Image classification for content-based indexing
Image classification for content-based indexing
复制标题
DOI：
10.1109/83.892448
复制
发表时间：
2001-01-01
影响因子：
10.6
通讯作者：
Zhang, HJ
中科院分区：
文献类型：
--
作者：
Vailaya, A;Figueiredo, MAT;Zhang, HJ
在基于内容的图像检索中，利用图像的低层视觉特征将图像分类为语义上有意义的类别是一个具有挑战性的重要问题。使用二进制贝叶斯分类器，我们试图捕捉高层次的概念，从低层次的图像特征的约束下，测试图像不属于类之一。具体来说，我们考虑度假图像的分层分类;在最高级别，图像被分类为室内或室外;室外图像被进一步分类为城市或景观;最后，景观图像的子集被分类为日落，森林和山脉类。我们证明，一个小的矢量量化器（其最佳大小是使用修改后的MDL标准选择）可以用来模拟的类条件密度的功能，需要BG的贝叶斯方法。在6931张度假照片的数据库上进行了分类器的设计和评估，我们的系统对室内/室外，城市/景观，日落/森林和山脉，森林/山脉分类问题的分类准确率分别为90.5%，95.3%，96.6%和96%。我们进一步开发了一种学习方法，随着更多数据的可用，逐步训练分类器。我们还展示了使用聚类技术进行特征约简的初步结果。我们的目标是将多个两类分类器联合收割机组合成一个分层分类器。
Grouping images into (semantically) meaningful categories using low-level visual features is a challenging and important problem in content-based image retrieval. Using binary Bayesian classifiers, we attempt to capture high-level concepts from low-level image features under the constraint that the test image does belong to one of the classes. Specifically, we consider the hierarchical classification of vacation images; at the highest level, images are classified as indoor or outdoor; outdoor images are further classified as city or landscape; finally, a subset of landscape images is classified into sunset, forest, and mountain classes. We demonstrate that a small vector quantizer (whose optimal size is selected using a modified MDL criterion) can be used to model the class-conditional densities of the features, required bg the Bayesian methodology. The classifiers have been designed and evaluated on a database of 6931 vacation photographs, Our system achieved a classification accuracy of 90.5% for indoor/outdoor, 95.3% for city/landscape, 96.6% for sunset/forest & mountain, and 96% for forest/mountain classification problems. We further develop a learning method to incrementally train the classifiers as additional data become available. We also show preliminary results for feature reduction using clustering techniques. Our goal is to combine multiple two-class classifiers into a single hierarchical classifier.