Year-end Sale % OFF 
Abstract
As the Internet of Things (IoT) is predicted to deal with different problems based on big data, its applications have become increasingly dependent on visual data and deep learning technology, and it is a big challenge to find a suitable method for IoT systems to analyze image data. Traditional deep learning methods have never explicitly taken the color differences of data into account, but from the experience of human vision, colors play differently significant roles in recognizing things. This paper proposes a weight initialization method for deep learning in image recognition problems based on RGB influence proportion, aiming to improve the training process of the learning algorithms. In this paper, we try to extract the RGB proportion and utilize it in the weight initialization process. We conduct several experiments on different datasets to evaluate the effectiveness of our proposal, and it is proven to be effective on small datasets. In addition, as for the access to the RGB influence proportion, we also provide an expedient approach to get the early proportion for the following usage. We assume that the proposed method can be used for IoT sensors to securely analyze complex data in the future.
Highlights
The Internet of Things (IoT) is designed for making everything in our living environment integrated to improve quality of life [1]
Motivated by the fact that color difference plays an important part in image recognition, this paper proposed a novel solution to explicitly make use of the RGB proportion in the initialization process for convolution neural network (CNN)
The proposed method was applied based on the traditional initialization method, which is designed to use a pre-training method to emulate the RGB distribution after being trained
Summary
The Internet of Things (IoT) is designed for making everything in our living environment integrated to improve quality of life [1]. The data need to be obtained from visual sensing devices. There is gesture recognition for unlocking in the smart home, image segmentation for judgments in autonomous driving, medical image analysis in the health care system, and so forth [4,5,6]. When an IoT system integrates with visual sensors like complementary metal oxide semiconductor (CMOS) image sensors [7], a huge amount of data will be collected or generated by them [8], and these data need to be analyzed fast in order to achieve better communication of devices in the IoT system [9,10].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
