Glaucoma, a primary cause of irreversible blindness, necessitates early detection to prevent significant vision loss. In the literature, fundus imaging is identified as a key tool in diagnosing glaucoma, which captures detailed retina images. However, manual analysis of these images can be time-consuming and subjective. Thus, this paper presents an automated system for glaucoma detection using fundus images, combining diverse feature extraction methods with advanced classifiers, specifically Support Vector Machine (SVM) and AdaBoost (ADB). The pre-processing step incorporates Image Enhancement via Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance image quality and feature extraction. This work investigates individual features such as Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP), Chip Histogram Features, and Gray Level Co-occurrence Matrix (GLCM), as well as their various combinations, including HOG + LBP + Chip Histogram + GLCM, HOG + LBP + Chip Histogram, and others. These features are utilized with SVM and ADB classifiers to improve classification performance. For validation, the ACRIMA dataset, a public fundus image collection comprising 369 glaucoma-affected and 309 normal images is used in this work, with 80% of the data allocated for training and 20% for testing. The results of the proposed study show that different feature sets yield varying accuracies with SVM and ADB classifiers. For instance, the combination of LBP + Chip Histogram achieved the highest accuracy of 99.29% with ADB, while the same combination yielded 65.25% accuracy with SVM. The individual feature LBP alone achieved 97.87% with ADB and 98.58% with SVM. Furthermore, the combination of GLCM + LBP provided 98.58% accuracy with ADB and 97.87% with SVM. The results demonstrate that CLAHE and combined feature sets significantly enhance detection accuracy, providing a reliable tool for early and precise glaucoma diagnosis, thus facilitating timely intervention and improved patient outcomes.