In order to realize a robust computer vision system which can cope with a variety of scenes, we propose a new scheme to integrate multiple vision algorithms in a cooperative framework. The key concepts of the scheme can be summarized as follows: (1) A vision algorithm is implemented as an independent specialist. (2) There are multiple specialists in the system. (3) All specialists work in parallel. (4) Each specialist tries to solve the vision problem in its own way. (5) A specialist may communicate with another specialist when it needs a help. The scheme clearly has a nature of task parallelism and is suitable to be built on a parallel computer. In order to demonstrate the feasibility of the proposed scheme, we are developing two computer vision systems in two different approaches which are both based on the same concept. They are called a cooperative approach and a concurrent top-down approach. Roughly speaking, the former is an integration of multiple algorithms in a bottom-up framework while the latter is in a top-down framework. Preliminary results obtained by the systems are also presented.