github 地址,包含数据集。 https://github.com/ranran4082391/ran_11 # coding=gbk from PIL import Image import numpy as np import os from sklearn.datasets import load_digits # 加载手写数字识别数据 from sklearn.model_selection import train_test_split # 训练测试数据分割 from sklearn.preprocessing import StandardScaler # 标准化工具 from sklearn.svm import LinearSVC from sklearn.metrics import classification_report # 预测结果分析工具 def ImageToMatrix(filename): # 读取图片 im = Image.open(filename) img = im.resize((32, 32), Image.ANTIALIAS) img = img.convert("1") data = img.getdata() data = np.matrix(data, dtype='float')/255.0 return np.array(data) mat = [] for filename in os.walk('train'): for list_f in filename[2]: data = ImageToMatrix('train/'+list_f) print(data) mat.append(data.reshape(1, -1).tolist()[0]) X = np.array(mat) y = np.array([x for x in range(0, 10)]) test_filename = r'train\9.jpg' test_data = ImageToMatrix(test_filename) print(test_data[0]) svm = LinearSVC() svm.fit(X, y) print(svm.predict(test_data)) ''' 以上是解决问题的基本方法,下面是包含大量训练集与测试集的样本,更有训练价值。 ''' digits = load_digits() # 数据纬度,1797幅图,8*8 print(digits.data.shape) # 分割数据 X_train, X_test, Y_train, Y_test = train_test_split(digits.data, digits.target, test_size=0.25, random_state=33) ss = StandardScaler() # fit是实例方法,必须由实例调用 X_train = ss.fit_transform(X_train) X_test = ss.transform(X_test) lsvc = LinearSVC() lsvc.fit(X_train, Y_train) Y_predict = lsvc.predict(X_test) print(classification_report(Y_test, Y_predict, target_names=digits.target_names.astype(str)))
SVM 算法处理手写识别体(包含如何处理原始图片的代码)
最新推荐文章于 2024-02-01 12:23:35 发布