Object Recognition Using Convolutional Neural Networks

Abstract

This chapter intends to present the main techniques for detecting objects within images. In recent years there have been remarkable advances in areas such as machine learning and pattern recognition, both using convolutional neural networks (CNNs). It is mainly due to the increased parallel processing power provided by graphics processing units (GPUs). In this chapter, the reader will understand the details of the state-of-the-art algorithms for object detection in images, namely, faster region convolutional neural network (Faster RCNN), you only look once (YOLO), and single shot multibox detector (SSD). We will present the advantages and disadvantages of each technique from a series of comparative tests. For this, we will use metrics such as accuracy, training difficulty, and characteristics to implement the algorithms. In this chapter, we intend to contribute to a better understanding of the state of the art in machine learning and convolutional networks for solving problems involving computational vision and object detection.

Perancangan Sistem Deteksi Pelanggaran Penggunaan Helm Dengan Metode Deep Learning Menggunakan Yolov5 Ultralytic

“…Gambar 1 Model Deteksi YOLO [12] Gambar 1 memperlihatkan arsitektur YOLO mirip dengan jaringan saraf konvolusi yang terinspirasi oleh model GoogLeNet untuk klasifikasi gambar. Lapisan awal jaringan pertama-tama mengekstrak fitur gambar, dan lapisan yang terhubung sepenuhnya memprediksi probabilitas dan koordinat keluaran.…”

Lightweight and Parameter-Optimized Real-Time Food Calorie Estimation from Images Using CNN-Based Approach

“…In [18], Menezes et al discuss the latest object identification methods, such as you only look once, faster region convolutional neural network, and single-shot multibox detector. The authors, however, do not focus on the real-time food calorie estimation.…”

Investigating the RSSI-based Distance Classification using Median Confidence Interval in a Multi-Device BLE Environment

“…These systems primarily detect motion using image processing and background reduction to indicate human presence (Ahamad et al, 2020). Apart from this, several other detection algorithms exist, such as the pre-trained convolutional neural network (CNN) based models (Ahamad et al, 2020;Teles de Menezes et al, 2020). CNN-based models contribute to the automation filtering and feature extraction process of deep learning algorithms for object detection and classification (Teles de Menezes et al (2020).…”

“…Apart from this, several other detection algorithms exist, such as the pre-trained convolutional neural network (CNN) based models (Ahamad et al, 2020;Teles de Menezes et al, 2020). CNN-based models contribute to the automation filtering and feature extraction process of deep learning algorithms for object detection and classification (Teles de Menezes et al (2020). Several deep object detection algorithms such as You Only Look Once (YOLO), Single Shot Detector (SSD), Faster Region-based Convolutional Neural Network (Faster R-CNN), and Region-based Fully Convolutional Neural Network (R-FCN) were already studied for monitoring the adherence of the people to social distancing (Ahamad et al, 2020;Bhambani et al, 2020).…”