Shape matching and recognition is a fundamental aspect of many problems in computer vision, including object or scene recognition, moving tracking and object detection, etc. While rigid shape matching is relatively well understood, matching shapes undergoing non-rigid deformations remains challenging. Moreover, shape generation is also a challenging task since nearly all approaches face the same difficulty: background clutter. The aim of this book is to propose novel approaches to generate, represent and match object shapes. To achieve this, the following three aspects are particularly explored: Shape generation, shape representation and shape matching. Shape generation is applied based on shape contour detection which is able to locate an object, identify its contour parts, and segment out its contour. Shape representation looks for effective and perceptually important shape features based on either shape boundary or region information. Shape matching aims to calculate the overall similarity (or dissimilarity) between two object shapes. Based on the proposed approaches, two shape-based applications are introduced and assessed.