Over the past few years, Deep Neural networks (DNN) have been evolving rapidly as an engineering technology, with the models becoming larger and deeper. Image classification in computer vision plays a key role in various sectors including environmental monitoring, land cover classification, medical images, and urban planning. Image classification in which classify by assigning the label or class to an entire image. Traditional methods of Machine Learning, Deep Learning, and Computer Vision cannot match human-level performance such as image classification, image segmentation, feature extraction, image enhancement, and object detection. It is also simple because these other classifications have some standout features that make them simple to differentiate, making classification simple by the CNN model. This model may have a high modeling size, more time taken for process or feature extraction from the large sample data, and also process a large amount of data and lack adaptability to diverse datasets. This paper proposed the MobileNet Model for the classification and recognition of images. Using of well-trained sample dataset of the ImageNet dataset for a better classification process. To improve the accuracy of image classification by solving through these algorithms for handling complicated images, feature extraction processing a large amount of data for giving the better prediction by using MobileNet Model with ImageNet dataset.