This study, we propose a solution to apply artificial intelligence to assist in detecting whether a person may have melasma or not through data sets related to information about a person's daily activities, then If we detect a person with a high likelihood of having melasma, we will apply machine learning to diagnose the type of melasma through a photo taken of that person. Through a machine learning model of predicting and diagnosing a person's melasma, we also suggest relevant prevention and treatment options based on the disease's prevention and treatment regimen. Our method build predict Melasma model based on Catboost machine learning algorithm on users' data combined with medical practice data commu-nity by dermatologists to predict the disease and make some necessary recommendations in the patient screening. Based on our dataset, we have statistically described the data characteristics as well as the correlated data parameters that may cause Melasma. The method using for diagnosing melasma disease based on machine learning algorithms with input data being facial images. we built a machine learning model for diagnosing melasma to detect melasma objects to support dermatologists in predicting the risk of melasma in a person after entering his/her facial image. Our dataset of facial images combined with the expertise of melasma experts to classify different types of melasma. We used YOLO V8 with machine learning algorithms to detect melasma objects to build a diagnostic model for whether a patient has melasma and with which type of melasma such as central melasma, butterfly-shaped melasma, or mandibular melasma.
Most fruit classification studies rely on color-based features, but shape-based analysis provides a promising alternative for distinguishing subtle variations within the same variety. Tomato shape classification is challenging due to irregular contours, variable imaging conditions, and difficulty in extracting consistent geometric features. In this study, we propose an efficient and structured workflow to address these challenges through contour-based analysis. The process begins with the application of a Mask Region-based Convolutional Neural Network (Mask R-CNN) model to accurately isolate tomatoes from the background. Subsequently, the segmented tomatoes are extracted and encoded using Elliptic Fourier Descriptors (EFDs) to capture detailed shape characteristics. These features are used to train a range of machine learning models, including Support Vector Machine (SVM), Random Forest, One-Dimensional Convolutional Neural Network (1D-CNN), and Bidirectional Encoder Representations from Transformers (BERT). Experimental results observe that the Random Forest model achieved the highest accuracy of 79.4%. This approach offers a robust, interpretable, and quantitative framework for tomato shape classification, reducing manual labor and supporting practical agricultural applications.