• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Proceedings of the 34th IASTED International Conference on Modelling, Identification and Control >OBJECT RECOGNITION IN CLUTTER COLOR IMAGES USING HIERARCHICAL TEMPORAL MEMORY COMBINED WITH SALIENT-REGION DETECTION
【24h】

OBJECT RECOGNITION IN CLUTTER COLOR IMAGES USING HIERARCHICAL TEMPORAL MEMORY COMBINED WITH SALIENT-REGION DETECTION

机译：分层时间记忆与显着区域检测相结合的杂波彩色图像对象识别

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The essential goal of this paper consists in extending the functionality of the bio-inspired intelligent HTM (Hierarchical Temporal Memory) network towards two capabilities: (ⅰ) object recognition in color images, and (ⅱ) classification of objects located in "clutter color images. The former extension is based on development of a novel scheme for application of three parallel HTM networks which separately process color, texture, and shape information in color images. For the latter HTM extension we proposed a novel system in which HTM is combined with a modified model of computational visual attention. We adopted the results of and, and added new elements for the calculation of image saliency maps. The proposed algorithm enables to locate individual objects in clutter images automatically. For computer experiments a special image database has been created to simulate ideal single object images and cluttered images with multiple objects. The recognition performance of the HTM alone and in combination with a salient-region detection method has been evaluated. The evaluation of the attention subsystem shows promising results in the sense that the system satisfactorily locates several objects in clutter color images with non-homogeneous background. Our pilot study confirmed that the proposed attention system can improve the HTM's capabilities for object classification in cluttered images. However, as expected, the system cannot match the HTM's recognition accuracy achieved on single object images.
机译：本文的基本目标在于将受生物启发的智能HTM（分层时间记忆）网络的功能扩展为两种功能：（ⅰ）彩色图像中的对象识别，以及（ⅱ）位于“凌乱的彩色图像中”的对象分类。前一种扩展是基于一种新颖的方案的开发，该方案适用于三个并行的HTM网络，它们分别处理彩色图像中的颜色，纹理和形状信息；对于后一种HTM扩展，我们提出了一种新颖的系统，其中HTM与改进的计算视觉注意力模型，我们采用和的结果，并添加了新元素来计算图像显着性图，该算法可以自动在杂波图像中定位单个对象，并为计算机实验创建了一个特殊的图像数据库来模拟理想的单个物体图像和具有多个物体的混乱图像。结合显着区域检测方法进行了评估。从系统令人满意地在背景不均匀的杂色彩色图像中定位多个对象的意义上来说，注意力子系统的评估显示出令人鼓舞的结果。我们的初步研究证实，所提出的注意力系统可以提高HTM对混乱图像中的对象进行分类的能力。但是，正如预期的那样，该系统无法匹配HTM在单个物体图像上实现的识别精度。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号