We give an overview of the shape based techniques used in object matching, object identification and object classification tasks. We distinguish between the area based methods, which use all the shape points, and boundary based methods, which use boundary information only. We also discuss a recent `multi-component shape' approach. This approach considers a group of objects as a single but compound object. The idea is already shown to be very efficient in a wide spectrum of applications. Illustrative examples are provided, including those related to personal signature identification and outliers detections, which have, pretty much, obvious and straightforward applications in security and crime prevention related tasks.