An Efficient Comparative Analysis of CNN-based Image Classification in the Jupyter Tool Using Multi-Stage Techniques

The main process of this image classification with a convolution neural network using deep learning model was performed in the programming language Python code Jupyter tool, mainly data set IRS P-6 LISS IV from an Indian remote sensing satellite high resolution multi-spectral camera around 5.8m 817 km altitude Delhi image. To classify areas within cropped required to apply enhancement techniques, size 1000 mb. view file high-end software for opening. For that, initially, ERDAS imaging viewer used cropping into correct pixels. based on that preprocessing applying filters enhancement. And model, train sample images same pixels, collected group objects were cropped. Then we needed use rate and epoch improve object detection accuracy notebook tool tensorflow machine produce 90.78%.