文章目录

  • 前言
  • 一、代码实现步骤
    • 1.引入库
    • 2.均值滤波（高斯滤波、高斯双边滤波）
    • 3.边缘检测
    • 4.像素二值化
    • 5.旋转矫正
    • 6.ROI获取
    • 7.建立特征
    • 8.二值纹理特征提取
    • 9.图片分成m*n块
    • 10.LBP特征提取
    • 11.SIFT特征提取与匹配
    • 12.绘制第几组样本的类内类间距离直方图
  • 总结

前言

手指静脉识别技术是一种新的生物特征识别技术，它利用手指内的静脉分布图像来进行身份识别。
工作原理
是依据人类手指中流动的血液可吸收特定波长的光线，而使用特定波长光线对手指进行照射，可得到手指静脉的清晰图像。利用这一固有的科学特征，将实现对获取的影像进行分析、处理，从而得到手指静脉的生物特征，再将得到的手指静脉特征信息与事先注册的手指静脉特征进行比对，从而确认登录者的身份。本文利用OpenCV各种图像算法实现对手指静脉进行识别，使用传统的方法来处理图像，而不是深度学习方法。代码实现框架图如下所示：


直方图识别效果

一、代码实现步骤

1.引入库

# -*- coding: utf-8 -*-
import cv2
import numpy as np
import matplotlib.pyplot as plt
import math
import numpy
import os

2.均值滤波（高斯滤波、高斯双边滤波）

def first_filter(img):#均值滤波img_Blur=cv2.blur(img,(5,5))'''#高斯滤波img_GaussianBlur=cv2.GaussianBlur(img,(7,7),0)#高斯双边滤波img_bilateralFilter=cv2.bilateralFilter(img,40,75,75)'''return img, img_Blur

3.边缘检测

代码如下（示例）：

def edge_detection(img):#img = cv2.imread(file, 0)#img = cv2.imread("01.jpg", 0)x = cv2.Sobel(img,cv2.CV_16S,1,0)y = cv2.Sobel(img,cv2.CV_16S,0,1)absX = cv2.convertScaleAbs(x)# 转回uint8absY = cv2.convertScaleAbs(y)img_edge = cv2.addWeighted(absX,0.5,absY,0.5,0)'''#cv2.imshow("absX", absX)#cv2.imshow("absY", absY)#cv2.imshow("Result", img_edge)#cv2.waitKey(0)#cv2.destroyAllWindows()fig = plt.figure(figsize = (30, 30))ax1 = fig.add_subplot(1, 2, 1)ax2 = fig.add_subplot(1, 2, 2)#ax3 = fig.add_subplot(1, 3, 3)ax1.imshow(img, cmap = plt.cm.gray)ax2.imshow(img_edge, cmap = plt.cm.gray)plt.show()'''return img, img_edge

