Detection and Classification of Different Weapon Types Using Deep Learning

Abstract

Today, with the increasing number of criminal activities, automatic control systems are becoming the primary need for security forces. In this study, a new model is proposed to detect seven different weapon types using the deep learning method. This model offers a new approach to weapon classification based on the VGGNet architecture. The model is taught how to recognize assault rifles, bazookas, grenades, hunting rifles, knives, pistols, and revolvers. The proposed model is developed using the Keras library on the TensorFlow base. A new model is used to determine the method required to train, create layers, implement the training process, save training in the computer environment, determine the success rate of the training, and test the trained model. In order to train the model network proposed in this study, a new dataset consisting of seven different weapon types is constructed. Using this dataset, the proposed model is compared with the VGG-16, ResNet-50, and ResNet-101 models to determine which provides the best classification results. As a result of the comparison, the proposed model’s success accuracy of 98.40% is shown to be higher than the VGG-16 model with 89.75% success accuracy, the ResNet-50 model with 93.70% success accuracy, and the ResNet-101 model with 83.33% success accuracy.

Human Violence Detection Using Deep Learning Techniques

“…With help of the VGG net and ResNet-50, the weapons like hunting refile, knives, pistols and revolvers can be detected. Images from of these weapons are collected from sources, trained and tested which results as a better detection model [1].…”

“…For that we can use a confusion matrix to get the accuracy and the confusion matrix shows the results rate of the models trained [10].  False Positive: The actual data is negative but predicted as positive  False Negative: The actual data is positive but predicted as negative Using the obtained value, the accuracy of the modelling can be found using Equation (1). Recall tells the number of positive predictions that were made out of all positive predictions (Equation ( 2)).…”

“…The technological improvement in video and image processing has been exceptional due to the importance of finding the contents for various applications which includes recognizing actions and objects they use like knives or guns [1]. The recognition of finding the actions from video streams has been improving in recent years only because of the rise of human violence happening in our daily life.…”

Spectrum Sensing Algorithm Based on Shapiro Wilk Test

“…It can be said that NP and GLRD are better than other tests in terms of performance and reliability. It has been used for spectrum detection in some methods based on deep learning [13].…”

Realization of a Yolo-V3-Based Application for the Detection of Tick-Borne Cases

“…Rapid developments in computer vision have allowed the training of new image recognition models [2]. The place of deep learning in the training of image recognition models is indisputably recognized [3]. However, the evaluations on which model will be more effective in tick detection or which should be together have not yet provided the desired level of enlightenment.…”