利用mnist數據集的demo來做識別單張圖片數字

最近領導讓我做圖片識別,把這兩天的工作記錄一下吧,雖然中間做的磕磕碰碰,但是一個好的開始,加油!好了不灌雞湯了,let's? show!

在做圖片識別之前,需要對圖片做處理,利用的是opencv(python 環境需要裝)

比如我們要識別的電表的數字

下面是對該圖片的做opencv處理,源代碼如下:

# coding=utf-8

from __future__ import division? #整數相除為浮點數

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)

#圖像統一預處理成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)

處理后的結果如下:需要說明一下,對圖片數字的小數點,我們還沒有做處理,在此先擱淺,以后寫出來,后補!


下面就是我們的重頭戲了,利用的是兩層cnn做訓練并識別圖片,訓練的模型是mnist的demo,在這里我們是保存了該訓練的模型,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)

接下來就是利用訓練的模型來做識別了,plz see

# coding:utf-8

import tensorflow as tf

import numpy as np

import cv2

#初始化單個卷積核上的參數

def weight_variable(shape):

? ? initial = tf.truncated_normal(shape, stddev=0.1)

? ? return tf.Variable(initial)

#初始化單個卷積核上的偏置值

def bias_variable(shape):

? ? initial = tf.constant(0.1, shape=shape)

? ? return tf.Variable(initial)

#輸入特征x,用卷積核W進行卷積運算,strides為卷積核移動步長,

#padding表示是否需要補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進行最大池化操作,ksize進行池化的范圍,

def max_pool_2x2(x):

? ? return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')

#

? ? # 定義會話

with tf.Session() as sess:

? ? #聲明輸入圖片數據,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])

? ? #進行卷積操作,并添加relu激活函數

? ? h_conv1 = tf.nn.relu(conv2d(x_img,W_conv1) + b_conv1)

? ? #進行最大池化

? ? 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])

? ? #將卷積的產出展開

? ? h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])

? ? #神經網絡計算,并添加relu激活函數

? ? 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)

? ? # 圖片預處理

? ? # 數據從0~255轉為-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))

結果如下:

這里的數字識別大致過程差不多就這樣,雖然表面看起來很完美,但是還有些數字沒有識別正確,我舉的例子數字是都識別出來了,但是其他的數字還有點問題,這里在隨后我解決了,再做補充吧。

?著作權歸作者所有,轉載或內容合作請聯系作者
平臺聲明:文章內容(如有圖片或視頻亦包括在內)由作者上傳并發布,文章內容僅代表作者本人觀點,簡書系信息發布平臺,僅提供信息存儲服務。

推薦閱讀更多精彩內容