渔夫老师 第一节课后作业礼包.zip

import cv2 import numpy as np from numpy.linalg import norm import sys import os import json SZ = 20 # 训练图片长宽 MAX_WIDTH = 1000 # 原始图片最大宽度 Min_Area = 2000 # 车牌区域允许最大面积 PROVINCE_START = 1000 # 读取图片文件 def imreadex(filename): return cv2.imdecode(np.fromfile(filename, dtype=np.uint8), cv2.IMREAD_COLOR) def point_limit(point): if point[0] < 0: point[0] = 0 if point[1] < 0: point[1] = 0 # 根据设定的阈值和图片直方图，找出波峰，用于分隔字符 def find_waves(threshold, histogram): up_point = -1 # 上升点 is_peak = False if histogram[0] > threshold: up_point = 0 is_peak = True wave_peaks = [] for i, x in enumerate(histogram): if is_peak and x < threshold: if i - up_point > 2: is_peak = False wave_peaks.append((up_point, i)) elif not is_peak and x >= threshold: is_peak = True up_point = i if is_peak and up_point != -1 and i - up_point > 4: wave_peaks.append((up_point, i)) return wave_peaks # 根据找出的波峰，分隔图片，从而得到逐个字符图片 def seperate_card(img, waves): part_cards = [] for wave in waves: part_cards.append(img[:, wave[0]:wave[1]]) return part_cards # 来自opencv的sample，用于svm训练 def deskew(img): m = cv2.moments(img) if abs(m['mu02']) < 1e-2: return img.copy() skew = m['mu11'] / m['mu02'] M = np.float32([[1, skew, -0.5 * SZ * skew], [0, 1, 0]]) img = cv2.warpAffine(img, M, (SZ, SZ), flags=cv2.WARP_INVERSE_MAP | cv2.INTER_LINEAR) return img # 来自opencv的sample，用于svm训练 def preprocess_hog(digits): samples = [] for img in digits: gx = cv2.Sobel(img, cv2.CV_32F, 1, 0) gy = cv2.Sobel(img, cv2.CV_32F, 0, 1) mag, ang = cv2.cartToPolar(gx, gy) bin_n = 16 bin = np.int32(bin_n * ang / (2 * np.pi)) bin_cells = bin[:10, :10], bin[10:, :10], bin[:10, 10:], bin[10:, 10:] mag_cells = mag[:10, :10], mag[10:, :10], mag[:10, 10:], mag[10:, 10:] hists = [np.bincount(b.ravel(), m.ravel(), bin_n) for b, m in zip(bin_cells, mag_cells)] hist = np.hstack(hists) # transform to Hellinger kernel eps = 1e-7 hist /= hist.sum() + eps hist = np.sqrt(hist) hist /= norm(hist) + eps samples.append(hist) return np.float32(samples) # 不能保证包括所有省份 provinces = [ "zh_cuan", "川", "zh_e", "鄂", "zh_gan", "赣", "zh_gan1", "甘", "zh_gui", "贵", "zh_gui1", "桂", "zh_hei", "黑", "zh_hu", "沪", "zh_ji", "冀", "zh_jin", "津", "zh_jing", "京", "zh_jl", "吉", "zh_liao", "辽", "zh_lu", "鲁", "zh_meng", "蒙", "zh_min", "闽", "zh_ning", "宁", "zh_qing", "靑", "zh_qiong", "琼", "zh_shan", "陕", "zh_su", "苏", "zh_sx", "晋", "zh_wan", "皖", "zh_xiang", "湘", "zh_xin", "新", "zh_yu", "豫", "zh_yu1", "渝", "zh_yue", "粤", "zh_yun", "云", "zh_zang", "藏", "zh_zhe", "浙" ] class StatModel(object): def load(self, fn): self.model = self.model.load(fn) def save(self, fn): self.model.save(fn) class SVM(StatModel): def __init__(self, C=1, gamma=0.5): self.model = cv2.ml.SVM_create() self.model.setGamma(gamma) self.model.setC(C) self.model.setKernel(cv2.ml.SVM_RBF) self.model.setType(cv2.ml.SVM_C_SVC) # 训练svm def train(self, samples, responses): self.model.train(samples, cv2.ml.ROW_SAMPLE, responses) # 字符识别 def predict(self, samples): r = self.model.predict(samples) return r[1].ravel() class CardPredictor: def __init__(self): # 车牌识别的部分参数保存在js中，便于根据图片分辨率做调整 f = open('config.js') j = json.load(f) for c in j["config"]: if c["open"]: self.cfg = c.copy() break else: raise RuntimeError('没有设置有效配置参数') def __del__(self): self.save_traindata() def train_svm(self): # 识别英文字母和数字 self.model = SVM(C=1, gamma=0.5) # 识别中文 self.modelchinese = SVM(C=1, gamma=0.5) if os.path.exists("svm.dat"): self.model.load("svm.dat") else: chars_train = [] chars_label = [] for root, dirs, files in os.walk("train\\chars2"): if len(os.path.basename(root)) > 1: continue root_int = ord(os.path.basename(root)) for filename in files: filepath = os.path.join(root, filename) digit_img = cv2.imread(filepath) digit_img = cv2.cvtColor(digit_img, cv2.COLOR_BGR2GRAY) chars_train.append(digit_img) # chars_label.append(1) chars_label.append(root_int) chars_train = list(map(deskew, chars_train)) chars_train = preprocess_hog(chars_train) # chars_train = chars_train.reshape(-1, 20, 20).astype(np.float32) chars_label = np.array(chars_label) print(chars_train.shape) self.model.train(chars_train, chars_label) if os.path.exists("svmchinese.dat"): self.modelchinese.load("svmchinese.dat") else: chars_train = [] chars_label = [] for root, dirs, files in os.walk("train\\charsChinese"): if not os.path.basename(root).startswith("zh_"): continue pinyin = os.path.basename(root) index = provinces.index(pinyin) + PROVINCE_START + 1 # 1是拼音对应的汉字 for filename in files: filepath = os.path.join(root, filename) digit_img = cv2.imread(filepath) digit_img = cv2.cvtColor(digit_img, cv2.COLOR_BGR2GRAY) chars_train.append(digit_img) # chars_label.append(1) chars_label.append(index) chars_train = list(map(deskew, chars_train)) chars_train = preprocess_hog(chars_train) # chars_train = chars_train.reshape(-1, 20, 20).astype(np.float32) chars_label = np.array(chars_label) print(chars_train.shape) self.modelchinese.train(chars_train, chars_label) def save_traindata(self): if not os.path.exists("svm.dat"): self.model.save("svm.dat") if not os.path.exists("svmchinese.dat"): self.modelchinese.save("svmchinese.dat") def accurate_place(self, card_img_hsv, limit1, limit2, color): row_num, col_num = card_img_hsv.shape[:2] xl = col_num xr = 0 yh = 0 yl = row_num # col_num_limit = self.cfg["col_num_limit"] row_num_limit = self.cfg["row_num_limit"] col_num_limit = col_num * 0.8 if color != "green" else col_num * 0.5 # 绿色有渐变 for i in range(row_num): count = 0 for j in range(col_num): H = card_img_hsv.item(i, j, 0) S = card_img_hsv.item(i, j, 1) V = card_img_hsv.item(i, j, 2) if limit1 < H <= limit2 and 34 < S and 46 < V: count += 1 if count > col_num_limit: if yl > i: yl = i