[模式识别(视觉/语音等)] chatbot_simbert
该项目设计的检索类型的微信聊天机器人 问答系统,通过API异步通信,可以查询天气、重复问句识别等情况;本项目包括模型和工程化部署一体化。用到SimBert等模型。它的特点是模仿人的语言习惯,几乎都是通过检索匹配的方式来寻找问题最合适的答案。聊天机器人对于知道答案的问题,往往回答的比较准确,而对于不知道的问题,则通过猜测,转移话题,或回答不知道的方式给出答案。
The retrieval type of WeChat chat robot question and answer system designed in this project can query weather, repeated question recognition and other conditions through API asynchronous communication; This project includes integration of model and engineering deployment. SimBert and other models are used. It is characterized by imitating people s language habits, and almost all of them search for the most appropriate answers to questions through retrieval and matching. The chat robot often answers the questions that know the answers accurately, while for the questions that do not know, it gives the answers by guessing, changing the topic, or answering the questions that do not know. (2024-03-08, Python, 0KB, 下载0次)
[模式识别(视觉/语音等)] MATLAB_COLOR
这是一个关于颜色搭配的web项目,旨在帮助用户了解和学习如何合理地搭配颜色以创造出具有吸引力和视觉效果的网页设计。该项目采用了前端开发技术,使用户可以通过浏览器轻松地浏览和测试不同的颜色搭配方案。 在颜色搭配web项目中,用户可以自由地选择不同的颜色组合,并查看这些颜色在网...
This is a web project about color matching, which aims to help users understand and learn how to reasonably match colors to create attractive and visual web designs. The project adopts front-end development technology, so that users can easily browse and test different color matching schemes through a browser. In the color matching web project, users can freely choose different color combinations, and view these colors on the web (2023-10-29, HTML, 0KB, 下载0次)
[模式识别(视觉/语音等)] WXPayOneCard
微信企业号一卡通充值系统,员工关注了企业号后,可以按照企业号的菜单授权登录进入首页后,自动识别你是否绑卡了,如果未绑卡则会弹出模态框要求绑卡,进入首页后,员工可以查看自己的基本信息,也可以去充值,点击充值时,弹出充值框,输入金额点击支...
The WeChat Enterprise One Card Recharge System allows employees to follow the enterprise account and log in according to the authorization menu on the enterprise account. After entering the homepage, they can automatically identify whether you have tied the card. If you have not tied the card, a modal box will pop up requesting the card to be tied. After entering the homepage, employees can view their basic information or go to recharge. When clicking on the recharge button, a recharge box will pop up, where they can enter the amount and click to disburse (2017-11-08, JavaScript, 6160KB, 下载0次)
[模式识别(视觉/语音等)] zhiwen
这个程序就是从联合开发网下载的，但是有一个错误导致识别率不足60%。
原始版本在图像旋转后提取的指纹中心点算法有误，每次提取的中心点都在图像边缘，造成后面提取的FingerCode也会出错。
这个修改使旋转前的中心点与旋转后的中心点保持一致，同时减少了运算复杂度
This program is downloaded from www.pudn.com, but one error led to recognition rate of less than 60%.
The original version of the extracted fingerprint center point after the image rotation is incorrect, and each extracted center point is at the edge of the image, resulting in the wrong FingerCode extracted later.
This modification keeps the center point before rotation consistent with the center point after rotation while reducing the computational complexity. (2018-02-03, matlab, 242KB, 下载15次)
[模式识别(视觉/语音等)] pdfcopier
这是我编写的一个适用于医学写作者的中文pdf扫描识别的文档字符格式化工具，针对万网、CNKI的文献常见的编码问题如标点格式、中英文全半角、多余的换行符等自动转换。基本上复制文档内容时候，开着这个软件就可以自动对剪切板的数据转换，直接复制到word写作即可。
This is for medical writers I write a PDF scanned documents in Chinese character formatting tools, networks, CNKI literature common coding issues such as punctuation formats and English half-width, extra line breaks automatically converted. Essentially duplicate the document content, this software can automatically open the Clipboard data, can be directly copied to the word write. (2016-03-12, Visual Basic, 7KB, 下载2次)
[模式识别(视觉/语音等)] uart_latest.tar
串行UART开源的核心。该设计是专为使用作为一个独立的芯片或用于与其他我们芯的使用。其原因显影串行UART核的事实，即异步串行通信是很常见的，几乎每一个机器理解it.Also，为OCRP-1，我们需要的通信的方式与主计算机，以使它可通过网。
serial UART open source core. The design is engineered for use as a stand alone chip or for use with other of our cores. The reason for developing the Serial UART core is the fact, that asynchronous serial communication is very common that almost every machine understands it.Also, for OCRP-1, we needed a way of communication with a host computer, to make it available over the net. (2015-09-13, VHDL, 9KB, 下载4次)
[模式识别(视觉/语音等)] PY
python版本网络抢票软件源码，一、运行环境： 基于python2.7 二、原理: 图像识别基于tesseract 数据抓包使用httpwatch, IE，识别出所有的POST请求，获取各步骤中数据，分析页面里token等 三、用法: 修改conf_example.py里的买票信息, 然后运行
python version of the network software source code to grab votes, a run environment: Based on python2.7 Second, the principle: tesseract-based image recognition data capture using httpwatch, IE, identify all POST requests, the steps to get the data, analysis page in token etc. Third, usage: Modify conf_example.py in the ticket information, and then run (2014-05-20, Python, 3761KB, 下载70次)
[模式识别(视觉/语音等)] hausdorff
摘 要： 提出了一种基于改进 Ha u s d o r f f距离的人脸相似度匹配的方法， 该方法首先将人脸划分为脸型、 双眼、 鼻、 嘴等几个特征点
集， 分别计算各部分的改进 Ha u s d o r f f 距离， 然后进行加权计算相似度。利用该方法， 在 A S M( 主动形状模型) 定位人脸的基础上进
行了人脸检索。 实验表明， 利用人脸相似度计算方法对人脸特征库进行搜索， 达到 了较好的效果。同时结合 A S M 自动人脸检测， 本
方法可以全自动完成人脸匹配， 应用于人脸识别及数字娱乐等领域。
Abstract: This paper presents a distance based on an improved Ha usdorff face similarity matching method, which will first face is divided into face, eyes, nose, mouth, and several other feature point sets, were calculated to improve the various parts of Ha usdorff distance, and then weighted similarity. Using this method, in the ASM (active shape model) positioned on the basis of human face human face retrieval. Experiments show that the use of face similarity calculation method for facial feature database to search, to achieve good results. ASM automatically combined with face detection, this method can be completed fully automatic human face matching, used in face recognition and digital entertainment and other fields. (2009-10-15, Visual C++, 198KB, 下载252次)
[模式识别(视觉/语音等)] lpcseg
用matlab做的车牌识别的完整源代码,包括车牌定位,二值化,滤波去噪,字符分割,识别,识别部分用的BP网
Matlab do with License Plate Recognition complete source code, including the license plate location, binarization, filtering noise, character segmentation, identification, identification of parts used in BP network (2009-01-10, matlab, 4KB, 下载306次)
[模式识别(视觉/语音等)] NoiseReduction_v1
本程式实做了Noise Reductin Algorithm
2005年一个韩国人在ieee发表的Paper
Block-based noise estimation using adaptive Gaussian filtering
此论文也收录在资料夹中，供使用者参考。
首先，click open file，
选择第一张原始图(未被杂讯污染)
接下来选择第二张图(有杂讯)
你可以直接点选Noise Reduction观看结果
也可以先调整旁边的threshold，观看不同threshold下去除杂讯的效果。
本程式利用统计理论，在去除杂讯的过程，成功保留了边缘特征，
使影像看起来较为立体、清晰。
This program is to do a Noise Reductin Algorithm2005 a Korean in the year ieee published PaperBlock-based noise estimation using adaptive Gaussian filtering of this thesis is also included in the folder for reference. First of all, click open file, select first the original plan (not noise pollution) Next select the second graph (with noise) you can watch the results of Click Noise Reduction can also adjust next threshold, watch different under the threshold to remove noise effects. This program using statistical theory, to remove noise in the process of successfully retained the edge features, to make images look more three-dimensional and clear. (2008-03-14, C++ Builder, 6314KB, 下载96次)
[模式识别(视觉/语音等)] Visual_C++_MATLAB
《Visual C++_MATLAB图像处理与识别实用案例精选》本书系统地介绍了图像处理与识别的基本原理、典型方法和实用技术。全书共分12章，第1章－第6章是图像处理与识别的基础内容，包括图像科学综述、MATLAB语言图像编程、图像增强、图像分割、图像特征提取和图像识别；第7章－第10章是图像处理与识别的工程实例，涵盖了医学图像处理、文字识别和自导引小车路径识别等应用实例，并结合理论算法，提供了大量MATLAB代码程序，以帮助读者掌握如何使用MATLAB语言快速进行算法的仿真、调试和估计等方法。第11章－第12章，是两个综合性较强的实例，分别足Visual C++实现的基于神经网络的文字识别系统和车牌定位系统。
本书附带的光盆给出了各个章节列举的实例的源代码，同时赠送了28个常用数字图像处理算法的Visual C++代码实现。光盘在下一次的上载中给出。
注 此为超星图书，请用超星阅读软件打开阅读。
"Visual C _MATLAB image processing and recognition of the practical case Showcase" the book systematically introduced the image processing and recognition of the basic tenets of the typical methods and practical skills. The book is divided into 12 chapters, Chapter 1-Chapter 6 of image processing and recognition of content, including images scientific overview MATLAB programming language images, image enhancement, image segmentation, image feature extraction and image recognition; Chapter 7-Chapter 10 of image processing and recognition of the engineering example, covering medical image processing, Character Recognition and self-guided trolley path recognition example, the combination of theory and algorithms, for a lot of MATLAB code procedures to help readers how to use MATLAB (2006-05-24, Visual C++, 8306KB, 下载3716次)