In this paper, a conditional model (CM) is used to incorporate different feature potentials including texture, texture environment and location features of objects for multi-class object recognition and segmentation in complex natural images. Besides, we model the relationship between different objects by the scene of images and propose a new scene-based conditional model called the sCM model. We investigate the performance of our model in the class-based pixel-wise segmentation of images on the Oliva & Torralba database and compare its result with other methods. The results show that our theme-based R-CRF model significantly improves the accuracy of objects in the whole database. More significantly, a large perceptual improvement is gained, I. E. The details of different objects are correctly labeled.%为了实现复杂自然场景中多类目标的识别与分割,本文利用条件概率模型(CM)对目标特征进行建模,融合了纹理特征、纹理环境特征和位置特征,并采用场景类别对各类目标间的相互约束关系进行建模,在此基础上研究基于场景类别的条件概率模型(sCM)在多类目标识别与分割中的应用.本文选用Oliva & Torralba数据库对模型进行实验并与国外其他方法进行了比较.实验结果表明,该算法在多类目标识别与分割中取得很好的结果,在提高总体识别率的同时提高了物体边缘部分识别与分割的正确率,更有效地提高了视觉效果.
展开▼