大作业基于pyqt5+svm实现车牌识别源码+模型+数据集（高质量项目）

# 识别 import time import cv2 import numpy as np import SVM_Train import os from SVM_Train import SVM from args import args class PlateRecognition(): def __init__(self): self.SZ = args.Size # 训练图片长宽 self.MAX_WIDTH = args.MAX_WIDTH # 原始图片最大宽度 self.Min_Area = args.Min_Area # 车牌区域允许最大面积 self.PROVINCE_START = args.PROVINCE_START self.provinces = args.provinces self.cardtype = args.cardtype self.Prefecture = args.Prefecture self.cfg = args.Pic_size # 读取图片文件 def __imreadex(self, filename): return cv2.imdecode(np.fromfile(filename, dtype=np.uint8), cv2.IMREAD_COLOR) def __point_limit(self, point): if point[0] < 0: point[0] = 0 if point[1] < 0: point[1] = 0 # 利用投影法，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(self, 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(self, img, waves): part_cards = [] for wave in waves: part_cards.append(img[:, wave[0]:wave[1]]) return part_cards # 缩小车牌边界 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 if yh < i: yh = i for j in range(col_num): count = 0 for i in range(row_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 > row_num - row_num_limit: if xl > j: xl = j if xr < j: xr = j return xl, xr, yh, yl # 预处理 def __preTreatment(self, car_pic): if type(car_pic) == type(""): img = self.__imreadex(car_pic) else: img = car_pic pic_hight, pic_width = img.shape[:2] if pic_width > self.MAX_WIDTH: resize_rate = self.MAX_WIDTH / pic_width img = cv2.resize(img, (self.MAX_WIDTH, int(pic_hight * resize_rate)), interpolation=cv2.INTER_AREA) # 图片分辨率调整 # cv2.imshow('Image', img) ''' # 代码后期添加 # 用于处理不同亮度时色调整 gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) dark_point = (gray<40) target_array = gray[dark_point] datk_size = int(target_array.size / gray.size * 100) # datk_size为暗色占比 # img = cv2.addWeighted(img, 1, img, 2, 40) # 调整亮度 # img = cv2.addWeighted(img, 1.5, img, 0.5, 1) # 调整对比度 ''' kernel = np.array([[0, -1, 0], [-1, 5, -1], [0, -1, 0]], np.float32) # 定义一个核 img = cv2.filter2D(img, -1, kernel=kernel) # 锐化 blur = self.cfg["blur"] # 高斯去噪 if blur > 0: img = cv2.GaussianBlur(img, (blur, blur), 0) oldimg = img img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # cv2.imshow('GaussianBlur', img) kernel = np.ones((20, 20), np.uint8) img_opening = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel) # 开运算 img_opening = cv2.addWeighted(img, 1, img_opening, -1, 0); # 与上一次开运算结果融合 # cv2.imshow('img_opening', img_opening) # 找到图像边缘 ret, img_thresh = cv2.threshold(img_opening, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU) # 二值化 img_edge = cv2.Canny(img_thresh, 100, 200) # cv2.imshow('img_edge', img_edge) # 使用开运算和闭运算让图像边缘成为一个整体 kernel = np.ones((self.cfg["morphologyr"], self.cfg["morphologyc"]), np.uint8) img_edge1 = cv2.morphologyEx(img_edge, cv2.MORPH_CLOSE, kernel) # 闭运算 img_edge2 = cv2.morphologyEx(img_edge1, cv2.MORPH_OPEN, kernel) # 开运算 # cv2.imshow('img_edge2', img_edge2) # 查找图像边缘整体形成的矩形区域，可能有很多，车牌就在其中一个矩形区域中 try: image, contours, hierarchy = cv2.findContours(img_edge2, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) except ValueError: # ValueError: not enough values to unpack (expected 3, got 2) # cv2.findContours方法在高版本OpenCV中只返回两个参数 contours, hierarchy = cv2.findContours(img_edge2, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) contours = [cnt for cnt in contours if cv2.contourArea(cnt) > self.Min_Area] # 逐个排除不是车牌的矩形区域 car_contours = [] for cnt in contours: # 框选 生成最小外接矩形 返回值（中心(x,y), (宽,高), 旋转角度） rect = cv2.minAreaRect(cnt) # print('宽高:',rect[1]) area_width, area_height = rect[1] # 选择宽大于高的区域 if area_width < area_height: area_width, area_height = area_height, area_width wh_ratio = area_width / area_height # print('宽高比：',wh_ratio) # 要求矩形区域长宽比在2到5.5之间，2到5.5是车牌的长宽比，其余的矩形排除 if wh_ratio > 2 and wh_ratio < 5.5: car_contours.append(rect) # box = cv2.boxPoints(rect) # box = np.int0(box) # 框出所有可能的矩形 # oldimg = cv2.drawContours(img, [box], 0, (0, 0, 255), 2) # cv2.imshow("Test",oldimg ) # 矩形区域可能是倾斜的矩形，需要矫正，以便使用颜色定位 card_imgs = [] for rect in car_contours: if rect[2] > -1 and rect[2] < 1: # 创造角度，使得左、高、右、低拿到正确的值 angle = 1 else: angle = rect[2] rect = (rect[0], (rect[1][0] + 5, rect[1][1] + 5), angle) # 扩大范围，避免车牌边缘被排除 box = cv2.boxPoints(rect) heigth_point = right_point = [0, 0] left_point = low_point = [pic_width, pic_hight] for point in box: if left_point[0] > point[0]: left_point = point if low_point[1] > point[1]: low_point = point if heigth_point[1] < poi