Detection and Recognition of Abnormal Behaviour Patterns in Surveillance Videos using SVM Classifier

2019 ◽  
Author(s):  
Manjula S ◽  
Lakshmi K
2011 ◽  
Vol 225-226 ◽  
pp. 437-441
Author(s):  
Jing Zhang ◽  
You Li

Nowadays, face detection and recognition have gained importance in security and information access. In this paper, an efficient method of face detection based on skin color segmentation and Support Vector Machine(SVM) is proposed. Firstly, segmenting image using color model to filter candidate faces roughly; And then Eye-analogue segments at a given scale are discovered by finding regions which are darker than their neighborhoods to filter candidate faces farther; at the end, SVM classifier is used to detect face feature in the test image, SVM has great performance in classification task. Our tests in this paper are based on MIT face database. The experimental results demonstrate that the proposed method is encouraging with a successful detection rate.


2021 ◽  
Author(s):  
Konstantinos Gkountakos ◽  
Despoina Touska ◽  
Konstantinos Ioannidis ◽  
Theodora Tsikrika ◽  
Stefanos Vrochidis ◽  
...  

In recent years, traffic accidents have become the major cause to injuries, deaths and property damages. One of the main reasons to such accidents is due to high speed of vehicles. In order to maintain proper speed limit and thus provide significant contribution to improve safety, we propose Speed Limit sign detection and recognition method which is one of the features of Advanced Driver Assistance System (ADAS). In this paper we propose two approaches, i.e., histogram oriented gradient feature with SVM classifier namely HOG-SVM and CNN based approach. In these approaches we first pre-process the image using red color enhancement method and then we detect the Region of Interest using Maximally Stable Extremal Regions (MSER). Later, we classify the image by using different classifiers. In the HOG-SVM method, we are using HOG for feature extraction and Support Vector Machine (SVM) classifier for classification. In the CNN approach, we are using Convolutional Neural Networks (CNN) both for feature extraction and classification. Performance analysis of SVM classifier and CNN classifier are first evaluated on simple German Traffic Sign Recognition Benchmark (GTSRB) dataset using 5 fold classification, we got accuracy 100% for SVM classifier and 98.5% for CNN classifier. Also Further evaluated on German Traffic Sign Detection and Recognition Benchmark datasets and the experimental results show detection accuracy upto 93.6% for SVM classifier and 85.8% for CNN classifier


2018 ◽  
Vol 2018 ◽  
pp. 1-7
Author(s):  
Yong Ruan ◽  
Yueliang Qian ◽  
Xiangdong Wang

Automatic audio announcement systems are widely used in public places such as transportation vehicles and facilities, hospitals, and banks. However, these systems cannot be used by people with hearing impairment. That brings great inconvenience to their lives. In this paper, an approach of audio announcement detection and recognition for the hearing-impaired people based on the smart phone is proposed and a mobile phone application (app) is developed, taking the bank as a major applying scenario. Using the app, the users can sign up alerts for their numbers and then the system begins to detect audio announcements using the microphone on the smart phone. For each audio announcement detected, the speech within it is recognized and the text is displayed on the screen of the phone. When the number the user input is announced, alert will be given by vibration. For audio announcement detection, a method based on audio segment classification and postprocessing is proposed, which uses a SVM classifier trained on audio announcements and environment noise collected in banks. For announcement speech recognition, an ASR engine is developed using a GMM-HMM-based acoustic model and a finite state transducer (FST) based grammar. The acoustic model is trained on audio announcement speech collected in banks, and the grammar is human-defined according to the patterns used by the automatic audio announcement systems. Experimental results show that character error rates (CERs) around 5% can be achieved for the announcement speech, which shows feasibility of the proposed method and system.


Sign in / Sign up

Export Citation Format

Share Document