Multi-spectral image

Hyperspectral remote sensing collects spectral images across the electromagnetic spectrum. Hyperspectral remote sensing detects many more spectral bands than traditional multispectral remote sensing. Hyperspectral imagers cover the visible, near infrared, short-wave infrared and thermal infrared spectral ranges which are useful for studying vegetation (Schlerf et al, 2012). Hyperspectral sensors include the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) and the EO-1 satellite, both of which

pan-sharpening technique, which aims at fusing a low-resolution multispectral (LRM) image and a high-resolution panchromatic (HRP) image in order to produce a high-resolution multispectral (HRM) image, has become an effective pre-processing technique in many remote sensing applications [1]. Many remote sensing applications such as land-cover classification, map updating, reconnaissance, etc. demands images with both high spectral and high spatial resolution however most remote sensing satellites such as

INTRODUCTION 1.1 IMAGE An image is an artifact that depicts or records visual notion, for example a two-dimensional picture, that has a comparable appearance to some subject – normally a physical object or a person, for this reason offering an outline of it. Photos may be -dimensional, which includes a photo, display screen show, and as well as a 3-dimensional, inclusive of a statue or hologram. They may be captured by optical devices – such as cameras, mirrors, lenses, telescopes, microscopes, and

Image classification and analysis processes are for digitally identify and classify pixels in the data. It performed on a multi-channel dataset. This process allocate each pixel and image to a particular class or theme and depend on statistical features of brightness value pixel. There are various approaches for digital classification: Supervised classification predicate the spectral features of training areas are particular areas of known types of land cover are obtained from the image. Each pixel

are many categories of spectroscopy eg. Atomic and infrared spectroscopy, which have numerous uses and are essential in the world of science. When investigating spectroscopy four parameters have to be considered; spectral range, spectral bandwidth, spectral sampling and signal-to-noise ratio, as they describe the capability of a spectrometer. In the world of spectroscopy there are many employment and educational opportunities as the interest in spectroscopy and related

Hyperspectral imaging (HSI) order has progressed toward becoming a well known research point as of late, and compelling include extraction is a vital stride before the arrangement undertaking. Generally, Spectral component extraction methods are connected to the HSI information shape straightforwardly. This paper shows a novel calculation for HSI include extraction by abusing the curvelet transformed space by means of a moderately new unearthly component preparing procedure—solitary range examination

Classification is a principle technique in hyperspectral images (HSI) analysis, where a label is assigned to each pixel based on its characteristics. Applying machine learning techniques to these datasets need special consideration, since the hyperspectral images are typically represented by features vectors of extremely high dimensions. A robust HSI classification requires a prudent combination of deep feature extractor and powerful classifier. In the last one decade, extensive classification methods

of factors such as site assessment, plant type, and climatic conditions at the time of planting, fertilisation, early detection of insect attacks, and weed control. The advantage of remote sensing technique is the combination of detailed spectral data to aid image classification and tree crown discrimination. For the mapping of vegetation, landscape, insect infestation and invasive weeds from the remotely sensed data are usually supervised classification , unsupervised

comparison of results of two image using it. They also proposed comparison of new hybrid algorithm with older. Discrete cosine transform and variance combination with hybrid discrete wavelet transform. These techniques provides good results in terms of Pseudo signal to noise ratio and mean square error. [11] Kede ma et al. has worked on the untouched area of perceptual quality assessment as used for multi-solarization image fusion. The authors have designed multi-solarization fusion data-list

Zeng et al. have worked on perception evaluation. Authors have used multi-solarization image fusion algorithms. In this research first authors have build a database that contains source input images with multiple exposure levels(>= 3) together with fuse images generated by both standard and new image fusion algorithms. In this research, image fusion is active in the last ten years and a valid number of image fusion and objective image quality assessment methods have been proposed. In this paper, authors