安卓利用opencv实现自定义图像识别

「爱情、让人受尽委屈。」 2022-05-09 10:34 947阅读 0赞

## 安卓利用opencv实现自定义图像识别 ##

要在安卓上实现自定义图像识别，我们需要用到opencv-android-sdk先上效果图

![70][]

下面来讲讲具体实现思路：

[1、配置android studio中opencv的环境][1_android studio_opencv]

[2、训练自定义图像数据集][2]

3、将训练好的数据集加载进行识别

InputStream is = getResources().openRawResource(R.raw.cascade);
                            File cascadeDir = getDir("cascade", Context.MODE_PRIVATE);
                            mCascadeFile = new File(cascadeDir, "lbpcascade_frontalface.xml");
                            FileOutputStream os = new FileOutputStream(mCascadeFile);
    
                            byte[] buffer = new byte[4096];
                            int bytesRead;
                            while ((bytesRead = is.read(buffer)) != -1) {
                                os.write(buffer, 0, bytesRead);
                            }
                            is.close();
                            os.close();
    
                            mJavaDetector = new CascadeClassifier(mCascadeFile.getAbsolutePath());
                            if (mJavaDetector.empty()) {
                                Log.e(TAG, "Failed to load cascade classifier");
                                mJavaDetector = null;
                            } else
                                Log.i(TAG, "Loaded cascade classifier from " + mCascadeFile.getAbsolutePath());
    
                            mNativeDetector = new DetectionBasedTracker(mCascadeFile.getAbsolutePath(), 0);
    
                            cascadeDir.delete();

整个工程已上传有需要请复制下面链接：

[https://download.csdn.net/download/sm16111/10703471][https_download.csdn.net_download_sm16111_10703471]

参考博客：

环境配置：[https://blog.csdn.net/andrexpert/article/details/78993533][https_blog.csdn.net_andrexpert_article_details_78993533]

自定义目标训练：[https://blog.csdn.net/wuxiaoyao12/article/details/39227189][https_blog.csdn.net_wuxiaoyao12_article_details_39227189]

[70]: /images/20220509/fa701c1facf94cf1b22571a477ef9796.png
[1_android studio_opencv]: https://blog.csdn.net/sm16111/article/details/81839401
[2]: https://blog.csdn.net/sm16111/article/details/81624317
[https_download.csdn.net_download_sm16111_10703471]: https://download.csdn.net/download/sm16111/10703471
[https_blog.csdn.net_andrexpert_article_details_78993533]: https://blog.csdn.net/andrexpert/article/details/78993533
[https_blog.csdn.net_wuxiaoyao12_article_details_39227189]: https://blog.csdn.net/wuxiaoyao12/article/details/39227189