In the present study an attempt was made to generate cadastral base from high resolution satellite image (LISS IV) and to integrate with land use land cover information. The digital cadastral map with survey number for Kolathupalayam village in Erode district of Tamil Nadu was scanned, digitized and parcels were extracted. Similarly parcels or field boundaries were digitized and extracted from satellite image and were statistically compared by area. The area obtained from both the source through digitization correlated well with a pearson correlation of 0.87 and it was significant at 5 per cent. Thus, the area comparisons from both methods are significant indicating boundaries of individual fields generated from satellite image matched well with the one generated from cadastral map. The cadastral base generated from satellite image was overlaid on the classified image (level III output) to identify and generate land cover information against each survey number. Thus, the LISS IV data can be used for the identification and extraction of cadastral boundaries with good accuracy.

No abstract

No abstract

Skin cancer is very important notable disease and it is probable to everyone nowadays, it flourishes on the area of body where it exposed to ultraviolet rays. It leads anomalous gain in skin cells. It initiate on various parts of body like face, hand and bottoms of the feet as cautious hole or spot. The initial investigation of anomalous gain is essence to cure the disease at early stage, and it still remains a feasible challenge in the scientific improvements. From the analysis, this paper endeavour to inspect the category of disease with the following improvements. Initially, the skin dataset from ISIC machine archive is utilized for image processing. Secondly, the values of dataset images are normalized by dividing all the RGB values by 255. Thirdly, keras sequential API is used to add one layer at a time, initiating from the input. The CNN can extract the features that are useful for classifying the image, by using the kernel filter matrix. MaxPool reduce the computational cost by down-sampling the image, and the relu activation function is implemented to provide non linearity to the network. The flatten layer is utilized to remodel the final feature maps into 1D vector. CNN model provides accuracy of 94.83% with 3297 images and ResNet 50 model has attained accuracy of 90.78% due to less number of images used for classification. AlexNet model has attained accuracy of 81.8% with 1300 images and GoogleNet V3 inception has attained accuracy of 96% with 3374 images. Finally Vgg16 model has attained accuracy of 97.3% with 5636 samples.

In the present study an attempt was made to perform land use land cover classification at Level-III in order to discriminate and map individual crops. IRS Resources at 2 LISS IV sensor imagery (5.0 m spatial resolution) of September 2014 was utilized for the study. A hybrid classification approach of unsupervised classification followed by supervised classification was adopted to identify and map the crop area in Kodumudi block, Erode district of Tamil Nadu. Signature evaluation was carried out to study the class separability and through cross tabulation and the accuracy was assessed by error matrix. The signature separability analysis to classify various land cover classes indicated that the class viz., waterbody, settlement, sandy area and fallow land were better and for vegetation sub-classes viz., individual crops were poor, which means classification of individual crops was a challenge. The overall accuracy with three different algorithms varied from 56 to 65 per cent and this low accuracy was due to the problem in discriminating the tonal variation and spectral pattern of individual crops in the study area. Thus, classification of vegetation categories into individual crops using LISS IV data resulted in moderate classification accuracy in areas with multiple cropping.