4.像素二值化

 # threshold 像素两极化的阈值
def pixel_polarization(img_edge, img, threshold):for i in range(len(img_edge)):for j in range(len(img_edge[i,:])):if img_edge[i][j] > threshold:img_edge[i][j] = 255else:img_edge[i][j] = 0'''fig = plt.figure(figsize = (16, 16))ax1 = fig.add_subplot(1, 2, 1)ax2 = fig.add_subplot(1, 2, 2)ax1.imshow(img, cmap = plt.cm.gray)ax2.imshow(img_edge, cmap = plt.cm.gray)plt.show()'''img_edge_polar = img_edgereturn img_edge_polardef positioning_middle_point(img, dst, point_pixel):h, w = img.shapew1 = w // 5  # 作为左边竖线的x坐标w2 = (w // 5) * 4 # 作为右边竖线的x坐标'''print("roi width: ",h, w1, w2)'''low_l = Falsehigh_l = Falsewhile (not low_l or not high_l) and w1 < (w // 2):for i, pix in enumerate(dst[:, w1]):if i+1 < (h // 2) and not low_l:if pix == 255:low_l = Truelower_left = ielif i+1 > (h // 2) and not high_l:h_h = int(h * (3/2) - (i+1)) # 除法会带来小数，因此用int(), h/2开始对称位置找亮点'''print(h_h)'''if dst[h_h, w1] == 255:high_l = Truehigher_left = h_hif not low_l or not high_l:w1 = w1 + 2middle_left = (lower_left + higher_left) // 2low_r = Falsehigh_r = Falsewhile (not low_r or not high_r) and w2 > (w // 2):for i, pix in enumerate(dst[:, w2]):if i+1 < (h // 2) and not low_r:if pix == 255:low_r = Truelower_right = ielif i+1 > (h // 2) and not high_r:h_h = int(h * (3/2) - (i+1))if dst[h_h, w2] == 255:high_r = Truehigher_right = h_hif not low_r or not high_r:w2 = w2 - 2middle_right = (lower_right + higher_right) // 2'''dst[middle_left, w1] = point_pixeldst[middle_left+1, w1] = point_pixeldst[middle_left-1, w1] = point_pixeldst[middle_left, w1 + 1] = point_pixeldst[middle_left, w1 - 1] = point_pixeldst[middle_right, w2] = point_pixeldst[middle_right+1, w2] = point_pixeldst[middle_right-1, w2] = point_pixeldst[middle_right, w2 + 1] = point_pixeldst[middle_right, w2 - 1] = point_pixelfig = plt.figure(figsize = (16, 16))ax1 = fig.add_subplot(1, 2, 1)ax2 = fig.add_subplot(1, 2, 2)ax1.imshow(img, cmap = plt.cm.gray)ax2.imshow(dst, cmap = plt.cm.gray)plt.show()'''return dst, middle_left, middle_right, w1, w2

5.旋转矫正

def rotation_correction(img, dst, middle_right, middle_left, w1, w2):tangent_value = float(middle_right - middle_left) / float(w2 - w1)rotation_angle = np.arctan(tangent_value)/math.pi*180(h,w) = img.shapecenter = (w // 2,h // 2)M = cv2.getRotationMatrix2D(center,rotation_angle,1)#旋转缩放矩阵：(旋转中心，旋转角度，缩放因子)rotated_dst = cv2.warpAffine(dst,M,(w,h))rotated_img = cv2.warpAffine(img,M,(w,h))'''fig = plt.figure(figsize = (16, 16))ax1 = fig.add_subplot(1, 3, 1)ax2 = fig.add_subplot(1, 3, 2)ax3 = fig.add_subplot(1, 3, 3)ax1.imshow(img, cmap = plt.cm.gray)ax2.imshow(rotated_dst, cmap = plt.cm.gray)ax3.imshow(rotated_img, cmap = plt.cm.gray)plt.show()'''return rotated_dst, rotated_imgdef roi(rotated_img, rotated_edge, w1, w2, url):h, w = rotated_edge.shaper = range(0, h)r1 = range(0, h // 2)r2 = range(h // 2, h - 1)c = range(0, w)c1 = range(0, w // 2)c2 = range(w // 2, w-1)highest_edge = (rotated_edge[r1][:,c].sum(axis=1).argmax())lowest_edge = (rotated_edge[r2][:,c].sum(axis=1).argmax() + (h // 2))'''leftest_edge = (rotated_edge[r][:,c1].sum(axis=0).argmax())rightest_edge = (rotated_edge[r][:,c2].sum(axis=0).argmax() + (w // 2))'''leftest_edge = w1rightest_edge = w2'''_, img_w = rotated_edge.shapehalf = int(img_w/2)max_right_sum = 0max_right_i = 0sum_img = numpy.sum(rotated_img,axis=0)for i in range(half,img_w-50):s = sum(sum_img[i:i+50])if s > max_right_sum:max_right_sum = smax_right_i = i'''#print(highest_edge, lowest_edge, leftest_edge, rightest_edge)#print max_right_i#rightest_edge = max_right_i + 200#leftest_edge = 0 '''rotated_edge[highest_edge, : ] = 200rotated_edge[lowest_edge, : ] = 200 #150rotated_edge[: , leftest_edge] = 200 #200rotated_edge[: , rightest_edge] = 200 #250rotated_croped = rotated_edge[highest_edge : lowest_edge, leftest_edge : rightest_edge]'''rotated_croped_img = rotated_img[highest_edge : lowest_edge, leftest_edge : rightest_edge]'''fig = plt.figure(figsize = (30, 30))ax1 = fig.add_subplot(2, 2, 1)ax2 = fig.add_subplot(2, 2, 2)ax3 = fig.add_subplot(2, 2, 3)ax4 = fig.add_subplot(2, 2, 4)ax1.imshow(rotated_edge, cmap = plt.cm.gray)ax2.imshow(rotated_croped, cmap = plt.cm.gray)ax3.imshow(rotated_img, cmap = plt.cm.gray)ax4.imshow(rotated_croped_img, cmap = plt.cm.gray)plt.show()'''#print("rotated_croped_img type: ", rotated_croped_img)#cv2.imwrite(url, rotated_croped_img)#im = Image.fromarray(rotated_croped_img)#im.save(url)return rotated_croped_img

