| Summary: | 碩士 === 朝陽科技大學 === 資訊管理系碩士班 === 96 === With the development of information technology, the cameras’ capabilities become more and more well. However, we find most of cameras are absence of circumstances perception. When taking a picture, if cameras can judge the corresponding scene immediately, it can choose the corresponding mode to capture the better photograph automatically. The scene images contain a lot of important low-level features and all of them have their representatives. Therefore, it is a difficult challenge to classify the scene images accurately. This thesis tries to use particle swarm optimization (PSO) algorithm, that has biological characteristic, and to find the semantics of images. We can get a scene transform matrix during the process. We hope the scene transform matrix can be used to classify scene images, which are close to human’s semantics, and then help the camera to set their photograph’s modes accurately.
|
|---|
