The use of machine learning algorithms for image recognition

Abstract

The article presents a way of using machine learning algorithms to recognize objects in images. To implement this task, an artificial neural network was used, which has a high adaptability and allows work with a very large set of input data. The neural network was described using a program written in the MATLAB simulation environment. The basic problem faced by the designer of objects recognition is to collect a sufficient training set of images to achieve the high probability of correct recognition. The set of learning patterns in the artificial neural networks may contain from several dozen thousands to one million training samples. In this article at the beginning the neural network was pre-trained trained based on the images included in the publicly available CIFAR 100 database, which are characterized by a small size of 32x32 pixels. It contains 70 000 images assigned to 10 basic categories. Then the author's database, consisting from 1000 pedestrians, cars and road signs was used. The article contains a description of applied algorithm, method of supervised learning and correction of weight coefficients, selection of activation function and operation on max pooling filter. The results of proposed solution are presented in the form of screenshots from calculations and in figures depicting results of recognized objects. Attention was also paid to the impact of used database for learning the network on the speed of calculations and recognition efficiency. The proper selection of number and types of layers, number of neurons, activation function and the value of the learning factor is very important in designing the neural network in application to objects recognition contained in the images. The problems occurring in the process of learning the neural networks and suggestions for their further improvement are also presented.

Handwritten Text Recognition System using Machine Learning

“…Have used R-CNN to solve detection in object classification problems and bounding boxes. [12] The use of machine learning algorithms for image recognition [Jan Matuszewski et al, 2020] To recognize objects in images, an artificial neural network was used (ANN).…”

CIDOC-CRM and Machine Learning: A Survey and Future Research

“…An interesting work for automatic art analysis is described in [50]. Note that there are several works that detect and identify objects from images: [51] describes the system YOLO that can be also used for detecting objects in moving images due to its fast response, [52] makes use of artificial neural networks to support the identification of objects in images and [53] proposes a fast and more accurate object detector. Finally, we could also mention Detector2 [54], which includes various object detection and segmentation algorithms and has been implemented by Facebook AI Research.…”