您好,登錄后才能下訂單哦!
本文實(shí)例為大家分享了基于神經(jīng)卷積網(wǎng)絡(luò)的人臉識(shí)別,供大家參考,具體內(nèi)容如下
1.人臉識(shí)別整體設(shè)計(jì)方案
客_服交互流程圖:
2.服務(wù)端代碼展示
sk = socket.socket() # s.bind(address) 將套接字綁定到地址。在AF_INET下,以元組(host,port)的形式表示地址。 sk.bind(("172.29.25.11",8007)) # 開始監(jiān)聽傳入連接。 sk.listen(True) while True: for i in range(100): # 接受連接并返回(conn,address),conn是新的套接字對(duì)象,可以用來接收和發(fā)送數(shù)據(jù)。address是連接客戶端的地址。 conn,address = sk.accept() # 建立圖片存儲(chǔ)路徑 path = str(i+1) + '.jpg' # 接收?qǐng)D片大?。ㄗ止?jié)數(shù)) size = conn.recv(1024) size_str = str(size,encoding="utf-8") size_str = size_str[2 :] file_size = int(size_str) # 響應(yīng)接收完成 conn.sendall(bytes('finish', encoding="utf-8")) # 已經(jīng)接收數(shù)據(jù)大小 has_size has_size = 0 # 創(chuàng)建圖片并寫入數(shù)據(jù) f = open(path,"wb") while True: # 獲取 if file_size == has_size: break date = conn.recv(1024) f.write(date) has_size += len(date) f.close() # 圖片縮放 resize(path) # cut_img(path):圖片裁剪成功返回True;失敗返回False if cut_img(path): yuchuli() result = test('test.jpg') conn.sendall(bytes(result,encoding="utf-8")) else: print('falue') conn.sendall(bytes('人眼檢測(cè)失敗,請(qǐng)保持圖片眼睛清晰',encoding="utf-8")) conn.close()
3.圖片預(yù)處理
1)圖片縮放
# 根據(jù)圖片大小等比例縮放圖片 def resize(path): image=cv2.imread(path,0) row,col = image.shape if row >= 2500: x,y = int(row/5),int(col/5) elif row >= 2000: x,y = int(row/4),int(col/4) elif row >= 1500: x,y = int(row/3),int(col/3) elif row >= 1000: x,y = int(row/2),int(col/2) else: x,y = row,col # 縮放函數(shù) res=cv2.resize(image,(y,x),interpolation=cv2.INTER_CUBIC) cv2.imwrite(path,res)
2)直方圖均衡化和中值濾波
# 直方圖均衡化 eq = cv2.equalizeHist(img) # 中值濾波 lbimg=cv2.medianBlur(eq,3)
3)人眼檢測(cè)
# -*- coding: utf-8 -*- # 檢測(cè)人眼,返回眼睛數(shù)據(jù) import numpy as np import cv2 def eye_test(path): # 待檢測(cè)的人臉路徑 imagepath = path # 獲取訓(xùn)練好的人臉參數(shù) eyeglasses_cascade = cv2.CascadeClassifier('haarcascade_eye_tree_eyeglasses.xml') # 讀取圖片 img = cv2.imread(imagepath) # 轉(zhuǎn)為灰度圖像 gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY) # 檢測(cè)并獲取人眼數(shù)據(jù) eyeglasses = eyeglasses_cascade.detectMultiScale(gray) # 人眼數(shù)為2時(shí)返回左右眼位置數(shù)據(jù) if len(eyeglasses) == 2: num = 0 for (e_gx,e_gy,e_gw,e_gh) in eyeglasses: cv2.rectangle(img,(e_gx,e_gy),(e_gx+int(e_gw/2),e_gy+int(e_gh/2)),(0,0,255),2) if num == 0: x1,y1 = e_gx+int(e_gw/2),e_gy+int(e_gh/2) else: x2,y2 = e_gx+int(e_gw/2),e_gy+int(e_gh/2) num += 1 print('eye_test') return x1,y1,x2,y2 else: return False
4)人眼對(duì)齊并裁剪
# -*- coding: utf-8 -*- # 人眼對(duì)齊并裁剪 # 參數(shù)含義: # CropFace(image, eye_left, eye_right, offset_pct, dest_sz) # eye_left is the position of the left eye # eye_right is the position of the right eye # 比例的含義為:要保留的圖像靠近眼鏡的百分比, # offset_pct is the percent of the image you want to keep next to the eyes (horizontal, vertical direction) # 最后保留的圖像的大小。 # dest_sz is the size of the output image # import sys,math from PIL import Image from eye_test import eye_test # 計(jì)算兩個(gè)坐標(biāo)的距離 def Distance(p1,p2): dx = p2[0]- p1[0] dy = p2[1]- p1[1] return math.sqrt(dx*dx+dy*dy) # 根據(jù)參數(shù),求仿射變換矩陣和變換后的圖像。 