最近領(lǐng)導(dǎo)讓我做圖片識(shí)別拉盾,把這兩天的工作記錄一下吧,雖然中間做的磕磕碰碰,但是一個(gè)好的開始豁状,加油捉偏!好了不灌雞湯了,let's? show泻红!
在做圖片識(shí)別之前告私,需要對圖片做處理,利用的是opencv(python 環(huán)境需要裝)
比如我們要識(shí)別的電表的數(shù)字
下面是對該圖片的做opencv處理,源代碼如下:
# coding=utf-8
from __future__ import division? #整數(shù)相除為浮點(diǎn)數(shù)
import cv2
import numpy as np
import os
img = cv2.imread('testset/img4.PNG')
#cv2.imshow('Original', img)
cv2.waitKey(0)
#cv2.imwrite('save/img4.PNG',img)
# 灰度處理
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
#cv2.imshow('Gray', gray)
cv2.waitKey(0)
#cv2.imwrite('save/gray.PNG',gray)
# 均值濾波
# median = cv2.medianBlur(gray, 3)
blur = cv2.blur(img, (4, 4))
#cv2.imshow('Blur', blur)
cv2.waitKey(0)
#cv2.imwrite('save/blur.PNG',blur)
# Canny邊緣提取
canny = cv2.Canny(blur, 300, 450)
#cv2.imshow('Canny', canny)
cv2.waitKey(0)
#cv2.imwrite('save/canny.PNG',canny)
# 二值處理
#ret, thresh = cv2.threshold(canny, 90, 255, cv2.THRESH_BINARY)
#kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
#closed = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
# 膨脹操作
kernel = np.uint8(np.ones((7, 7)))
dilate = cv2.dilate(canny, kernel)
# 腐蝕操作
erode = cv2.erode(dilate,(9,9))
#cv2.imshow('Dilate', erode)
cv2.waitKey(0)
#cv2.imwrite('save/dilate.PNG',dilate)
(image, cnts, _) = cv2.findContours(dilate.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
for index, c in enumerate(cnts):
? ? rect = cv2.minAreaRect(c)
? ? box = np.int0(cv2.boxPoints(rect))
? ? # draw a bounding box arounded the detected number and display the image
? ? cv2.drawContours(img, [box], -1, (0, 255, 0), 0)
? ? Xs = [i[0] for i in box]
? ? Ys = [i[1] for i in box]
? ? x1 = min(Xs)
? ? x2 = max(Xs)
? ? y1 = min(Ys)
? ? y2 = max(Ys)
? ? hight = y2 - y1
? ? width = x2 - x1
? ? cropImg = image[y1:y1+hight, x1:x1+width]
? ? cv2.imshow(str(i + 1), cropImg)
? ? ######? ? 按順序保存圖片
? ? for j in i:
? ? ? ? cv2.imwrite('save/%d.PNG' % i[0], cropImg)
? ? ######
? ? cv2.waitKey(0)
#cv2.imshow('Image', img)
cv2.waitKey(0)
#cv2.imwrite('save/img.PNG',img)
#圖像統(tǒng)一預(yù)處理成28*28
imgs=os.listdir('save')
num = len(imgs)
for index,i in enumerate(imgs):
? ? img=cv2.imread('save/'+i,0)
? ? #print img.shape
? ? width=img.shape[1]
? ? height=img.shape[0]
? ? fx=28/width
? ? fy=28/height
? ? res = cv2.resize(img, None, fx=fx, fy=fy, interpolation=cv2.INTER_CUBIC) #圖像縮放成28x28
? ? cv2.imwrite('save/%d.png' % (index), res)
處理后的結(jié)果如下:需要說明一下承桥,對圖片數(shù)字的小數(shù)點(diǎn)驻粟,我們還沒有做處理,在此先擱淺,以后寫出來蜀撑,后補(bǔ)挤巡!
下面就是我們的重頭戲了,利用的是兩層cnn做訓(xùn)練并識(shí)別圖片酷麦,訓(xùn)練的模型是mnist的demo,在這里我們是保存了該訓(xùn)練的模型矿卑,talk is cheap ,show you my code!
