Compression of color skin tumor images with vector quantization.
Compression of color skin tumor images with vector quantization.
复制标题
使用矢量量化压缩彩色皮肤肿瘤图像。
DOI：
10.1109/51.982287
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
Cheng,Y
中科院分区：
文献类型：
--
作者：
Guo,L;Umbaugh,S;Cheng,Y
医学中使用的许多不同的成像模式，与广泛可用的数字成像计算机系统相结合，以及远程医疗的出现，都需要新的图像压缩方法。即使是X射线和超声波等成熟的成像方式也越来越多地以数字格式进行处理和存储。如果我们需要在不同的站点保存多个副本，或者需要通过互联网或某些物理渠道将这些图像从一个站点传输到另一个站点，那么对高性能压缩算法的需求以降低存储和传输成本是显而易见的[1]。本文中讨论的这项研究是在以前的工作[1-5]的基础上实现的，用于压缩一组皮肤肿瘤图像。这项工作的一个目标是开发一种工具，这将是有用的，作为一个医生的援助，并在大规模筛选的设置，如购物中心或疗养院。因此，已经建立了一个由1000多个数字皮肤肿瘤图像组成的相对较大的数据库，用于开发和测试分析工具。每幅原始图像的空间分辨率为512× 512像素，大小为24位（每个波段8位），占用786 kB的存储空间。
The many different imaging modalities used in medicine, combined with digital imaging computer systems being widely available, and the advent of telemedicine have created the need for new image compression methods. Even well-established imaging modalities such as X-rays and ultrasound are increasingly being processed and stored in a digital format. If we need to keep multiple copies in different sites, or need to transfer these images from site to site through the Internet or certain physical channels, the need for high-performance compression algorithms to reduce storage and transmission costs is evident [1]. This research discussed in this article was implemented for compression of a set of skin tumor images, building on previous work [1-5]. One goal of this work is to develop a tool that will be useful as a physician’s aid and in mass screening in settings such as shopping malls or nursing homes. As a result, a relatively large database consisting of more than 1000 digital skin tumor images has been established for the purpose of developing and testing the analysis tool. Each original image has a spatial resolution of 512× 512 pixels, 24-bit magnitude (8 bits for each band), and occupies 786 kB of storage space.