Application of an incremental SVM algorithm for on-line human recognition from video surveillance using texture and color features

Abstract

The goal of the paper is to present a new on-line human recognition system, which is able to classify persons with adaptive abilities using an incremental classifier. The proposed incremental SVM is fast, as its training periodrely on only few images and it uses the mathematical properties of SVM to update only the needed parts. In our system, first of all, feature extraction and selection are implemented, based on color and texture features (appearance of the person). Then the incremental SVM classifier has been introduced to recognize a person from a set of 20 persons in CASIA Gait Database. The proposed incremental classifier is updated step by step when a new frame including a person is presented. With this technique, we achieved a correct classification rate of 98.46%, knowing only 5% of the dataset at the beginning of the experiment. A comparison with a non-incremental technique reaches recognition rate of 99% on the same database. Extended analyses have been carried out and showed that the proposed method can be adapted to on-line setting.

Recognition of Image in Different Cameras using an Improved Algorithm in Viola-Jones

“…Convolutional Neural Network (dCNN) [19], Hidden Markov (HMM) [20], [21], [22] and Support Vector Machines (SVM) [23], as the authors argue, are algorithms models used to classify images, the analyze data, with computational methods for the patterns recognition.…”

“…The SVM model is used to perform recognition of people in a real application [23], and with the criteria of the authors of [8], the implementation of the Viola-Jones algorithm allowed us to obtain the capture of the image of a person. Which is represented with a frame, and that these pixels minimizing the amount and time of necessary calculations.…”

Adaptive SVM for Data Stream Classification

“…However, several applications require on-line classification. For example, detecting abnormal human actions from camera-based real-time scene monitoring (Lu, Boukharouba, Boonaert, Fleury, & Lecuche, 2014), and timely separation of legitimate emails from spam in an on-line spam email filtering (Vipin & Nizar, 2014).…”

Enhanced Denoising Algorithm for Improving Quality of Objects in Frames for Video Surveillance

“…This wide usage has directly motivated several researchers to design and develop sophisticated automated video surveillance systems that can mimic the activity of human brain in identifying events in moving objects [5]. However, due to the advanced technological breakthroughs in video capturing devices, increase in the number of cameras used, dynamic nature of the objects (human, vehicles, animals) in the video, has made this process a very challenging field of research.…”