搜索资源列表
TheResearchforRecognition
- 基于视频图像的运动车辆识别系统主要是由汽车牌照识别和汽车类型识 别两大核心技术构成,它在智能交通领域中有着广泛的应用,同时也是计算机 视觉、图像处理和模式识别等交叉学科研究的热门课题,因此对相关技术的研 究正受到普遍关注。本文正是在这一背景下,对运动车辆识别技术进行了系统 的研究。在车牌识别技术中,本文着重对车牌定位和车牌字符识别等关键技术 所涉及的难点进行了深入的研究。在车型识别技术中,与当前国内外学者侧重 于研究车辆外形、大小的识别不同,本文主要侧重对汽车标志的定位和
handwritten-character-recognition
- 基于深层网络学习的手写字符识别,识别率高-Handwritten character recognition based on deep network learning, the recognition rate
deep-learning-scene-recognition
- deep learning code it helpful the begainer in deep learning-deep learning code it helpful the begainer in deep learning
Deep Learn 深度学习
- 基于深度学习的论文资料和最新的源代码学习资料,非常值得学习。-face recognition
Deep-learning-and-new-progress-
- 深度学习是机器学习中的一个新的研究领域。通过深度学习的方法构建深度网络来抽取特征是目 前目标和行为识别中得到关注的研究方向。为引起更多计算机视觉领域研究者对深度学习进行探索和讨论,并推 动目标和行为识别的研究,对深度学习及其在目标和行为识别中的新进展给予概述。方法首先介绍深度学习领 域研究的基本状况、主要概念和原理 然后介绍近期利用深度学习在目标和行为识别应用中的一些新进展。结 果阐述了深度学习与神经网络之间的关系,深度学习的优缺点,以及目前深度学习理论需要解决的主要问题。
Deep-learning-for-recogniztion
- 基于深度学习的视频人脸识别方法,CAJ格式的,请下载CAJ阅览器-Depth study of face recognition method based on video
Dual Deep Network for Visual Tracking
- 转载:基于深度学习方法来实现行人再识别的程序段。(To achieve pedestrian re-recognition of the program)
voiceprint
- 声纹识别,或称为说话人识别,机遇i-vector方法和基于深度学习(speaker recognition by deep learning)
awesome-deep-vision-master
- file recognition, using by a++ to define a file
Deep Face Recognition
- This pdf is a paper talk about Face Recognition published in 2015
neural face recognition
- This pdf introduces a method of face recognition untitled Face Recognition with Very Deep Neural Networks
DeepLearning
- 包含神经网络、卷积神经网络、深度信念网络等深度学习程序,该程序可以用于语音识别、分类等处。(Deep learning programs including neural network, convolutional neural network and deep belief network can be used for speech recognition, classification and so on.)
gait-recognition-master
- I利用了深度学习,实现视频中的人的步态行为检测。(In this project you can find implementation of deep neural network for people identification from video by the characteristic of their gait. The processing is very robust against various covariate factors such as clothing, ca
NER-Deep-Learning-master
- 利用LSTM和条件随机场进行命名实体识别(Named entity recognition with LSTM and CRF)
deep-learning-opencv
- opencv3.3以上的版本调用caffe模型提前训练好的模型进行图片识别。(The above version of opencv3.3 calls the Caffe model in advance training model for image recognition.)
deep-learning-HAR-master
- 一份用tensorflow平台做的cnn分类时序信号,是分类UCI 项目中的人体活动识别(HAR)数据集。该数据集包含原始的时序数据和经预处理的数据(包含 561 个特征)(A CNN classification timing signal made by tensorflow platform is a human activity recognition (HAR) dataset in the classified UCI project. The dataset contains or
phonetic-recognition-master
- 基于paddlepaddle开发的语音识别框架(This is a ASR application based on paddlepaddle,the deep learning frame of Baidu.Using it,you can recognize the sound,and turn it to the text.)
stanford-deep-learning-matlab-code
- Stanford 大学的深度学习源代码,可用于模式识别和预测,比较稳定。(Stanford University's deep learning source code can be used for pattern recognition and prediction, and is relatively stable.)
Face Recognition. From Traditional to Deep Learning Methods
- 近几年,传统的人脸识别算法被深度卷积网络所代替。CNN的主要优势就是可以结合庞大的数据集提取出原先所提出不出来的优质feature,与此同时精度也提升了很多。同时CNN的出现也加速了计算机视觉的发展,例如object detection 、recognition、segmentation。
tensorflow-vgg16-train-and-test-master
- vgg深度学习,图像识别,用于图像的分类,在python上运行(vgg deep learning, image recognition, used for image classification, running on Python)