Electronics Optics & Control, Volume. 26, Issue 12, 44(2019)
Cost Function Selection and Performance Evaluation for Digital Image Recognition
In order to solve the problem that the accuracy of image recognition is not high in the training process of convolutional neural network by using traditional quadratic cost functiona convolutional neural network algorithm based on cross-entropy cost function is proposed.By mathematical derivationit is proved that the cross-entropy cost function is more accurate than the quadratic cost function in image recognition.Based on MNIST dataset and CIFAR-10 datasetand using AlexNet convolutional neural networkthe quadratic cost function and the cross-entropy cost function are adopted to train the image recognition model respectively.When the recognition accuracy and loss value of the digital image are stablethe cost function is tested several times by using the test dataand comparison is made to the recognition accuracy of the two functions.The simulation results show that the proposed method can not only improve the accuracy of digital image recognitionbut also has a faster model training speed than the traditional cost function.The process of training deep neural network model is obviously shortened.
Get Citation
Copy Citation Text
LI Zhong-de, LU Xiang-ri, CUI Gui-mei. Cost Function Selection and Performance Evaluation for Digital Image Recognition[J]. Electronics Optics & Control, 2019, 26(12): 44
Category:
Received: Jan. 2, 2019
Accepted: --
Published Online: Feb. 11, 2020
The Author Email: