1. Introduction This work is based on the belief that a computational theory of perception must encompass dual theories of representation and recognition. We propose a procedural model of recognition which 1) provides a mechanism for flexibly integrating top-down and bottom-up control structures, 2) supports the use of a hierarchy of model driven methods, and 3) defines a deductive process scheduling mechanism. 2. The Chicken and Egg Problem The top-down recognition model proposed by Minsky(1974), championed by Kuipers(1975), and used by many others exhibits a number of shortcomings: 1. A frame must explicitly be made the current hypothesis before its expertise is available to the recognition process. 2. An ordering must be placed on alternative subgoals. The top-down paradigm forces the choice of a single, hypothesis at a time. The mechanism for choosing a next hypothesis is completely failure driven. 3. Identical subgoals must be carried out independently. The same subgoal may be attempted and achieved numerous times by the system. To avoid this thrashing behaviour, Kuipers(1975) has advocated the use of a similarity network to recommend a replacement candidate frame on failure. This scheme assumes first that a mapping exists between the failing frame and each next candidate frame and secondly that the network is in some sense "complete". Any "surprises" cause the system to revert to blind automatic backtracking. These difficulties are three manifestations of what Mackworth(1975) has called "the chicken and egg problem". It seems clear that to avoid these problems, an integration of both top-down and bottom-up techniques are needed. Kaplan(1973) and more recently Bobrow & Winograd(1977) have advocated the use of multiprocessing with priority queue scheduling. We argue that in order to effectively integrate top-down and bottom-up recognition methods more sophisticated mechanisms than priority queues are needed. 3. Implementation We define a procedural recognition model which utilizes multiprocessing and a deductive scheduling mechansim to realize an integration of top-down and bottom-up search. The model operates in two mutually recursive modes. The first mode is called matching and incorporates essentially the top-down recognition paradigm. The expectations of a frame are matched by direct observation by recursive use of matching I.e. subgoaling, and by recursive calls to the second mode described below. The second mode implements bottom-up search and consists of two cyclical phases called expectation and completion. Each frame may have associated with a number of processes called supergoals. Instead of relying entirely on matching to …
[1]
Benjamin Kuipers,et al.
A FRAME FOR FRAMES: Representing Knowledge for Recognition
,
1975
.
[2]
Alan K. Mackworth.
How To See A Simple World
,
1975
.
[3]
Ronald M. Kaplan.
A multi-processing approach to natural language
,
1973,
AFIPS National Computer Conference.
[4]
Daniel G. Bobrow,et al.
On Overview of KRL, a Knowledge Representation Language
,
1976,
Cogn. Sci..
[5]
Richard Fikes,et al.
STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving
,
1971,
IJCAI.
[6]
Marvin Minsky,et al.
A framework for representing knowledge
,
1974
.
[7]
Chitoor V. Srinivasan,et al.
The Architecture of Coherent Information System: A General Problem Solving System
,
1973,
IEEE Transactions on Computers.