a face emotion detector by caizheng

RunOnlineFaceEmotionDetecter.py

@@ -0,0 +1,80 @@
+# -*-coding:utf-8-*-
+import cv2
+import numpy as np
+import caffe
+import os
+
+SKIPCOUNT = 5  #跳帧数目
+
+def fe_init():
+    global caffe_root
+    global net
+    global transformer
+    caffe.set_mode_gpu()
+    net = caffe.Net('deploy.prototxt', 'fe_train_iter_40000.caffemodel', caffe.TEST)
+    transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
+    transformer.set_transpose('data', (2, 0, 1))
+    transformer.set_mean('data', np.load('fe_test_mean.npy').mean(1).mean(1))
+    transformer.set_raw_scale('data', 255)
+    transformer.set_channel_swap('data', (2, 1, 0))
+    net.blobs['data'].reshape(50, 3, 227, 227)
+
+def fe_predict(file_name):
+    global net
+    net.blobs['data'].data[...] = transformer.preprocess('data', caffe.io.load_image(file_name))
+    out = net.forward()
+    labels = np.loadtxt('synset_words.txt', str, delimiter='\t')
+    top_k = net.blobs['prob'].data[0].flatten().argsort()[-1:-6:-1]
+    #print(labels[out['prob'].argmax()])
+    index = out['prob'].argmax()
+    #print(out['prob'][index, index])
+    return [labels[out['prob'].argmax()], out['prob'][index, index]]
+
+
+cv2.namedWindow('faceDetect')
+cap = cv2.VideoCapture(0) #打开0号摄像头
+success, frame = cap.read()#读取一桢图像，前一个返回值是是否成功，后一个返回值是图像本身
+size = frame.shape[:2]#获得当前桢彩色图像的大小
+color = (255, 0, 0)#设置人脸框的颜色
+classifier = cv2.CascadeClassifier("haarcascade_frontalface_alt2.xml")#定义分类器
+faceid = 0
+fe_init()
+skipcount = SKIPCOUNT#每SKIPCOUNT帧判断一帧
+while success:
+    success, frame = cap.read()
+    image = np.zeros(size, dtype=np.float16)#定义一个与当前桢图像大小相同的的灰度图像矩阵
+    image = cv2.cvtColor(frame, cv2.cv.CV_BGR2GRAY)#将当前桢图像转换成灰度图像
+    cv2.equalizeHist(image, image)#灰度图像进行直方图等距化
+
+    #如下三行是设定最小图像的大小
+    divisor = 8
+    h, w = size
+    minSize = (w/divisor, h/divisor)
+    faceRects = classifier.detectMultiScale(image, 1.1, 4, cv2.CASCADE_SCALE_IMAGE, minSize)#人脸检测
+    if len(faceRects) > 0:  # 如果人脸数组长度大于0
+        faceRect = faceRects[0]
+        x, y, w, h = faceRect
+        if w > 0 and skipcount == 0:
+            skipcount = SKIPCOUNT
+            im = image[y:y+w, x:x+h]
+            save_name = 'test/face'+str(faceid)+'.jpg'
+            faceid += 1
+            im = cv2.resize(im, (227, 227))
+            cv2.imwrite(save_name, im)
+            [emotion, confidence] = fe_predict(save_name)
+            os.remove(save_name) 
+	    if confidence > 0.5:
+                print(emotion)
+        elif w > 0:
+            skipcount -= 1
+        cv2.rectangle(image, (x, y), (x+w, y+h), color)
+    cv2.imshow("faceDetect", image)#显示图像
+
+    key= cv2.waitKey(10)
+    c = chr(key & 255)
+    if c in ['q', 'Q', chr(27)]:
+        break
+
+
+
+cv2.destroyWindow("faceDetect")

