Abstract
Image Classification is an important task within the field of computer vision. Image classification refers to the labelling of images into one of a number of predefined categories. Classification includes image sensors, image pre-processing, object detection, object segmentation, feature extraction and object classification. Image classification is an important and challenging task in various application domains, including biomedical imaging, biometry, video surveillance, vehicle navigation, industrial visual inspection, robot navigation, and remote sensing. Many Machine Learning and Deep Learning classification techniques like Artificial Neural Network(ANN), Decision Tree(DT), Support Vector Machine(SVM) ,Convolutional Neural Network(CNN), ResNet etc. have been developed for image classification. In this survey various Machine Learning and Deep Learning classification techniques are applied on various types of datasets. Machine learning algorithms generally give efficient and accurate result when applied on lighter datasets where as for heavier datasets Deep Learning algorithms are used.
In our survey we will analyze the algorithms like ResNet, convolutional neural network(CNN), Bagging, Bayesian, Decision trees(ID3), Support vector machines, Discriminant Analysis, Nearest Neighbors, Neural network, Random forests by applying them on various datasets to check if the algorithms provide the accurate result as expected. By doing the comparison of the accuracy obtained by applying all the algorithms on a particular dataset we get to know the most efficient algorithm that can be applied on that particular dataset for image classification. We also try to increase the size of the dataset and apply the algorithm to check if the algorithm performs as predicted, this is considered as critical analysis of the algorithm. Suppose an algorithm does not provide the predicted accuracy, we tweak the parameters that led to the decrease in the accuracy, this is considered as optimization of algorithms.