Image Classification Based On CNN: A Survey

Abstract

Computer vision is one of the fields of computer science that is one of the most powerful and persuasive types of artificial intelligence. It is similar to the human vision system, as it enables computers to recognize and process objects in pictures and videos in the same way as humans do. Computer vision technology has rapidly evolved in many fields and contributed to solving many problems, as computer vision contributed to self-driving cars, and cars were able to understand their surroundings. The cameras record video from different angles around the car, then a computer vision system gets images from the video, and then processes the images in real-time to find roadside ends, detect other cars, and read traffic lights, pedestrians, and objects. Computer vision also contributed to facial recognition; this technology enables computers to match images of people’s faces to their identities. which these algorithms detect facial features in images and then compare them with databases. Computer vision also play important role in Healthcare, in which algorithms can help automate tasks such as detecting Breast cancer, finding symptoms in x-ray, cancerous moles in skin images, and MRI scans. Computer vision also contributed to many fields such as image classification, object discovery, motion recognition, subject tracking, and medicine. The rapid development of artificial intelligence is making machine learning more important in his field of research. Use algorithms to find out every bit of data and predict the outcome. This has become an important key to unlocking the door to AI. If we had looked to deep learning concept, we find deep learning is a subset of machine learning, algorithms inspired by structure and function of the human brain called artificial neural networks, learn from large amounts of data. Deep learning algorithm perform a task repeatedly, each time tweak it a little to improve the outcome. So, the development of computer vision was due to deep learning. Now we'll take a tour around the convolution neural networks, let us say that convolutional neural networks are one of the most powerful supervised deep learning models (abbreviated as CNN or ConvNet). This name ;convolutional ; is a token from a mathematical linear operation between matrixes called convolution. CNN structure can be used in a variety of real-world problems including, computer vision, image recognition, natural language processing (NLP), anomaly detection, video analysis, drug discovery, recommender systems, health risk assessment, and time-series forecasting. If we look at convolutional neural networks, we see that CNN are similar to normal neural networks, the only difference between CNN and ANN is that CNNs are used in the field of pattern recognition within images mainly. This allows us to encode the features of an image into the structure, making the network more suitable for image-focused tasks, with reducing the parameters required to set-up the model. One of the advantages of CNN that it has an excellent performance in machine learning problems. So, we will use CNN as a classifier for image classification. So, the objective of this paper is that we will talk in detail about image classification in the following sections.