OBJECT RECOGNITION WITH DEEP LEARNING AND MACHINE LEARNING METHODS

The field of computer vision, which is widely studied area, is basically the imitation of the human vision system with digital devices. Computer systems perform operations through digital images or video images and decide according to the result. In this context, object recognition must be performed at the first stage in order to extract meaningful information from the image. In this study, the application of object recognition was developed using the deep learning method, which is especially popular in recent years. It has also been compared with classical machine learning methods often used in recognition applications. The proposed method developed with Convolutional Neural Network (CNN) has been compared by using the Histogram of Oriented Gradient (HOG) features and classifying them with Support Vector Machines (SVM) and K-Nearest Neighbor (KNN) methods. Experimental results show that the proposed CNN method is more successful than HOG+SVM, and HOG+KNN methods.