The objective of this research is to develop an intelligent information system to recognize rice seeds variety based on image processing and artificial neural network (ANN). At first, images of rice seeds were acquired with a color machine vision system. Each image was processed to extract twenty-one quantitative features. The classification ability of all the features was evaluated for different varieties recognition. To ensure system reasoning veracity and intelligence, ANN was used. A digital image-processing algorithm was developed to classify varieties of rice seeds based on external features. As an example of application of the system, the image data of common rice seeds varieties in Zhejiang province were input and the results of practical application proved that this software system achieved desired results.

Intelligent home systems interconnect various devices within the home using Internet of Things (IoT) technology. In order to achieve the objectives of remote control, automated management, and intelligent services, these systems require robust scene recognition capabilities. However, the accuracy and real-time performance of current image processing algorithms in complex environments and diverse scenarios remain to be improved. Additionally, the interoperability and security issues among intelligent home devices are challenging to address. Therefore, this study delves into the scene recognition technology of intelligent homes based on image processing and IoT. A GLN network is constructed to process multi-view images of intelligent home scenes, enabling the determination of subregion positions within the scenes. A model aggregation algorithm based on distributed learning is proposed, selecting intelligent home edge devices as the intelligent nodes of the IoT. By processing data and training models on these intelligent nodes, distributed intelligent home scene recognition is achieved. A dual-channel deep neural network-based intelligent home scene recognition model is constructed, and experimental results verify the effectiveness of the proposed model.