ABSTRACT
Doing image processing and especially blob analysis it is often required to check some objects' shape and depending on it perform further processing of a particular object or not. For example, some applications may require finding only circles from all the detected objects, or quadrilaterals, rectangles, etc. Human vision seems to make use of many sources of information to detect and recognize an object in a scene. At the lowest level of object recognition, researchers agree that edge and region information are utilized to extract a “perceptual unit” in the scene. Some of the possible invariant features are recognized and additional signal properties (texture or appearance) are sent to help in making the decision as to whether a point belongs to an object or not. In many cases, boundary shape information, such as the rectangular shapes of vehicles in aerial imagery, seems to play a crucial role. Local features such as the eyes in a human face are sometimes useful. These features provide strong clues for recognition, and often they are invariant to many scene variables. The study of shapes is a recurring theme in computer vision. For example, shape is one of the main sources of information that can be used for object recognition. In medical image analysis, geometrical models of anatomical structures play an important role in automatic tissue segmentation. The shape of an organ can also be used to diagnose diseases. In a completely different setting, shape plays an important role in the perception of optical illusions (we tend to see particular shapes) and this can be used to explain how our visual system interprets the ambiguous and incomplete information available in an image. Characterizing the shape of a specific rigid object is not a particularly hard problem, although using the shape information to solve perceptual tasks is not easy.
PROJECT OUTPUT
PROJECT VIDEO
.png)
.png)