import tensorflow as tf
import tensorflow.examples.tutorials.mnist.input_data as input_data
import os
MODEL_SAVE_PATH="model_data/"
MODEL_NAME="save_net.ckpt"
def weight_variable(shape):
? ? initial=tf.truncated_normal(shape,stddev=0.1)
? ? return tf.Variable(initial)
def bias_variable(shape):
? ? initial=tf.constant(0.1,shape=shape)
? ? return tf.Variable(initial)
def conv2d(x,W):
? ? return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding="SAME")
def max_pool_2x2(x):
? ? return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
with tf.Session() as sess:
? ? mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
? ? x = tf.placeholder(tf.float32, [None, 784])
? ? w_conv1=weight_variable([5,5,1,32])
? ? b_conv1=bias_variable([32])
? ? x_image=tf.reshape(x,[-1,28,28,1])
? ? y_ = tf.placeholder("float", [None, 10])
? ? h_conv1=tf.nn.relu(conv2d(x_image,w_conv1)+b_conv1)
? ? h_pool1=max_pool_2x2(h_conv1)
? ? w_conv2=weight_variable([5,5,32,64])
? ? b_conv2=bias_variable([64])
? ? h_conv2=tf.nn.relu(conv2d(h_pool1,w_conv2)+b_conv2)
? ? h_pool2=max_pool_2x2(h_conv2)
? ? w_fc1=weight_variable([7*7*64,1024])
? ? b_fc1=bias_variable([1024])
? ? h_pool2_flat=tf.reshape(h_pool2,[-1,7*7*64])
? ? h_fc1=tf.nn.relu(tf.matmul(h_pool2_flat,w_fc1)+b_fc1)
? ? keep_prob=tf.placeholder("float")
? ? h_fc1_drop=tf.nn.dropout(h_fc1,keep_prob)
? ? w_fc2=weight_variable([1024,10])
? ? b_fc2=bias_variable([10])
? ? y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop,w_fc2)+b_fc2)
? ? cross_entropy=-tf.reduce_sum(y_*tf.log(y_conv))
? ? train_step=tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
? ? saver = tf.train.Saver()
? ? correct_prediction=tf.equal(tf.argmax(y_conv,1),tf.argmax(y_,1))
? ? accuracy=tf.reduce_mean(tf.cast(correct_prediction,"float"))
? ? sess.run(tf.global_variables_initializer())
? ? for i in range(2000):
? ? ? ? batch=mnist.train.next_batch(50)
? ? ? ? if i%100==0:
? ? ? ? ? ? train_accuracy=accuracy.eval(feed_dict={x:batch[0],y_:batch[1],keep_prob:1.0})
? ? ? ? ? ? print("step %d,training accuracy %g" % (i,train_accuracy))
? ? ? ? train_step.run(feed_dict={x:batch[0],y_:batch[1],keep_prob:0.5})
? ? print("test accuracy %g" % accuracy.eval(feed_dict={x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0}))
? ? saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), write_meta_graph=False)
接下來就是利用訓(xùn)練的模型來做識(shí)別了,plz see
# coding:utf-8
import tensorflow as tf
import numpy as np
import cv2
#初始化單個(gè)卷積核上的參數(shù)
def weight_variable(shape):
? ? initial = tf.truncated_normal(shape, stddev=0.1)
? ? return tf.Variable(initial)
#初始化單個(gè)卷積核上的偏置值
def bias_variable(shape):
? ? initial = tf.constant(0.1, shape=shape)
? ? return tf.Variable(initial)
#輸入特征x沃饶,用卷積核W進(jìn)行卷積運(yùn)算母廷,strides為卷積核移動(dòng)步長,
#padding表示是否需要補(bǔ)齊邊緣像素使輸出圖像大小不變
def conv2d(x, W):
? ? return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
#對x進(jìn)行最大池化操作糊肤,ksize進(jìn)行池化的范圍琴昆,
def max_pool_2x2(x):
? ? return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')
#
? ? # 定義會(huì)話
with tf.Session() as sess:
? ? #聲明輸入圖片數(shù)據(jù),類別
? ? x = tf.placeholder(tf.float32,[None,784])
? ? x_img = tf.reshape(x , [-1,28,28,1])
? ? W_conv1 = weight_variable([5, 5, 1, 32])
? ? b_conv1 = bias_variable([32])
? ? #進(jìn)行卷積操作馆揉,并添加relu激活函數(shù)
? ? h_conv1 = tf.nn.relu(conv2d(x_img,W_conv1) + b_conv1)
? ? #進(jìn)行最大池化
? ? h_pool1 = max_pool_2x2(h_conv1)
? ? W_conv2 = weight_variable([5,5,32,64])
? ? b_conv2 = bias_variable([64])
? ? # 同理第二層卷積層
? ? h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
? ? h_pool2 = max_pool_2x2(h_conv2)
? ? W_fc1 = weight_variable([7*7*64,1024])
? ? b_fc1 = bias_variable([1024])
? ? #將卷積的產(chǎn)出展開
? ? h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])
? ? #神經(jīng)網(wǎng)絡(luò)計(jì)算业舍,并添加relu激活函數(shù)
? ? h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1) + b_fc1)
? ? keep_prob = tf.placeholder(tf.float32)
? ? h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
? ? W_fc2 = weight_variable([1024,10])
? ? b_fc2 = bias_variable([10])
? ? # 引用mnist訓(xùn)練好的保存的模型
? ? saver = tf.train.Saver(write_version=tf.train.SaverDef.V1)
? ? saver.restore(sess, 'model_data/save_net.ckpt')
? ? #輸出層,使用softmax進(jìn)行多分類
? ? y_conv=tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2)
? ? im = cv2.imread('save/img4_4.png', cv2.IMREAD_GRAYSCALE)
? ? im = cv2.resize(im, (28, 28), interpolation=cv2.INTER_CUBIC)
? ? img = cv2.GaussianBlur(im, (3, 3), 0)
? ? # 圖片預(yù)處理
? ? # 數(shù)據(jù)從0~255轉(zhuǎn)為-0.5~0.5
? ? img_gray = (im - (255 / 2.0)) / 255
? ? # img_gray = (im)/255
? ? # for i in range(28):
? ? #? ? for j in range(28):
? ? #? ? ? ? if img_gray[i][j]<=0.5:
? ? #? ? ? ? ? ? img_gray[i][j]=0
? ? #? ? ? ? else:
? ? #? ? ? ? ? ? img_gray[i][j]=1
? ? cv2.imshow('out',img_gray)
? ? cv2.waitKey(0)
? ? x_img = np.reshape(img_gray, [-1, 784])
? ? output = sess.run(y_conv , feed_dict = {x:x_img})
? ? print('the y_con :? ', '\n',output)
? ? print('the predict is : ', np.argmax(output))
結(jié)果如下:
這里的數(shù)字識(shí)別大致過程差不多就這樣升酣,雖然表面看起來很完美舷暮,但是還有些數(shù)字沒有識(shí)別正確,我舉的例子數(shù)字是都識(shí)別出來了噩茄,但是其他的數(shù)字還有點(diǎn)問題下面,這里在隨后我解決了,再做補(bǔ)充吧绩聘。