Implementation Of Image Analysis System By Using Convolution Neural Networks
B. Sridhar · i-manager’s Journal on Image Processing · 2020
In deep learning neural network architectures, the term "deep" usually refers to the number of hidden layers in the neural network. Traditional neural networks only contain 2-3 hidden layers, while deep networks can have as many as 150. One Analysis is the process to analyse various feature of the image such as segmentation of the image, classification of the images, etc. In this proposed work, a CNN based Image Analysis System has been proposed to detect the objects in real time image and classify the image based on the feature of extraction. The proposed method is implemented by using MATLAB and Python software. The system is trained with the CIFAR -10 and MINST Dataset and own image database. The performance of the proposed method is evaluated by using accuracy and loss factor. The proposed system is tested with unknown samples of images and also trained for accuracy and average test loss.