Visually, it is difficult to differentiate between smoker and non-smoker tongue even for an experienced doctor or dentist. One of the most objective ways to acknowledge the smoker tongue is by using tools such as a camera. The proposed system contains two parts, hardware, and software. The hardware consists of a workbench, slider, a halogen light source and hyperspectral camera with a spectral range between 400-1000 nm connected to a personal computer. The system complemented with image processing software built up especially to analyze the smoker tongue. The reflectance values of the tongue surface were extracted from respondent tongue image that previously corrected using white and dark hyperspectral image references. The principal component analysis (PCA) was used to compute and select the features subset which will be used as an input by the classifier. The support vector machine (SVM) classifier is used as image classification model since it performs excellently to choose the best hyperplane separator between two different classes. The evaluation of system result is checked using confusion matrix by making false positive rate (FPR), false negative rate (FNR), sensitivity and specificity as system reliability parameters. A Smoker detection system to identify smoker's melanosis is successfully classify the tongue of smokers and non-smokers with reasonable accuracy.