Detection of Parkinson’s Disease at The Level of Motor Experiences of Daily Living Using Spiral Handwriting

Parkinson's disease (PD) is a neurological disease that gradually worsens and affects the brain's part that functions to coordinate body movements. As a result, sufferers have difficulty regulating body movements, including when talking, walking, and writing. The diagnosis of PD patients can be analyzed through handwriting. Measurement of Parkinson's disease at the level of motor experiences of daily living uses handwriting tasks. This paper aims to evaluate various image feature extraction techniques from handwriting. Handwriting were collected from 102 subjects (51 PD and 51 healthy control (HC)) The proposed method uses feature extraction of Histogram of Gradient (HOG), Oriented FAST and Rotated BRIEF (ORB), Speed-Up Robust Feature (SURF), Scale Invariant Feature Transform (SIFT), Color Gradient Histogram (CGH) and KAZE. Classifiers based on Random Forest (RF). The analysis shows that the extraction features of HOG and RF classification have the best accuracy 0.8167.