scholarly journals Research and Performance of Recognition System of the Human Activity with a Filter Bank of Gabor by Hidden Markov Model

recognition of human movement is one of the huge growing generation. It has a massive feature for example supervision (movements evaluation), safety (walker detection), manage (character-computer interfaces); content material- based video retrieval, and plenty of others. Human interest reputation device of is a device of identifying a selection of Human sports activities beside a few saved sample Human interest. In this paper Human activity reputation machine for popularity of man or woman is provided. It gets facts of individual photo and look for comparable interior the store pics. Human interest can be visible as fit or now not fit if there can be in shape or not matched in stop result. consumer cannot create a few form of regulate inside the stored photo documents, i.e. a purchaser isn't always accredited to insert or dispose of photographs from the garage records. The manager of the scheme has verification to make changes in the storage facts. The supervisor of the scheme has verification to make adjustments inside the storage statistics. Biometrics device of automatic Human hobby recognition system acting recognition is supplied. Extraction of capabilities is finished through the usage of the use of Gabor filter out to this tool. function extraction of the picture is convolving with Gabor clear out and extra person pattern era set of guidelines is used to determine a hard and rapid of realistic and non redundant functions of Gabor. Hidden Markov models for matching the input Human interest photograph to the stored pics is used.

2016 ◽  
Vol 19 (6) ◽  
pp. 27-31 ◽  
Author(s):  
Ruben San-Segundo ◽  
Julian Echeverry-Correa ◽  
Christian Salamea ◽  
Jose Manuel Pardo

Author(s):  
Yosra Abdulaziz Mohammed

Cries of infants can be seen as an indicator of pain. It has been proven that crying caused by pain, hunger, fear, stress, etc., show different cry patterns. The work presented here introduces a comparative study between the performance of two different classification techniques implemented in an automatic classification system for identifying two types of infants' cries, pain, and non-pain. The techniques are namely, Continuous Hidden Markov Models (CHMM) and Artificial Neural Networks (ANN). Two different sets of acoustic features were extracted from the cry samples, those are MFCC and LPCC, the feature vectors generated by each were eventually fed into the classification module for the purpose of training and testing. The results of this work showed that the system based on CDHMM have better performance than that based on ANN. CDHMM gives the best identification rate at 96.1%, which is much higher than 79% of ANN whereby in general the system based on MFCC features performed better than the one that utilizes LPCC features.


Sign in / Sign up

Export Citation Format

Share Document