[英]Can vision.cascadeObjectDetector calculate HOG, LBP features given a cascade.xml?
I have created a cascade.xml for detecting face images using the opencv_traincascade utility. 我已经创建了一个使用opencv_traincascade实用工具检测面部图像的cascade.xml。 I am using LBP or HOG feature based cascades since they are much faster.
我正在使用基于LBP或HOG功能的级联,因为它们的速度要快得多。 And I do all my testing on Matlab using
vision.cascadeObjectDetector
. 然后,我使用
vision.cascadeObjectDetector
在Matlab上进行了所有测试。 But I am unsure if Matlab is capable of understanding and calculating LBP/ HOG features for a given cascade.xml file. 但是我不确定Matlab是否能够理解和计算给定的cascade.xml文件的LBP / HOG功能。
Is this the correct approach for testing a cascade detector? 这是测试级联检测器的正确方法吗? If not, what platform should I be using for testing?
如果没有,我应该使用哪个平台进行测试?
Yes, vision.cascadeObjectDetector
supports LBP and HOG, as well as Haar features, as of version R2013a. 是的,
vision.cascadeObjectDetector
支持LBP和HOG,以及哈尔的功能,如版本R2013a的。
Furthermore you can now train your detector using trainCascadeObjectDetector
function, which is easier to use than opencv_traincascade
. 此外,您现在可以使用
trainCascadeObjectDetector
函数训练检测器,该函数比opencv_traincascade
易于使用。 There is also a trainingImageLabeler
app, which gives you a nice GUI to label objects of interest in your images. 还有一个
trainingImageLabeler
应用程序,它为您提供了一个漂亮的GUI,可以在图像中标记感兴趣的对象。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.