Automatic recognition of an object involves several stages such as lwo level processing, moel formation, features extraction and finally model matching. Several algorithms and procedures are now avvailable for each one of the above stages and these tend to be highly complex as well as context dependent, because o f which a suitable choice for a given application is rather difficult for a non-expert in this discipline. This paper reports a semantically integrated system developed for recommending the appropriate algorithms for various stages in object recognition. The system is functionally divided into four different modules: Low Level Vision Expert (LLVE), Model Selection Expert (MSE), Geometrical Reasoning Expert (GRE), and Question and Answer Modue (QAM). The reported work here gives the details of Low Level Vision Expert module based on semantic integration of image processing procedures paradigm. Given an image, the system suggests a suitable image processing procedure, allows the suggested procedure to be evaluated on the image and suggests alternate choice in case of unsatisfied results.
|Number of pages||10|
|Publication status||Published - 30 Jun 1995|
|Event||8th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, IEA/AIE 1995 - Melbourne, Australia|
Duration: 5 Jun 1995 → 9 Jun 1995
|Conference||8th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, IEA/AIE 1995|
|Period||5/06/95 → 9/06/95|