The research of image semantics is a new field.
图像语义是研究图像模式识别与图像检索的一个新理论。
The experimental results showed that the two methods have better performance on image semantics extraction.
实验结果表明，这两种方法对图像有较好的语义提取效果。
In order to explain and calculate the image semantics, the feature vectors and the semantic partition are constructed in structure related.
从高级信息的角度来描述图像语义，建立图像语义的特征矢量空间和语义划分的结构关系，实现图像与语义值的结构表达。
In this paper, a novel system for content-based image retrieval is designed and created, which combines image semantics based on a multi-level model for image description.
该系统利用了一个多级图像描述模型将语义特征结合到图像检索技术中。
Binary custom properties support allows for the attaching of arbitrary binary values; for example, an audio recording or scanned image, to a human task on the fly, using key-value pair semantics.
二进制自定义属性支持允许使用键-值对语义，动态地向人工任务附加任意的二进制值，例如音频录音或扫描的图片。
The meaning of design semantics to creation and spreading of merchandise image was analyzed to achieve efficient communication between merchandise symbol and consumer.
旨在探析设计语义的使用对商品形象创建和传播的意义，如何实现商品符号与消费者之间的有效沟通。
In this image description model, image contents could be analyzed and represented through different levels and the transition from low-level features to high-level semantics is thus achieved.
该图像描述模型通过在不同层次上对图像内容进行分析和描述，实现了从低级特征到高级语义的过渡。
The thesis presents a semantic vector algorithm, builds up the network of image semantic keywords, and realizes the composite retrieval of the image low-level feature and semantics characteristics.
提出了一种语义向量算法，构建了图像语义关键词网络，实现了图像底层视觉特征和语义的复合索引。
This paper presents a new image retrieval method based on high-level semantics word and color name.
在基于内容的图像检索基础上，提出了基于高层语义词和颜色词检索。
The image contains abundant semantics, it is necessary to classify these images according to semantics which expressed.
图像中蕴涵着一定的语义，根据图像所表示的语义将其进行分类是非常必要的。
There are a small amount of pixel-based semantic image annotation systems which have no problem of adequate semantics learning but are time-consuming of the new image's semantic prediction.
也有少数系统是对像素点级别的特征进行语义学习和预测的，这样虽然可以确保特征的学习足够充分，但是语义的预测过程很耗时。
There are a small amount of pixel-based semantic image annotation systems which have no problem of adequate semantics learning but are time-consuming of the new image's semantic prediction.
也有少数系统是对像素点级别的特征进行语义学习和预测的，这样虽然可以确保特征的学习足够充分，但是语义的预测过程很耗时。
应用推荐