WOLFRAM

Wolfram 语言与系统参考资料中心

性别分类

训练一个分类器从图像中识别男性和女性的脸部.

导入有标签的前部数据.
Wolfram Language code: images = {[image], ..., [image]}; gender = {"male", ..., "female"};
从图像中裁剪出脸部，并用 FindFaces、HistogramTransform 和 ConformImages 将集合进行统一.
Wolfram Language code: faces = ConformImages[HistogramTransform@ImageTrim[#, FindFaces[#][[1]]]& /@ images, ColorSpace -> "Grayscale"]
Wolfram Language code: {[image], ..., [image]}
定义一个训练以及测试集合，并用其准备分类器.
Wolfram Language code: trainingSetSize = 30; trainingSet = Rule@@@Transpose@{faces, gender}[[All, ;; trainingSetSize]]; testSet = Rule@@@Transpose@{faces, gender}[[All, trainingSetSize + 1 ;; ]];
用 Classify 构建分类器.
Wolfram Language code: GenderClassifier = Classify[trainingSet, Method -> "LogisticRegression"]
在两个集合上测试分类器的准确性.
Wolfram Language code: ClassifierMeasurements[GenderClassifier, trainingSet, "Accuracy"]
Wolfram Language code: ClassifierMeasurements[GenderClassifier, testSet, "Accuracy"]
创建函数可以对任意图像进行分类.
Wolfram Language code: GenderDetect[img_Image] := With[{faces = FindFaces[img]}, If[faces =!= {}, GenderClassifier[ HistogramTransform[ImageTrim[ColorConvert[img, GrayLevel], faces[[1]]]] ], "no face detected" ]] GenderDetect[images__Image] := GenderDetect /@ {images}
Wolfram Language code: imgs = {[image], [image], [image], [image], [image]};
Wolfram Language code: GenderDetect@@imgs