6.ROI获取

def get_imgs_roi(img_file):images = os.listdir(img_file)for i, image in enumerate(images):print(i)print(image)img_raw = cv2.imread(os.path.join(img_file, image), 0)print(img_raw.shape)'''(h,w) = img.shapecenter = (w / 2,h / 2)M = cv2.getRotationMatrix2D(center,90,1)#旋转缩放矩阵：(旋转中心，旋转角度，缩放因子)img_raw = cv2.warpAffine(img,M,(w,h))'''#img_raw, img_edge = edge_detection(img_raw)img_raw, img_Blur = first_filter(img_raw)img_raw, img_Blur_edge = edge_detection(img_Blur)'''fig = plt.figure(figsize = (50, 15))ax1 = fig.add_subplot(1, 3, 1)ax2 = fig.add_subplot(1, 3, 2)ax3 = fig.add_subplot(1, 3, 3)ax1.imshow(img_raw, cmap = plt.cm.gray)ax2.imshow(img_edge, cmap = plt.cm.gray)ax3.imshow(img_Blur_edge, cmap = plt.cm.gray)plt.show()'''img_Blur_edge_polar = pixel_polarization(img_Blur_edge, img_raw, 25) #二值化img_Blur_edge_polar_midd, middle_left, middle_right, w1, w2= positioning_middle_point(img_raw, img_Blur_edge_polar, 100)img_Blur_edge_polar_midd_rotated, rotated_img = rotation_correction(img_raw, img_Blur_edge_polar_midd, middle_right, middle_left, w1, w2)# roi图像保存路径new_file = './roi_600_2_all_320240'save_root = os.path.join(new_file,image)roi_img = roi(rotated_img, img_Blur_edge_polar_midd_rotated, w1, w2, save_root)resized_roi_img = img_resized_enhance(roi_img, save_root)

7.建立特征

def build_filters():""" returns a list of kernels in several orientations"""filters = []ksize = 31for theta in np.arange(0, np.pi, np.pi / 4):params = {'ksize':(ksize, ksize), 'sigma':3.3, 'theta':theta, 'lambd':18.3,'gamma':4.5, 'psi':0.89, 'ktype':cv2.CV_32F}kern = cv2.getGaborKernel(**params)kern /= 1.5*kern.sum()filters.append((kern,params))return filtersdef getGabor(img, filters):""" returns the img filtered by the filter list"""accum = np.zeros_like(img)for kern,params in filters:fimg = cv2.filter2D(img, cv2.CV_8UC3, kern)np.maximum(accum, fimg, accum)return accum

