Normalization of data for training and analysis by the MaskRCNN model using the k-means method for a smart refrigerator’s computer vision

Abstract

The authors propose to use the k-means method for semantic image segmentation in the artificial vision of a smart refrigerator. The authors have developed a new two-tier architecture for the semantic segmentation system. In the proposed architecture, various sets of image contrast optimization settings are used to classify pixels belonging to fragments of the studied image. Experiments have shown that the proposed method has decisive advantages over existing works. The k-means method was used to cluster pixels directly into semantic groups. The clustered data is used to solve the semantic segmentation problem. For the correct selection of the number of centroids of the k-means method, the mean shift method was used. Extensive experiments with the traditional k-means algorithm and mean shift method have shown the advantage of the proposed approach in accuracy and performance.

Teachers’ Teaching Ability Promotion Strategies Based on Lightweight Deep Learning Combined with Target Detection Algorithm

“…It is more than 8% higher than the Faster R-CNN and the Mask R-CNN, 4% higher than the YOLOv3, and 6% higher than the Tiny YOLOv3 [ 26 ]. Additionally, the recall of the proposed model is higher than that of the Faster R-CNN model and the Mask R-CNN model [ 27 ]. Hence, the proposed improved YOLOv3 model can better trade-off recall and prediction accuracy.…”

Machine Learning-Based Virtual Sensors for Guiding User Behaviour: A Case Study on Household Appliances

“…This gap is usually overcome only if there are particularly advantageous economic aspects or in the presence of a brandnew function. There are different authors (Zhang, et al, 2018), (Anon., 2021), (Jain, et al, 2021) that are focused on the application of image recognition for food inside refrigerators. Despite this not being the exact application of the Virtual Sensor on a refrigerator, it is a topic of particular relevance because of its affinity in terms of applied algorithms and possible development.…”