection of distinctive features by reducing calculation time for feature matching and classification. Features from images are extracted based on the following descriptors: (a) Scale Invariant Feature Transform; (b) Histogram of Oriented Gradients; and (c) Local Binary Patterns. SC representation and local image features are combined to represent global features for classification. Features are deployed in a sparse model to store descriptor features using extant dictionaries such as (a) the Discrete Cosine Transform and (b) the Discrete Wavelet Transform. An additional two dictionaries are proposed as developed for the present work: (c) the Discrete Ridgelet Transform (DRT) and (d) the Discrete Tchebichef Transform. The DRT dictionary is constructed by using the Ricker wavelet function to generate finite Ridgelet transforms as basis elements for a hybrid dictionary. Different pooling methods have also been employed to convert sparse-coded features into a feature matrix. Various machine learning algorithms are then applied to the feature matrix to classify objects contained in UAV and satellite imagery data. Experimental results show that the SC model secured better accuracy rates for extracted discriminative features contained in remote sensing images. The authors concluded that the proposed SC technique and proposed dictionaries provided feasible solutions for image classification and object recognition. © 2017, The Natural Computing Applications Forum.
date: 2019
publisher: Springer London
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85039749366&doi=10.1007%2fs00521-017-3300-5&partnerID=40&md5=6fe11b9fa23c604501e4d591eedc41b5
id_number: 10.1007/s00521-017-3300-5
full_text_status: none
publication: Neural Computing and Applications
volume: 31
number: 8
pagerange: 3587-3607
refereed: TRUE
issn: 09410643
citation:   Qayyum, A. and Saeed Malik, A. and Saad, N.M. and Iqbal, M. and Abdullah, M.F. and Rasheed, W. and Abdullah, T.A.B.R. and Bin Jafaar, M.Y.  (2019) Image classification based on sparse-coded features using sparse coding technique for aerial imagery: a hybrid dictionary approach.  Neural Computing and Applications, 31 (8).  pp. 3587-3607.  ISSN 09410643