8.二值纹理特征提取

def bin_features_extract(roi_file):'''images_roi = os.listdir(roi_file)for i, image_roi in enumerate(images_roi):print(i)print(image_roi)img_roi_raw = cv2.imread(os.path.join(roi_file, image_roi), 0)'''img_roi_raw = cv2.imread(roi_file, 0)# Gabor滤波器filters = build_filters()img_roi_raw_gabor = getGabor(img_roi_raw, filters)#print(img_roi_raw_gabor)#灰度归一化#norm_resized_img = cv2.normalize(img_roi_raw_gabor, norm_resized_img, 0, 255, cv2.NORM_MINMAX)#二值化#img_roi_raw_gabor_polar60 = img_roi_raw_gabor.copy()#img_roi_raw_gabor_polar60 = pixel_polarization(img_roi_raw_gabor_polar60, img_roi_raw, 60)img_roi_raw_gabor_polar70 = img_roi_raw_gabor.copy()img_roi_raw_gabor_polar70 = pixel_polarization(img_roi_raw_gabor_polar70, img_roi_raw, 70)'''plt.figure(figsize = (30, 30))plt.subplot(2, 2, 1), plt.title('img_roi_raw')plt.imshow(img_roi_raw, cmap = plt.cm.gray)plt.subplot(2, 2, 2), plt.title('img_roi_raw_gabor')plt.imshow(img_roi_raw_gabor, cmap = plt.cm.gray)plt.subplot(2, 2, 3), plt.title('img_roi_raw_gabor_polar60')plt.imshow(img_roi_raw_gabor_polar60, cmap = plt.cm.gray)plt.subplot(2, 2, 4), plt.title('img_roi_raw_gabor_polar70')plt.imshow(img_roi_raw_gabor_polar70, cmap = plt.cm.gray)plt.show()'''return img_roi_raw_gabor_polar70def bin_match(img1_path, img2_path):img1 = bin_features_extract(img1_path)img2 = bin_features_extract(img2_path)height, width = img1.shapesize = height * widthscore = 0for i in range(len(img1)):for j in range(len(img1[i,:])):if img1[i][j] == img2[i][j]:score += 1scores = 100 * round((score / size), 4)#print(img1_path, img2_path, scores)return scores

9.图片分成m*n块

def cut_image(image, m, n):height, width = image.shapeitem_width = int(width // m)item_height = int(height // n)#box_list = []cropped_list = []# (left, upper, right, lower)for i in range(0,n):#两重循环，生成m*n张图片基于原图的位置for j in range(0,m):#print((i*item_width,j*item_width,(i+1)*item_width,(j+1)*item_width))#box = (j*item_width,i*item_height,(j+1)*item_width,(i+1)*item_height)#box_list.append(box)cropped = image[i*item_height:(i+1)*item_height, j*item_width:(j+1)*item_width]cropped_list.append(cropped)print(len(cropped_list))#image_list = [image.crop(box) for box in box_list]return cropped_list

10.LBP特征提取

def LBP_feature_extrector(roi_file):images_roi = os.listdir(roi_file)# settings for LBPradius = 3n_points = 8 * radiusMETHOD = 'uniform'for i, image_roi in enumerate(images_roi):print(i)print(image_roi)img_roi_raw = cv2.imread(os.path.join(roi_file, image_roi), 0)img_roi_raw_lbp = local_binary_pattern(img_roi_raw, n_points, radius, METHOD)#print(img_roi_raw_lbp.shape())#img_roi_raw_lbp_cut = cut_image(img_roi_raw_lbp, 4, 4) #分成4*4#分块显示#plt.figure(figsize = (30, 30))#print(img_roi_raw_lbp_cut.shape())'''score = cv2.compareHist(lbp_hist, lbp_hist, cv2.HISTCMP_BHATTACHARYYA)#score = kullback_leibler_divergence(lbp_hist, lbp_hist)print(score)''''''#绘制直方图#lbp_hist = plt.hist(img_roi_raw_lbp.ravel(),256,[0,256])n_bins = int(img_roi_raw_lbp.max() + 1)lbp_hist = plt.hist(img_roi_raw_lbp.ravel(), density=True, bins=n_bins, range=(0, n_bins), facecolor='0.5')plt.figure(figsize = (30, 30))plt.subplot(1, 2, 1), plt.title('img_roi_raw')plt.imshow(img_roi_raw, cmap = plt.cm.gray)plt.subplot(1, 2, 2), plt.title('img_roi_raw_lbp')plt.imshow(img_roi_raw_lbp, cmap = plt.cm.gray)
#        plt.subplot(1, 3, 3), plt.title('lbp_hist')
#        plt.imshow(lbp_hist)plt.show()'''

