Abnormal gait detection using hexagonal method on model based Front view model

الملخص EN

Gait abnormality recognition would be very useful in medical monitoring and surveillance system.

In this research, analysis of front view human gait silhouette had been done to investigate the possibility of the method in recognizing abnormality on proposed model-based approach.

The model based which utilised hexagonal theorem as feature extraction method is used to produce the vertical angles of both hip and knee for 70 image sequences as feature vectors for both legs for one complete cycle sequences.

Consequently, a total of 280 features generated based on four parameters from the lower limb of human body for gait abnormality purpose.

Further, the gait features extracted from different gait pattern namely as normal, drunken, dragging and tiptoed is classified as normal or abnormal using ANN and KNN.

Improvement findings of classification result for before and after normalisation confirmed that the proposed method suited to be utilized as gait abnormality recognition based on human gait patter