Comparative Analysis of Machine Learning
Algorithms with and without Feature Extraction
Image recognition is one of the core disciplines in Computer Vision. It is one of the most widely researched topics of the last few decades. Many advances in image recognition in the past decade, has made it one of the most efficient and powerful disciplines of all, having its applications in every sector including Finance, Healthcare, Security services, Agriculture and many more. Feature extraction is an integral part of image recognition. It helps in training the model more efficiently and with a higher accuracy, by getting rid of any unwanted or unnecessary features, thus reducing the dimensionality of the input image. This also helps in reducing the computational resources required by the algorithm to train, thus making it affordable for people with low end setups. Here we compare the accuracies of different machine learning classification algorithms, and their training times, with and without using feature Extraction. For the purpose of extracting features, a convolutional neural network was used. The model was trained and tested on the data of 12 classes containing a total of 2,175 images. For comparisons, we chose the Logistic regression, K-Nearest Neighbors Classifier, Random forest Classifier, and Support Vector Machine Classifier.