def ScaleRotateTranslate(image, angle, center =None, new_center =None, scale =None, resample=Image.BICUBIC): if (scale is None)and (center is None): return image.rotate(angle=angle, resample=resample) nx,ny = x,y = center sx=sy=1.0 if new_center: (nx,ny) = new_center if scale: (sx,sy) = (scale, scale) cosine = math.cos(angle) sine = math.sin(angle) a = cosine/sx b = sine/sx c = x-nx*a-ny*b d =-sine/sy e = cosine/sy f = y-nx*d-ny*e return image.transform(image.size, Image.AFFINE, (a,b,c,d,e,f), resample=resample) # 根據(jù)所給的人臉圖像,眼睛坐標(biāo)位置,偏移比例,輸出的大小,來進(jìn)行裁剪。 def CropFace(image, eye_left=(0,0), eye_right=(0,0), offset_pct=(0.2,0.2), dest_sz = (70,70)): # calculate offsets in original image 計(jì)算在原始圖像上的偏移。 offset_h = math.floor(float(offset_pct[0])*dest_sz[0]) offset_v = math.floor(float(offset_pct[1])*dest_sz[1]) # get the direction 計(jì)算眼睛的方向。 eye_direction = (eye_right[0]- eye_left[0], eye_right[1]- eye_left[1]) # calc rotation angle in radians 計(jì)算旋轉(zhuǎn)的方向弧度。 rotation =-math.atan2(float(eye_direction[1]),float(eye_direction[0])) # distance between them # 計(jì)算兩眼之間的距離。 dist = Distance(eye_left, eye_right) # calculate the reference eye-width 計(jì)算最后輸出的圖像兩只眼睛之間的距離。 reference = dest_sz[0]-2.0*offset_h # scale factor # 計(jì)算尺度因子。 scale =float(dist)/float(reference) # rotate original around the left eye # 原圖像繞著左眼的坐標(biāo)旋轉(zhuǎn)。 image = ScaleRotateTranslate(image, center=eye_left, angle=rotation) # crop the rotated image # 剪切 crop_xy = (eye_left[0]- scale*offset_h, eye_left[1]- scale*offset_v) # 起點(diǎn) crop_size = (dest_sz[0]*scale, dest_sz[1]*scale) # 大小 image = image.crop((int(crop_xy[0]),int(crop_xy[1]),int(crop_xy[0]+crop_size[0]),int(crop_xy[1]+crop_size[1]))) # resize it 重置大小 image = image.resize(dest_sz, Image.ANTIALIAS) return image def cut_img(path): image = Image.open(path) # 人眼識(shí)別成功返回True;否則,返回False if eye_test(path): print('cut_img') # 獲取人眼數(shù)據(jù) leftx,lefty,rightx,righty = eye_test(path) # 確定左眼和右眼位置 if leftx > rightx: temp_x,temp_y = leftx,lefty leftx,lefty = rightx,righty rightx,righty = temp_x,temp_y # 進(jìn)行人眼對(duì)齊并保存截圖 CropFace(image, eye_left=(leftx,lefty), eye_right=(rightx,righty), offset_pct=(0.30,0.30), dest_sz=(92,112)).save('test.jpg') return True else: print('falue') return False
4.用神經(jīng)卷積網(wǎng)絡(luò)訓(xùn)練數(shù)據(jù)
# -*- coding: utf-8 -*- from numpy import * import cv2 import tensorflow as tf # 圖片大小 TYPE = 112*92 # 訓(xùn)練人數(shù) PEOPLENUM = 42 # 每人訓(xùn)練圖片數(shù) TRAINNUM = 15 #( train_face_num ) # 單人訓(xùn)練人數(shù)加測(cè)試人數(shù) EACH = 21 #( test_face_num + train_face_num ) # 2維=>1維 def img2vector1(filename): img = cv2.imread(filename,0) row,col = img.shape vector1 = zeros((1,row*col)) vector1 = reshape(img,(1,row*col)) return vector1 # 獲取人臉數(shù)據(jù) def ReadData(k): path = 'face_flip/' train_face = zeros((PEOPLENUM*k,TYPE),float32) train_face_num = zeros((PEOPLENUM*k,PEOPLENUM)) test_face = zeros((PEOPLENUM*(EACH-k),TYPE),float32) test_face_num = zeros((PEOPLENUM*(EACH-k),PEOPLENUM)) # 建立42個(gè)人的訓(xùn)練人臉集和測(cè)試人臉集 for i in range(PEOPLENUM): # 單前獲取人 people_num = i + 1 for j in range(k): #獲取圖片路徑 filename = path + 's' + str(people_num) + '/' + str(j+1) + '.jpg' #2維=>1維 img = img2vector1(filename) #train_face:每一行為一幅圖的數(shù)據(jù);train_face_num:儲(chǔ)存每幅圖片屬于哪個(gè)人 train_face[i*k+j,:] = img/255 train_face_num[i*k+j,people_num-1] = 1 for j in range(k,EACH): #獲取圖片路徑 filename = path + 's' + str(people_num) + '/' + str(j+1) + '.jpg' #2維=>1維 