deploy.prototxt

@@ -0,0 +1,212 @@
+name: "CaffeNet"
+input: "data"
+input_dim: 10
+input_dim: 3
+input_dim: 227
+input_dim: 227
+layer {
+  name: "conv1"
+  type: "Convolution"
+  bottom: "data"
+  top: "conv1"
+  convolution_param {
+    num_output: 96
+    kernel_size: 11
+    stride: 4
+  }
+}
+layer {
+  name: "relu1"
+  type: "ReLU"
+  bottom: "conv1"
+  top: "conv1"
+}
+layer {
+  name: "pool1"
+  type: "Pooling"
+  bottom: "conv1"
+  top: "pool1"
+  pooling_param {
+    pool: MAX
+    kernel_size: 3
+    stride: 2
+  }
+}
+layer {
+  name: "norm1"
+  type: "LRN"
+  bottom: "pool1"
+  top: "norm1"
+  lrn_param {
+    local_size: 5
+    alpha: 0.0001
+    beta: 0.75
+  }
+}
+layer {
+  name: "conv2"
+  type: "Convolution"
+  bottom: "norm1"
+  top: "conv2"
+  convolution_param {
+    num_output: 256
+    pad: 2
+    kernel_size: 5
+    group: 2
+  }
+}
+layer {
+  name: "relu2"
+  type: "ReLU"
+  bottom: "conv2"
+  top: "conv2"
+}
+layer {
+  name: "pool2"
+  type: "Pooling"
+  bottom: "conv2"
+  top: "pool2"
+  pooling_param {
+    pool: MAX
+    kernel_size: 3
+    stride: 2
+  }
+}
+layer {
+  name: "norm2"
+  type: "LRN"
+  bottom: "pool2"
+  top: "norm2"
+  lrn_param {
+    local_size: 5
+    alpha: 0.0001
+    beta: 0.75
+  }
+}
+layer {
+  name: "conv3"
+  type: "Convolution"
+  bottom: "norm2"
+  top: "conv3"
+  convolution_param {
+    num_output: 384
+    pad: 1
+    kernel_size: 3
+  }
+}
+layer {
+  name: "relu3"
+  type: "ReLU"
+  bottom: "conv3"
+  top: "conv3"
+}
+layer {
+  name: "conv4"
+  type: "Convolution"
+  bottom: "conv3"
+  top: "conv4"
+  convolution_param {
+    num_output: 384
+    pad: 1
+    kernel_size: 3
+    group: 2
+  }
+}
+layer {
+  name: "relu4"
+  type: "ReLU"
+  bottom: "conv4"
+  top: "conv4"
+}
+layer {
+  name: "conv5"
+  type: "Convolution"
+  bottom: "conv4"
+  top: "conv5"
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    group: 2
+  }
+}
+layer {
+  name: "relu5"
+  type: "ReLU"
+  bottom: "conv5"
+  top: "conv5"
+}
+layer {
+  name: "pool5"
+  type: "Pooling"
+  bottom: "conv5"
+  top: "pool5"
+  pooling_param {
+    pool: MAX
+    kernel_size: 3
+    stride: 2
+  }
+}
+layer {
+  name: "fc6"
+  type: "InnerProduct"
+  bottom: "pool5"
+  top: "fc6"
+  inner_product_param {
+    num_output: 4096
+  }
+}
+layer {
+  name: "relu6"
+  type: "ReLU"
+  bottom: "fc6"
+  top: "fc6"
+}
+layer {
+  name: "drop6"
+  type: "Dropout"
+  bottom: "fc6"
+  top: "fc6"
+  dropout_param {
+    dropout_ratio: 0.5
+  }
+}
+layer {
+  name: "fc7"
+  type: "InnerProduct"
+  bottom: "fc6"
+  top: "fc7"
+  inner_product_param {
+    num_output: 4096
+  }
+}
+layer {
+  name: "relu7"
+  type: "ReLU"
+  bottom: "fc7"
+  top: "fc7"
+}
+layer {
+  name: "drop7"
+  type: "Dropout"
+  bottom: "fc7"
+  top: "fc7"
+  dropout_param {
+    dropout_ratio: 0.5
+  }
+}
+layer {
+  name: "myfc8"
+  type: "InnerProduct"
+  bottom: "fc7"
+  top: "myfc8"
+  inner_product_param {
+    num_output: 7
+  }
+}
+layer {
+  name: "prob"
+  type: "Softmax"
+  bottom: "myfc8"
+  top: "prob"
+}