首页>
外国专利>
Method for Implementing a High-Level Image Representation for Image Analysis
Method for Implementing a High-Level Image Representation for Image Analysis
展开▼
机译:用于图像分析的高级图像表示方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
Robust low-level image features have been proven to be effective representations for a variety of visual recognition tasks such as object recognition and scene classification; but pixels, or even local image patches, carry little semantic meanings. For high-level visual tasks, such low-level image representations are potentially not enough. The present invention provides a high-level image representation where an image is represented as a scale-invariant response map of a large number of pre-trained generic object detectors, blind to the testing dataset or visual task. Leveraging on this representation, superior performances on high-level visual recognition tasks are achieved with relatively classifiers such as logistic regression and linear SVM classifiers.
展开▼