11.SIFT特征提取与匹配

def SIFT_detector(gray_path):images_sift = os.listdir(gray_path)for i, image_sift in enumerate(images_sift):print(i)print(image_sift)img = cv2.imread(os.path.join(gray_path, image_sift), 0)'''#sift检测sift = cv2.xfeatures2d.SIFT_create()kp = sift.detect(img,None)img_sift=cv2.drawKeypoints(img,kp,img,flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)''''''#SURF检测surf = cv2.xfeatures2d.SURF_create()kp = surf.detect(img,None)img_surf=cv2.drawKeypoints(img,kp,img,flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)''''''#ORB检测，几乎没有orb = cv2.ORB_create()kp = orb.detect(img,None)img_orb=cv2.drawKeypoints(img,kp,img,flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)'''#KAZE检测kaze = cv2.KAZE_create()kp = kaze.detect(img,None)img_kaze=cv2.drawKeypoints(img,kp,img,flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)#cv2.imwrite('sift_keypoints.jpg',img)plt.figure(figsize = (30, 30))plt.subplot(1, 2, 1), plt.title('img')plt.imshow(img, cmap = plt.cm.gray)plt.subplot(1, 2, 2), plt.title('img_kaze')plt.imshow(img_kaze, cmap = plt.cm.gray)
#        plt.subplot(1, 3, 3), plt.title('lbp_hist')
#        plt.imshow(lbp_hist)plt.show()def SIFT_match(img1_path, img2_path):img1 = cv2.imread(img1_path,0)          # queryImageimg2 = cv2.imread(img2_path,0) # trainImage# Initiate SIFT detectorsift = cv2.xfeatures2d.SIFT_create()# find the keypoints and descriptors with SIFTkp1, des1 = sift.detectAndCompute(img1,None)# BFMatcher with default paramsbf = cv2.BFMatcher()matches = bf.knnMatch(des1,des2, k=2)# Apply ratio testgood = []for m,n in matches:if m.distance < 0.75*n.distance:good.append([m])# cv2.drawMatchesKnn expects list of lists as matches.img3 = cv2.drawMatchesKnn(img1,kp1,img2,kp2,good,None,flags=cv2.DrawMatchesFlags_NOT_DRAW_SINGLE_POINTS)plt.imshow(img3),plt.show()def FLANN_based_Matcher(img1_path, img2_path):img1 = cv2.imread(img1_path, 0)          # queryImageimg2 = cv2.imread(img2_path, 0) # trainImage'''# Initiate SURF detectorsurf = cv2.xfeatures2d.SURF_create()# find the keypoints and descriptors with SIFTkp1, des1 = surf.detectAndCompute(img1,None)kp2, des2 = surf.detectAndCompute(img2,None)''''''kaze = cv2.KAZE_create()kp1, des1 = kaze.detectAndCompute(img1, None)kp2, des2 = kaze.detectAndCompute(img2, None)# Initiate ORB detectororb = cv2.ORB_create()# find the keypoints and descriptors with ORBkp1, des1 = orb.detectAndCompute(img1,None)kp2, des2 = orb.detectAndCompute(img2,None)'''# Initiate SIFT detectorsift = cv2.xfeatures2d.SIFT_create()# find the keypoints and descriptors with SIFTkp1, des1 = sift.detectAndCompute(img1,None)kp2, des2 = sift.detectAndCompute(img2,None)# FLANN parametersFLANN_INDEX_KDTREE = 1index_params = dict(algorithm = FLANN_INDEX_KDTREE, trees = 5)search_params = dict(checks=50)   # or pass empty dictionaryflann = cv2.FlannBasedMatcher(index_params,search_params)matches = flann.knnMatch(des1,des2,k=2)# Need to draw only good matches, so create a maskmatchesMask = [[0,0] for i in range(len(matches))]#matchesMask = []# ratio test as per Lowe's papermatch_keypoints_count = 0for i,(m,n) in enumerate(matches):if m.distance < 0.8*n.distance:matchesMask[i]=[1,0]#matchesMask.append(m)match_keypoints_count += 1draw_params = dict(matchColor = (0,255,0),singlePointColor = (255,0,0),matchesMask = matchesMask,flags = cv2.DrawMatchesFlags_DEFAULT)#计算匹配得分，保留小数点后两位score = 100 * round(match_keypoints_count / len(matchesMask), 4)#print('score = ', score)'''img3 = cv2.drawMatchesKnn(img1,kp1,img2,kp2,matches,None,**draw_params)#img3 = cv2.drawMatchesKnn(img1,kp1,img2,kp2,matches,None,flags=2)plt.imshow(img3),plt.show()'''return score

