Abstract
Currently, there are many limitations to classify images of small objects. In addition, there are limitations such as error detection due to external factors, and there is also a disadvantage that it is difficult to accurately distinguish between various objects. This paper uses a convolutional neural network (CNN) algorithm to recognize and classify object images of very small moths and obtain precise data images. A convolution neural network algorithm is used for image data classification, and the classified image is transformed into image data to learn the topological structure of the image. To improve the accuracy of the image classification and reduce the loss rate, a parameter for finding a fast-optimal point of image classification is set by a convolutional neural network and a pixel image as a preprocessor. As a result of this study, we applied a convolution neural network algorithm to classify the images of very small moths by capturing precise images of the moths. Experimental results showed that the accuracy of classification of very small moths was more than 90%.
Highlights
With the amount of image data collected from smartphones, CCTV, BLACK BOXS, etc., there is an increasing demand for analyzing and utilizing the contents visually for the meaningful extraction of information by recognizing people, objects, and so on [1]
The fully connected layer (FC layer) used as input data in artificial neural networks (ANN) is a layer in which all nodes of from the previous layer are connected to all nodes of from the layer
After learning a target object and other objects using a convolutional neural network (CNN), we proposed a method of detecting object candidates using image data input by the target object
Summary
With the amount of image data collected from smartphones, CCTV, BLACK BOXS, etc., there is an increasing demand for analyzing and utilizing the contents visually for the meaningful extraction of information by recognizing people, objects, and so on [1]. To increase the accuracy of the object, high image quality image data is collected and necessary object data is extracted. The extracted object image can be learned by applying the deep learning algorithm, and the object’s type of the object can be selected [2,3,4]. The fully connected layer (FC layer) used as input data in artificial neural networks (ANN) is a layer in which all nodes of from the previous layer are connected to all nodes of from the layer. The input data of an ANN composed only of a FC layer is limited to a one-dimensional (array) form [5]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have