Depression is a pervasive mental health disorder affecting millions worldwide, often leading to profound personal and societal consequences. An accurate and timely diagnosis is essential for managing and treating conditions effectively. The use of Electroencephalography (EEG) signals in depression analysis has acquired critical consideration due to their potential for non-invasive and objective disorder assessment. This research presents a novel approach for depression analysis using EEG signals, leveraging the power of deep learning techniques. EEG data collected from individuals with and without depression are pre-processed to extract relevant features and a deep neural network is designed and trained for classification. The deep learning model, such as a convolutional neural network (CNN), is employed to automatically learn and recognize complex patterns within the EEG signals associated with depression. Our findings reveal that deep learning-based models can effectively discriminate between depressed and non-depressed individuals, achieving high classification accuracy. Overall, this work represents a significant step toward improving mental health assessment and treatment by integrating advanced deep learning techniques and EEG signal analysis. In this system, we compare the accuracy with Support Vector Machine (SVM) and Convolutional Neural Network (CNN). We got 76% accuracy on the SVM and 97.69% accuracy on the CNN classifier.