首页> 外文会议>International Joint Conference on Neural Networks >Use of true-complement optical images for efficient associative memory implementation
【24h】

Use of true-complement optical images for efficient associative memory implementation

机译:使用真正的互补光学图像以实现高效关联内存实现

获取原文

摘要

While true and complement images have the same information content, it is advantageous to retain both kinds of images for associative memory. This allows the implementation of a very simple optical computer which can perform real-time image matching. If a test image and a complementary stored image is compared optically with a complementary test image and a stored image, the emerging light intensity is proportional to the Hamming distance between the images. The suggested architecture then carries out efficient parallel comparison and points out the best matched test image using a TV screen and transparencies. A time-varying light-intensity (or a time-varying thresholding voltage) source and a thresholding device are used to select the best match in parallel. The architecture is also ideally suited to finding the closeness of match of two images for quality control-type operations. It can also be used for providing a feedback to search for the best match.
机译:虽然真实和补充图像具有相同的信息内容,但是将两种图像保留用于关联存储器是有利的。这允许实现可以执行实时图像匹配的非常简单的光学计算机。如果用互补测试图像和存储的图像光学地比较测试图像和互补存储的图像,则出现的光强度与图像之间的汉明距离成比例。然后,建议的架构进行了高效的并行比较,并使用电视屏幕和透明胶片指出最佳匹配的测试图像。时变光强度(或时变阈值电压)源和阈值控制设备用于并行选择最佳匹配。该架构也非常适合找到用于质量控制型操作的两个图像的匹配的亲密性。它还可以用于提供对搜索最佳匹配的反馈。

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