Region-based Object Detection and Classification using Faster R-CNN

Abbas, Syed Mazhar; Singh, Sanjiv

doi:10.1109/ciact.2018.8480413

Cited by 48 publications

(17 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The connections among neurons present patterns like the ones observed in the animal visual cortex [15]. They proved to be a useful tool regarding applications such as object detection [16], fault diagnosis [13], among others. The basic CNN is composed of an input layer, alternating convolutional and pooling layers, fully connected layers and an output layer [15].…”

Section: A Convolutional Neural Networkmentioning

confidence: 91%

Feature Extraction Using Convolutional Neural Networks for Anomaly Detection

Monteiro¹,

Filho²

2020

Anais Do 14. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

Anomaly detection is an import field of study, which has many applications, e.g., fraud and disease detection. It consists of identifying non-conforming patterns regarding an expected behavior. Despite the improvements provided by deep learning techniques in several areas, their use for anomaly detection is not widespread. The main reason is the difficulty to learn discriminative models when all the information available regards one class, or the classes are highly unbalanced. We propose a new deep learning-based solution for the anomaly detection problem. It consists of a hybrid system, composed of a feature extractor and a one-class classifier. The feature extractor is a convolutional neural network, trained as a regressor to learn a predefined distribution. The classifier is the one-class support vector machine, which performs the anomaly detection by using the outputs provided by the feature extractor. We used a gearbox failure diagnosis data set to assess the performance of our proposal. We also compared our anomaly detection system with other deep learning-based techniques commonly found in the literature. Our proposal presented an average accuracy close to 0.95, outperforming techniques based on the reconstruction error and hybrid models.

show abstract

Section: A Convolutional Neural Networkmentioning

confidence: 91%

Feature Extraction Using Convolutional Neural Networks for Anomaly Detection

Monteiro¹,

Filho²

2020

Anais Do 14. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

show abstract

“…To measure the performance of predicted results using the Computer Vision System Toolbox ™ and in the training process, using an NVIDIA ™ GPU supports CUDA with computational capabilities reaching computing 3.0 or more. Networks are trained using the train-FasterRCNNObjectDetector toolbox [17].…”

Section: Abbas Et Al Conducted Research Focusing On Faster R-cnnmentioning

confidence: 99%

Performance of Faster R-CNN to Detect Plastic Waste

2020

IJATCSE

View full text Add to dashboard Cite

Waste production in Indonesia reaches more than 65 million tons per year, which is a problem that has not been appropriately resolved. The government and organization must raise awareness of waste because improper waste management can cause pollution. The organization can manage waste by recycling to solve this problem. However, these efforts have encountered obstacles because public awareness of sorting waste is still deficient. Therefore, we need a sorting system for organic and inorganic waste. Reducing waste problems can be started by separating plastic waste from organic waste. This study aims to detect plastic waste and other separate plastic waste from organic waste. This plastic waste detection system will extract digital image features to detect plastic waste using the deep learning method. Deep learning is used because it is proven to have good performance. Faster Regional Convolutional Neural Network (Faster R-CNN) is a deep learning technique recently developed to recognize and classify computer vision. Faster R-CNN is an algorithm that utilizes the Convolutional Neural Network (CNN) in the object detection process. This study will detect and localize plastic waste in the image using the Faster R-CNN algorithm by utilizing the TensorFlow object detection framework. The system implements four network architecture models, namely Inception Resnet V2, Inception V2, Resnet 101, and Resnet 50. Based on the experiments that have been conducted, Faster R-CNN can provide good performance by obtaining an F1 Score of 93% on the Inception Resnet V2.

show abstract

“…They perform object recognition and classification tasks [16] well. Object detection [17], diseases detection [18], and fault diagnosis [6, 10] are three examples of applications that use CNNs. Their basic structure consists of an input layer, alternating blocks of convolutional and pooling layers, which are followed by fully connected layers, and an output layer [16].…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Using a Support Vector Machine Based Decision Stage to Improve the Fault Diagnosis on Gearboxes

Monteiro

Cerrada

Cabrera

et al. 2019

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Gearboxes are mechanical devices that play an essential role in several applications, e.g., the transmission of automotive vehicles. Their malfunctioning may result in economic losses and accidents, among others. The rise of powerful graphical processing units spreads the use of deep learning-based solutions to many problems, which includes the fault diagnosis on gearboxes. Those solutions usually require a significant amount of data, high computational power, and a long training process. The training of deep learning-based systems may not be feasible when GPUs are not available. This paper proposes a solution to reduce the training time of deep learning-based fault diagnosis systems without compromising their accuracy. The solution is based on the use of a decision stage to interpret all the probability outputs of a classifier whose output layer has the softmax activation function. Two classification algorithms were applied to perform the decision. We have reduced the training time by almost 80% without compromising the average accuracy of the fault diagnosis system.

show abstract

Region-based Object Detection and Classification using Faster R-CNN

Cited by 48 publications

References 5 publications

Feature Extraction Using Convolutional Neural Networks for Anomaly Detection

Feature Extraction Using Convolutional Neural Networks for Anomaly Detection

Performance of Faster R-CNN to Detect Plastic Waste

Using a Support Vector Machine Based Decision Stage to Improve the Fault Diagnosis on Gearboxes

Contact Info

Product

Resources

About