img = img2vector1(filename) # test_face:每一行為一幅圖的數(shù)據(jù);test_face_num:儲(chǔ)存每幅圖片屬于哪個(gè)人 test_face[i*(EACH-k)+(j-k),:] = img/255 test_face_num[i*(EACH-k)+(j-k),people_num-1] = 1 return train_face,train_face_num,test_face,test_face_num # 獲取訓(xùn)練和測(cè)試人臉集與對(duì)應(yīng)lable train_face,train_face_num,test_face,test_face_num = ReadData(TRAINNUM) # 計(jì)算測(cè)試集成功率 def compute_accuracy(v_xs, v_ys): global prediction y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1}) correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1}) return result # 神經(jīng)元權(quán)重 def weight_variable(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial) # 神經(jīng)元偏置 def bias_variable(shape): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial) # 卷積 def conv2d(x, W): # stride [1, x_movement, y_movement, 1] # Must have strides[0] = strides[3] = 1 return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') # 最大池化,x,y步進(jìn)值均為2 def max_pool_2x2(x): # stride [1, x_movement, y_movement, 1] return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME') # define placeholder for inputs to network xs = tf.placeholder(tf.float32, [None, 10304])/255. # 112*92 ys = tf.placeholder(tf.float32, [None, PEOPLENUM]) # 42個(gè)輸出 keep_prob = tf.placeholder(tf.float32) x_image = tf.reshape(xs, [-1, 112, 92, 1]) # print(x_image.shape) # [n_samples, 112,92,1] # 第一層卷積層 W_conv1 = weight_variable([5,5, 1,32]) # patch 5x5, in size 1, out size 32 b_conv1 = bias_variable([32]) h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 112x92x32 h_pool1 = max_pool_2x2(h_conv1) # output size 56x46x64 # 第二層卷積層 W_conv2 = weight_variable([5,5, 32, 64]) # patch 5x5, in size 32, out size 64 b_conv2 = bias_variable([64]) h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 56x46x64 h_pool2 = max_pool_2x2(h_conv2) # output size 28x23x64 # 第一層神經(jīng)網(wǎng)絡(luò)全連接層 W_fc1 = weight_variable([28*23*64, 1024]) b_fc1 = bias_variable([1024]) # [n_samples, 28, 23, 64] ->> [n_samples, 28*23*64] h_pool2_flat = tf.reshape(h_pool2, [-1, 28*23*64]) h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) # 第二層神經(jīng)網(wǎng)絡(luò)全連接層 W_fc2 = weight_variable([1024, PEOPLENUM]) b_fc2 = bias_variable([PEOPLENUM]) prediction = tf.nn.softmax((tf.matmul(h_fc1_drop, W_fc2) + b_fc2)) # 交叉熵?fù)p失函數(shù) cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = tf.matmul(h_fc1_drop, W_fc2)+b_fc2, labels=ys)) regularizers = tf.nn.l2_loss(W_fc1) + tf.nn.l2_loss(b_fc1) +tf.nn.l2_loss(W_fc2) + tf.nn.l2_loss(b_fc2) # 將正則項(xiàng)加入損失函數(shù) cost += 5e-4 * regularizers # 優(yōu)化器優(yōu)化誤差值 train_step = tf.train.AdamOptimizer(1e-4).minimize(cost) sess = tf.Session() init = tf.global_variables_initializer() saver = tf.train.Saver() sess.run(init) # 訓(xùn)練1000次,每50次輸出測(cè)試集測(cè)試結(jié)果 for i in range(1000): sess.run(train_step, feed_dict={xs: train_face, ys: train_face_num, keep_prob: 0.5}) if i % 50 == 0: print(sess.run(prediction[0],feed_dict= {xs: test_face,ys: test_face_num,keep_prob: 1})) print(compute_accuracy(test_face,test_face_num)) # 保存訓(xùn)練數(shù)據(jù) save_path = saver.save(sess,'my_data/save_net.ckpt')
5.用神經(jīng)卷積網(wǎng)絡(luò)測(cè)試數(shù)據(jù)
