This paper proposes an automated target recognition algorithm using Support Vector Machine (SVM) to extract landmark points for craniofacial features in cephalometry radiograph. The features are extracted by subjecting the radiograph to the Projected Principle Edge Distribution (PPED) algorithm. Edge flags are accumulated in every four columns and spatial distribution of edge flags are represented by a histogram. The resultants are the front end of support vector machine. Vectors, which possess land marks, are separated from all other vectors. The centroid points, automatically determined from PPED vectors, are the location of landmarks. The landmark points which are serving as a guide for construction and measurement of planes, are used to evaluate the dento-facial relationship, study of growth and development, and also for treatment planning.

No abstract

Object classification is a major application in video surveillance such as automatic vehicle detection and pedestrian detection, which is to monitor thousands of vehicles and people. In this study, an object classification algorithm is proposed to classify the objects into persons and vehicles despite the presence of shadow and partial occlusion in mid-field video using recurrent motion image (RMI) of skeleton features. In this framework, the background subtraction using a Gaussian mixture model is followed by Gabor filter based shadow removal in order to remove the shadow in the image. The star skeletonisation algorithm is performed on the segmented objects to obtain skeleton features. Then the RMI is computed and it is partitioned into two sections such as top and bottom. Based on the signatures derived from the bottom section of the partitioned RMI using skeleton features, the object is classified into people and vehicles.

No abstract

No abstract