Segmentation and Classification of Hyper-Spectral Skin Data

2008 ◽  
pp. 245-252 ◽  
Author(s):  
Hannes Kazianka ◽  
Raimund Leitner ◽  
Jürgen Pilz
Keyword(s):  
Hyper Spectral

scholarly journals Effective Morphological Transformation and Sub-pixel Classification of Clustered Images

2019 ◽  
Vol 8 (01) ◽  
pp. 08-14
Author(s):  
Mr. B. Naga Rajesh
Keyword(s):  
Time Complexity ◽  
Research Work ◽  
Morphological Operations ◽  
Morphological Transformation ◽  
Structuring Element ◽  
Hyper Spectral ◽  
Hyper Spectral Imaging ◽  
Pixel Scale ◽  
Spatial Regularization

The main aim of this research work is to perform the morphological operations with reduced time complexity and area complexity. Morphological operation is the key element in any image processing. Finding the maximum and minimum using a window of defined size will imply to the morphological dilation and erosion respectively. So the proposed algorithm should be fast in the comparison and sorting, this way the time complexity could be reduced. It’s believed that the anchor concept will fetch this cause. The idea behind this is it fixes a pixel and setting it as the center pixel all the surrounding pixels will be processed. Moreover this is now been implemented for rectangular structuring element. This paper attempts the same for flat and 3D structuring elements. Hyper-spectral Imaging is a developing zone of remote detecting applications. Hyper-spectral pictures incorporate more extravagant and better otherworldly data than the multi-spectral pictures got previously. Hyper-otherworldly pictures are described by an exchange off between the unearthly and spatial resolution. The principle issue of the hyper-ghostly information is the generally low spatial goal. For arrangement, the serious issue brought about by low spatial goal is the blended pixels. Blended pixels alluded to the pixels which are involved by more than one land spread class. In the proposed procedure another strategy is utilized to address the issue of blended pixels and to get a better spatial goal of the land spread characterization maps. The strategy misuses the upsides of both picture bunching methods and phantom dimming calculations, so as to decide the fragmentary plenitudes of the classes at a sub-pixel scale. Spatial regularization by Flank planning method is at last performed to spatially find the got classes at sub-pixel level.

Classification of Hyperspectral Data Based on Semi-Supervised Tri-Training Learning Framework

2012 ◽  
Vol 500 ◽  
pp. 374-382
Author(s):  
Rui Huang ◽  
Li Na Zhou
Keyword(s):  
Spectral Data ◽  
Classification Problem ◽  
Decision Fusion ◽  
Hyperspectral Data ◽  
Learning Framework ◽  
Training Scheme ◽  
Hyper Spectral ◽  
Multiple Classifier ◽  
Classifier Learning

A semi-supervised learning framework based on the tri-training scheme is proposed for the classification of hyper spectral data. The framework involves two stages: multiple classifier learning by the improved tri-training and integrating the outputs of classifiers to the final hypothesis by decision fusion. To settle the ill-posed classification problem, in the stage of classifier learning, the label confidence of each learner is measured by the improved estimation of classifier error, and self-training is introduced to expand the labeled set using unlabeled samples with confident labels assigned by classifiers. Hyper spectral data classification experiments show the effectiveness of the proposed framework.

scholarly journals Distance-based separability criterion of ROI in classification of farmland hyper-spectral images

2017 ◽  
Vol 10 (5) ◽  
pp. 177-185 ◽  
Author(s):  
Tang Jinglei ◽  
◽  
Miao Ronghui ◽  
Zhang Zhiyong ◽  
Xin Jing ◽  
...  
Keyword(s):  
Separability Criterion ◽  
Hyper Spectral

scholarly journals Assessment of Geospatial Approaches Used for Classification of Crops

2018 ◽  
Vol 3 (3) ◽  
pp. 271-279
Author(s):  
Suraj Kumar Singh ◽  
Shruti Kanga ◽  
Sudhanshu
Keyword(s):  
Support Vector Machine ◽  
Support Vector ◽  
General Survey ◽  
Processing Strategies ◽  
Hyper Spectral ◽  
Satellite Sensors ◽  
The Government ◽  
Spot 5 ◽  
Work Done

Harvests distinguishing proof from remotely detected pictures is fundamental because of utilization of remote identifying images as a contribution for rural and monetary arranging by the government and private offices. Accessible satellite sensors like IRS AWIFS, LISS, SPOT 5 and furthermore LANDSAT, MODIS are great wellsprings of multispectral information with various spatial resolutions and Hyperion, Hy-Map, AVIRIS are great wellsprings of hyper-Spectral. The technique for current research is choice of satellite information; utilization of appropriate strategy for arrangement and checking the accuracy. From most recent four decades different specialists have been taking a shot at these issues up to some degree yet at the same time a few difficulties are there like numerous products distinguishing proof, separation of harvests of the same sort this paper gives a general survey of the work done in this vital zone. Multispectral and hyper-spectral images contain spectral data about the crops. Good delicate registering and examination aptitudes are required to order and distinguish the class of enthusiasm from that datasets. Various specialists have worked with supervised and unsupervised arrangement alongside hard classifiers and also delicate processing strategies like fuzzy C mean, support vector machine and they have been discovered distinctive outcomes with various datasets.

Sign in / Sign up

Export Citation Format

Share Document