搜索资源列表
paper2
- 语音识别技术主要包括特征提取技术、模式匹配准则及模型训练技术三个方面。此外,还涉及到语音识别单元的选取。选择识别单元是语音识别研究的第一步。语音识别单元有单词(句)、音节和音素三种,具体选择哪一种,由具体的研究任务决定。-Speech recognition technology, including feature extraction techniques, pattern-matching criteria and the three aspects of model training t
Learning-depth-information
- 本文提出一种基于高斯- 马尔科夫 随机场模型,首先通过图像采集及激光测距系统,采集大量图像及其相匹配的深度信息图,在 人类视觉系统基础上,提取图像特征,通过训练完善模型,并应用于新采集图像上-This paper presents a Gauss- Markov random field model, first by image acquisition and laser ranging system, collecting a large number of images to ma
model-CANDIDE
- 在模型与人脸初步匹配后, 对模型局部进行网格优化,提高了模型的表征力同时并不影响匹配速度 -In the initial model and face after the match, the model for local mesh optimization to improve the characterization of the model at the same time does not affect the matching speed force