Investigation of image processing methods based on photographs for automatic posture recognition

Japan has the highest aging rate worldwide, underscoring the importance of maintaining daily health for older adults. Postural assessment serves as a valuable indicator of health status. The purpose of this study is to construct an automatic posture recognition model using photographs. As a preliminary investigation, pre-processing methods suitable for machine learning datasets was examined. A total of 278 older adults from sagittal were captured using Kinect v2. the photographs were cropped to exclude non-relevant areas and transformed into grayscale. Subsequently, the cropped images underwent background removed, four edge-detection methods (Prewitt, Sobel, Laplacian 4-neighbors, and Laplacian 8-neighbors), and silhouette extraction, respectively, along with the original images, resulting in seven distinct datasets. A posture the images were classified into Ideal and Non-ideal categories according to physical therapists. The recognition model employed a Support Vector Machine (SVM), with feature extraction methods utilizing Scale-Invariant Feature Transform (SIFT) and Speeded-Up Robust Features (SURF). The dataset was divided into training (70%) and test (30%) subsets, with 15 cross-validation sets generated for robustness. Results showed that the Prewitt edge detection method achieved the highest average of F1 score (0.45 ± 0.07) with SIFT, while silhouette extraction yielded the best performance (0.48 ± 0.08) with SURF. The overall accuracy was relatively low; however, when compared to the cropping images, all methods demonstrated higher values, and the order of accuracy was clearly established. These results suggest that further improvements in accuracy could be achieved through tuning the recognition model, highlighting the potential applicability to deep learning frameworks.