A Stochastic Grammar for Natural Shapes
This work addresses object detection in computer vision by bridging model-based recognition and grouping, potentially improving efficiency, but it appears incremental as it builds on existing approaches without claiming major breakthroughs.
The paper tackles the problem of object detection by proposing a generic model for natural shapes, arguing that model-based recognition and grouping processes can use similar computational mechanisms, and demonstrates that model-based techniques can implement a mid-level vision grouping process.
We consider object detection using a generic model for natural shapes. A common approach for object recognition involves matching object models directly to images. Another approach involves building intermediate representations via a generic grouping processes. We argue that these two processes (model-based recognition and grouping) may use similar computational mechanisms. By defining a generic model for shapes we can use model-based techniques to implement a mid-level vision grouping process.