Training Network Design Based on Convolution Neural Network for Object Classification in few class problem

Abstract

Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.키워드 : 딥러닝, 신경망, 객체 분류, 컨볼루션신경망

A Study on Mushroom Pest and Diseases Analysis System Implementation based on Convolutional Neural Networks for Smart Farm

“…CNN especially shows a high recognition rate in image analysis. CNN is a classification model that learns and identifies what an image is when it is input into a composite neural network [5][6]. When an image is given, the CNN model uses a method of reducing the image through the convolution layer, the pooling layer, and the feedforward layer, and it finally extracts and classifies the features from the image.…”