Computer Vision and the machine learning workflow
2016-06-19 10:42
1291 查看
The Computer Vision applications with machine learning have a common basic structure. This structure is divided into different steps that are repeated in almost all Computer Vision applications, and some others are omitted. In the following diagram, we show
you the different steps involved:
Almost any Computer Vision application starts with a
preprocessing stage that is applied to the input image. Preprocessing involveslight removal conditions and noise,
thresholding,blur, and so on.
After we apply all the preprocessing steps required to the input image, the second step is segmentation. In thesegmentation step, we need to
extract the regions of interest of an image and
isolate each one as a unique object of interest. For example,in a face detection system, we need to separate the faces from the rest of the parts in the scene.
After getting the objects inside the image, we continue with the next step. We need toextract all the features of each one detected object; a feature is a vector of characteristics of objects.
A characteristic describes our objects and can be thearea of the object,
contour, texture pattern, and so on.
Now, we have the descriptor of our object; a descriptor is a feature that describes an object, andwe use these descriptors to train our model or predict one of them. To do this, we need to create a big dataset of features,
where hundreds, thousands, and millions of images are preprocessed, and extracted features use all these features in a train model function that we choose:
When we train a dataset, the model learns all the parameters required to predict when a new vector of features with an unknown label is given:
After we get the prediction, sometimes, a
post-processing of output data is required;for example, merging multiple classifications todecrease the prediction error or merging multiple labels. A sample case is OCR (Optical Character Recognition),where the classification
result is per character, and by combining the results of character recognitions, we construct a word. This means that we can create a postprocessing method to correct errors in detected words.
you the different steps involved:
Almost any Computer Vision application starts with a
preprocessing stage that is applied to the input image. Preprocessing involveslight removal conditions and noise,
thresholding,blur, and so on.
After we apply all the preprocessing steps required to the input image, the second step is segmentation. In thesegmentation step, we need to
extract the regions of interest of an image and
isolate each one as a unique object of interest. For example,in a face detection system, we need to separate the faces from the rest of the parts in the scene.
After getting the objects inside the image, we continue with the next step. We need toextract all the features of each one detected object; a feature is a vector of characteristics of objects.
A characteristic describes our objects and can be thearea of the object,
contour, texture pattern, and so on.
Now, we have the descriptor of our object; a descriptor is a feature that describes an object, andwe use these descriptors to train our model or predict one of them. To do this, we need to create a big dataset of features,
where hundreds, thousands, and millions of images are preprocessed, and extracted features use all these features in a train model function that we choose:
When we train a dataset, the model learns all the parameters required to predict when a new vector of features with an unknown label is given:
After we get the prediction, sometimes, a
post-processing of output data is required;for example, merging multiple classifications todecrease the prediction error or merging multiple labels. A sample case is OCR (Optical Character Recognition),where the classification
result is per character, and by combining the results of character recognitions, we construct a word. This means that we can create a postprocessing method to correct errors in detected words.
相关文章推荐
- 奇怪的go语言iota
- lnmp环境搭建之编译安装php-5.3.27.tar.gz
- 七个问题回答
- intellij idea 代码正常,但是编译出现 java:需要";"
- 深度优先搜索-ZOJ 1047 Image Perimeters
- 并归排序
- linux下安装oracle中遇到的一些问题
- 两个iCarousel联动
- VMware网络连接模式—桥接、NAT以及仅主机模式的详细介绍和区别
- CSS选择器详解
- 获取网页音频资源
- Vim下的插件管理工具pathogen简介
- Struts2-->布尔值(boolean)类型转换注意问题
- SQL 的常用更改表约束
- PHP基础 CGI,FastCGI,PHP-CGI与PHP-FPM的区别
- git从ssh到提交到github
- Android定位获取当前经纬度
- c#datetime 类型数据操作
- C/C++中extern关键字详解
- SpringBoot入门系列:第一篇 Hello World