12.绘制第几组样本的类内类间距离直方图

def cal_scores(method='FLANN', flag=1):scores_list_diff = []scores_list_same = []#类间比较for k in range(1,5):if k is not flag:for i in range(1,11):for j in range(1,11):#print('%s', )strs1 = './data/roi_600_2_all_320240/600-{}-{}-1.bmp'.format(flag,i)strs2 = './data/roi_600_2_all_320240/600-{}-{}-1.bmp'.format(k,j)if method == 'FLANN':scores = FLANN_based_Matcher(strs1, strs2)scores_list_diff.append(scores)if method == 'BIN':scores = bin_match(strs1, strs2)scores_list_diff.append(scores)print(strs1,strs2, scores)#类内比较for i in range(1,11):for j in range(1,11):#print('%s', )strs1 = './data/roi_600_2_all_320240/600-{}-{}-1.bmp'.format(flag,i)strs2 = './data/roi_600_2_all_320240/600-{}-{}-1.bmp'.format(flag,j)if method == 'FLANN':scores = FLANN_based_Matcher(strs1, strs2)scores_list_same.append(scores)if method == 'BIN':scores = bin_match(strs1, strs2)scores_list_same.append(scores)print(strs1,strs2, scores)plt.hist(scores_list_diff, 60, range=(0,100), density=True, histtype="bar", facecolor='g', label='Inter-class', alpha=0.5)plt.hist(scores_list_same, 60, range=(0,100), density=True, histtype="bar", facecolor='r', label='In-class', alpha=0.5)plt.xlabel('Matched Features Ratio(MFR)(%)', fontsize=25)plt.ylabel('MFR Histogram', fontsize=25)plt.title('Distribution of matching ratio between in-class samples and inter-class samples', fontsize=30)#plt.text(60, .025, r'$\mu=100,\ \sigma=15$')#plt.axis([0, 1, 0, 0.03])plt.grid(True)plt.show()

总结

我们可以将阈值设置为60进行分类。

基于opencv的手指静脉识别（附源码）相关推荐

  1. Python基于OpenCV的人脸表情识别系统[源码＆部署教程]

    1.项目背景 人脸表情识别是模式识别中一个非常重要却十分复杂的课题.首先对计算机人脸表情识别技术的研究背景及发展历程作了简单回顾.然后对近期人脸表情识别的方法进行了分类综述.通过对各种识别方法的分析与 ...

  2. Python基于OpenCV的异常行为检测系统[源码＆部署教程]

    1.项目背景 智能视频监控(Intelligent Video Surveillance , IVS)[1.2·3.4是计算机视觉技术5l在安防领域的应用,实现了由"被动监控"到& ...

  3. 基于Simulink雷达系统建模仿真（附源码）

    目录 一.系统架构 二.运行结果 2.1示例模拟 2.2 天线增益/方向的影响 2.3 接收器 LO 上的相位噪声使能 2.4 相位噪声的影响 三.源码 此示例显示如何设置由发射器.带目标的信道和接收 ...

  4. python本科毕业设计基于神经网络的虚假评论识别系统源码，含模型及数据

    主要函数: 1.corpusprocess原始语料处理函数 2.train_word2vec生成word2vec向量 3.generate_id2wec获得索引的w2id,和嵌入权重embedding ...