# -*- coding: utf-8 -*- # 兩層神經(jīng)卷積網(wǎng)絡(luò)加兩層全連接神經(jīng)網(wǎng)絡(luò) from numpy import * import cv2 import tensorflow as tf # 神經(jīng)網(wǎng)絡(luò)最終輸出個(gè)數(shù) PEOPLENUM = 42 # 2維=>1維 def img2vector1(img): row,col = img.shape vector1 = zeros((1,row*col),float32) vector1 = reshape(img,(1,row*col)) return vector1 # 神經(jīng)元權(quán)重 def weight_variable(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial) # 神經(jīng)元偏置 def bias_variable(shape): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial) # 卷積 def conv2d(x, W): # stride [1, x_movement, y_movement, 1] # Must have strides[0] = strides[3] = 1 return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') # 最大池化,x,y步進(jìn)值均為2 def max_pool_2x2(x): # stride [1, x_movement, y_movement, 1] return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME') # define placeholder for inputs to network xs = tf.placeholder(tf.float32, [None, 10304])/255. # 112*92 ys = tf.placeholder(tf.float32, [None, PEOPLENUM]) # 42個(gè)輸出 keep_prob = tf.placeholder(tf.float32) x_image = tf.reshape(xs, [-1, 112, 92, 1]) # print(x_image.shape) # [n_samples, 112,92,1] # 第一層卷積層 W_conv1 = weight_variable([5,5, 1,32]) # patch 5x5, in size 1, out size 32 b_conv1 = bias_variable([32]) h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 112x92x32 h_pool1 = max_pool_2x2(h_conv1) # output size 56x46x64 # 第二層卷積層 W_conv2 = weight_variable([5,5, 32, 64]) # patch 5x5, in size 32, out size 64 b_conv2 = bias_variable([64]) h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 56x46x64 h_pool2 = max_pool_2x2(h_conv2) # output size 28x23x64 # 第一層神經(jīng)網(wǎng)絡(luò)全連接層 W_fc1 = weight_variable([28*23*64, 1024]) b_fc1 = bias_variable([1024]) # [n_samples, 28, 23, 64] ->> [n_samples, 28*23*64] h_pool2_flat = tf.reshape(h_pool2, [-1, 28*23*64]) h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) # 第二層神經(jīng)網(wǎng)絡(luò)全連接層 W_fc2 = weight_variable([1024, PEOPLENUM]) b_fc2 = bias_variable([PEOPLENUM]) prediction = tf.nn.softmax((tf.matmul(h_fc1_drop, W_fc2) + b_fc2)) sess = tf.Session() init = tf.global_variables_initializer() # 下載訓(xùn)練數(shù)據(jù) saver = tf.train.Saver() saver.restore(sess,'my_data/save_net.ckpt') # 返回簽到人名 def find_people(people_num): if people_num == 41: return '任童霖' elif people_num == 42: return 'LZT' else: return 'another people' def test(path): # 獲取處理后人臉 img = cv2.imread(path,0)/255 test_face = img2vector1(img) print('true_test') # 計(jì)算輸出比重最大的人及其所占比重 prediction1 = sess.run(prediction,feed_dict={xs:test_face,keep_prob:1}) prediction1 = prediction1[0].tolist() people_num = prediction1.index(max(prediction1))+1 result = max(prediction1)/sum(prediction1) print(result,find_people(people_num)) # 神經(jīng)網(wǎng)絡(luò)輸出最大比重大于0.5則匹配成功 if result > 0.50: # 保存簽到數(shù)據(jù) qiandaobiao = load('save.npy') qiandaobiao[people_num-1] = 1 save('save.npy',qiandaobiao) # 返回 人名+簽到成功 print(find_people(people_num) + '已簽到') result = find_people(people_num) + ' 簽到成功' else: result = '簽到失敗' return result
神經(jīng)卷積網(wǎng)絡(luò)入門簡(jiǎn)介
以上就是本文的全部?jī)?nèi)容,希望對(duì)大家的學(xué)習(xí)有所幫助,也希望大家多多支持億速云。
免責(zé)聲明:本站發(fā)布的內(nèi)容(圖片、視頻和文字)以原創(chuàng)、轉(zhuǎn)載和分享為主,文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng),如果涉及侵權(quán)請(qǐng)聯(lián)系站長(zhǎng)郵箱:is@yisu.com進(jìn)行舉報(bào),并提供相關(guān)證據(jù),一經(jīng)查實(shí),將立刻刪除涉嫌侵權(quán)內(nèi)容。