Attention Deficit Hyperactivity Disorder (ADHD) is a neurological condition, typically manifesting in childhood. Behavioral studies are used to treat the illness, but there is no conclusive way to diagnose it. In order to comprehend changes in the brain, electroencephalography (EEG) signals of ADHD patients are frequently examined. In the proposed study, we introduced EEG feature maps (EEG-FM)-based image construction to be used as input to CNN architectures. To demonstrate the effectiveness of the proposed method, EEG data of 15 ADHD patients and 18 control subjects are analyzed and ADHD detection performance is demonstrated. EEG-FM-based images are obtained using both time domain features such as Hjorth parameters (activity, mobility, complexity), skewness, kurtosis, and peak-to-peak, and nonlinear features such as largest Lyapunov Exponent, correlation dimension, Hurst exponent, Katz fractal dimension, Higuchi fractal dimension, and approximation entropy. ResNet18 is trained using EEG-FM-based images and deep features are extracted for each image subset. Using the SVM classifier, the ADHD detection performance of the proposed approach is evaluated. Experimental results revealed that using EEG-FM-based images as input to ResNet architecture offers important benefits in identifying ADHD.