Research on Image Classification Algorithm Based on Convolutional Neural Network

Abstract

Nowadays, we are in the information age. Pictures carry a lot of information and play an indispensable role. For a large number of images, it is very important to find useful image information within the effective time. Therefore, the excellent performance of the image classification algorithm has certain influence factors on the result of image classification. Image classification is to input an image, and then use a certain classification algorithm to determine the category of the image. The main process of image classification: image preprocessing, image feature extraction and classifier design. Compared with the manual feature extraction of traditional machine learning, the convolutional neural network under the deep learning model can automatically extract local features and share weights. Compared with traditional machine learning algorithms, the image classification effect is better. This paper focuses on the study of image classification algorithms based on convolutional neural networks, and at the same time compares and analyzes deep belief network algorithms, and summarizes the application characteristics of different algorithms.

Noaa Image Classification Using Google’s Teachable Machine

“…The processed image data comes from the NOAA-15, NOAA-18, and NOAA-19 satellites which passes through Indonesian territory. Ground station receiver device that is used is the WeSaCom APT-06 with a turnstile antenna and working on frequency 137.10 MHz to 137.9125 MHz (Luo, 2021).…”

“…CNN algorithm has advantages in image classification tasks. Preliminary study (Luo, 2021) on the deep learning image classification method based on CNN, which can achieve high recognition accuracy. The research for NOAA image classification using CNN can be a recommendation for future works.…”

Research on mass image classification based on CNN deep learning

“…pytorch framework [6] is used to build neural network, select different networks and optimizers, set different learning rates, and constantly adjust parameters to improve the classification accuracy as much as possible.…”