  5. 基于Simulink宽带单基地雷达系统仿真（附源码）

    目录 一.探索示例 1.1 收发器 1.2 信号处理子系统 1.3 渠道 1.4 目标子系统 二.结果和显示 三.总结 四.程序 本示例演示如何仿真宽带雷达系统.当雷达系统的带宽超过系统中心频率的5% ...

  6. Python基于OpenCV高空抛物检测系统[完整源码＆部署教程]

    1.视频演示: [项目分享]Python基于OpenCV高空抛物检测系统[完整源码&部署教程]_哔哩哔哩_bilibili 2.图片演示: 3.算法原理: 参考该博客提出的移动侦测法,即是根据 ...

  7. Python基于YOLOv5的交通标志识别系统[源码]

    1.图片演示: 2.视频演示: [项目分享]Python基于YOLOv5的交通标志识别系统[源码&技术文档&部署视频&数据集]_哔哩哔哩_bilibili 3.标注好的数据集: ...

  8. 简单实现 Android M 指纹识别(附源码)

    众所周知, Android阵营里的指纹兼容真可谓是一团糟, 每个厂家几乎都有一套自己的API, 直到Android M的出现, 才慢慢地走上正途. 那么今天我们就一起来探讨一下, Android M里 ...

  9. 源码系列：基于FPGA的PS2通信电路设计(附源码)

    今天给大侠带来基于FPGA的PS2通信电路设计,附源码,获取源码,请在"FPGA技术江湖"公众号内回复"PS2源码",可获取源码文件.话不多说,上货. 设计背景 ...

  10. Android上掌纹识别第一步：基于OpenCV的6种肤色分割 源码和效果图

    六种方法分别是:基于RGB分割,基于RG同道的分割,ycrcb+otsu(ostu可以参考http://blog.csdn.net/onezeros/article/details/6136770, ...

最新文章

  1. android studio 学习入门篇
  2. python文本数据增强_CVPR2020场景文字数据增强（纯python实现）
  3. TLB的作用及工作原理
  4. 模块化和组件化的定义以及两者的区别
  5. hdu 1176 dp 数塔问题
  6. echarts python源码_基于Django快速集成Echarts代码示例
  7. Redux有何优点？
  8. java JLabel改变大小后如何刷新_到底一行java代码是如何在计算机上执行的
  9. linux flush 文件,Linux文件系统学习：io的plug过程-blk_flush_plug_list的情况
  10. 在python中创建列表的最佳和/或最快方法
  11. java yyyy-mm-dd 日期格式_Java中的日历日期为yyyy-MM-dd格式
  12. 鸿蒙将至，安卓安否？
  13. HTML5程序开发范例宝典（韩旭著）读书笔记之渐变背景
  14. 隐藏版本信息号返回服务器名,Apache服务器隐藏版本号和系统
  15. 消息队列技术—获取JMS中文版和英文版API
  16. thinkphp5 两个控制器传参数_PID参数整定：看大神是如何整定参数
  17. Atitit mvc之道 attilax著 以vue为例 1. Atitti vue的几大概念 1 1.1. 声明式渲染 1 1.2. 条件与循环 2 1.3. 处理用户输入 click事件 2 1
  18. 一键u盘装系统ghost win7 64位教程
  19. 【学习周报】深度学习笔记第六周
  20. ASO代理业务浅析（一）aso服务商

热门文章

  1. javascript 验证 国际格式 电话号码
  2. 企业服务的定义、分类与特点
  3. win7计算机不显示dvd,win7系统不显示光驱盘符的解决方法
  4. 各类任务的数据集大数据库
  5. 马上2023年了，终于发现一款颜值爆表的记账软件
  6. IOS逆向分析—终极详细（一）
  7. matlab的四个取整函数！
  8. 图像处理之：最大类间方差法法进行图像二值化处理
  9. rtl8211 smi读取_RTL8211E应用（二）之信号输入、输出接口
  10. java jbutton_Java JButton按钮使用