Abstract
With the ever-growing volume of image data, textual annotation of images for mining of query specific image has become impractical and inefficient. Thus, computer vision-based image retrieval has received considerable interest in recent years. One of the fundamental characteristics of an image-object is its shape which plays a vital role to recognize the object at a primitive level.
Keeping this view as the central focus, we study the scope of a shape descriptive framework based on a multi-level polygonal approximation for generating shape defining features. Such a framework explores different degrees of convexity of an object’s contour-segments and captures shape features at different approximation stages as the proposed algorithm determines polygonal approximations starting from coarse-level to more refined representation of a closed contour by varying number of polygon-sides. We have presented a shape-encoding scheme based on multi-level polygonal approximation which allows us to use the popular distance metrics to compute shape similarity score between two objects. The proposed framework, when deployed for similar shape retrieval task demonstrates fairly good performance in comparison with other popular shape-retrieval algorithms.